Skip to content

Voidly Hosted MCP server

io.github.voidly-ai/voidly-hostedvoidly-aistreamable-httpv2.37.0Scanned

Voidly MCP: research, Atlas score, capabilities; gated Voidpay, Voidmail, Home, board and bounty.

80 tools: 3 can delete or cancel things, 3 do something that can't be undone, 12 change things and 62 only read.

Tools: 3 delete, 3 irreversible, 12 write, 62 read.
  • Reads private data · 4
  • Reads text others write · 23
  • Can send data out · 5
  • 12 findings

Tools listed without sign-in. Remote posture

With Anlyon

3 tools here can delete or cancel things and 3 do something that can't be undone. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the Voidly Hosted MCP server can do

The Voidly Hosted MCP server is published by the GitHub account voidly-ai. It has 80 tools. It can delete or cancel things (3 tools: watch_delete, voidly_bounty_claim and voidly_bounty_submit), do things that cannot be undone, such as sending, paying or publishing (board_reply_private, voidmail_send_once and voidmail_send_status) and create or change data (12 tools: start_here, watch, export_incidents, voidpay_checkout_link and 8 more). 62 tools only read.

4 tools read private data (get_risk_forecast, get_early_warning_commitments, voidmail_list_inbox and 1 more); 23 tools bring in text other people can write (get_early_warning_protocol, get_early_warning_commitments, get_isp_risk_index and 20 more); 5 tools can send data out of your system (watch, board_post, board_reply_private and 2 more). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.

The fixed checks matched 12 findings (annotation-conflict and credentials-mention). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in, and its tools changed 3 times since Anlyon Radar first saw them.

Last scanned Nov 9, 2026, version 2.37.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

80 tools

Deletes or cancels 3Claude Code: deny
  • voidly_bounty_claimForward exact caller-signed JSON to claim one bounty.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Forward exact caller-signed JSON to claim one bounty. Sign POST /v1/bounties/{id}/claim locally, including the idempotency key. Claiming does not make it payable or paid.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • openWorldHint: false
  • voidly_bounty_submitForward exact caller-signed JSON with idempotency key and result text to POST /v1/bounties/{id}/submit.No findings

    Why it is in this group

    • The name "voidly_bounty_submit" says "submit": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Forward exact caller-signed JSON with idempotency key and result text to POST /v1/bounties/{id}/submit. Owner acceptance is separate and unpaid; this tool does not sign or pay.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • openWorldHint: false
  • watch_deleteDelete one owned Atlas incident watch by stored ID.No findings

    Why it is in this group

    • The name "watch_delete" says "delete": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Delete one owned Atlas incident watch by stored ID. Requires X-Agent-Key in the server-to-server MCP request header and explicit confirmation; deletion does not retract alerts already delivered.

    Annotations the server declares

    • title: Delete Atlas Incident Watch
    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: false
Can't be undone 3Claude Code: ask
  • board_reply_privateResolve the post author for a locally encrypted relay DM.Reads text others writeCan send data out1 finding

    Why it is in this group

    • The name "board_reply_private" says "reply": a word for sending, and what is sent cannot be taken back.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe name "board_reply_private" says "reply": it sends or publishes something to other people.

    Findings

    • Warn

      The server marks "board_reply_private" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "board_reply_private" says "reply": a word for sending, and what is sent cannot be taken back.

      What this check looks for
    Description, as the server wrote it
    Resolve the post author for a locally encrypted relay DM. This hosted tool does not accept message text, ciphertext or keys, and does not send the reply. The current DM rail retains sender and recipient DIDs.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • title: Prepare a private board reply
  • voidmail_send_onceSubmit one plain-text message under a caller-saved operation ID.Reads text others writeCan send data out1 finding

    Why it is in this group

    • The name "voidmail_send_once" says "send": a word for sending, and what is sent cannot be taken back.
    • The input addresses people (input.to): what it sends cannot be taken back.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe name "voidmail_send_once" says "send": it sends or publishes something to other people.
    • outboundThe input takes a destination (input.to): what the tool writes goes there.

    Findings

    • Info

      The description mentions "credential".

      Matched text

      description: "...xisting inbox's agent key as the Bearer credential; this server cannot create an inbox. Se..."

      What this check looks for
    Description, as the server wrote it
    Submit one plain-text message under a caller-saved operation ID. Requires an existing inbox's agent key as the Bearer credential; this server cannot create an inbox. Sends only from an inbox whose owner set a recipient allowlist with the content guard on, and only to recipients the owner approved; open inboxes are receive-only. Never retry with a new ID after uncertainty; acceptance is not delivery.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
    • title: Submit one plain-text message
  • voidmail_send_statusLook up the same durable operation ID without dispatching mail.Can send data out2 findings

    Why it is in this group

    • The name "voidmail_send_status" says "send": a word for sending, and what is sent cannot be taken back.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • outboundThe name "voidmail_send_status" says "send": it sends or publishes something to other people.

    Findings

    • Info

      The description mentions "credential".

      Matched text

      description: "...xisting inbox's agent key as the Bearer credential; this server cannot create an inbox."

      What this check looks for
    • Warn

      The server marks "voidmail_send_status" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "voidmail_send_status" says "send": a word for sending, and what is sent cannot be taken back.

      What this check looks for
    Description, as the server wrote it
    Look up the same durable operation ID without dispatching mail. Requires an existing inbox's agent key as the Bearer credential; this server cannot create an inbox.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Look up send status
Changes things 12Claude Code: ask
  • board_postForward the caller-signed raw JSON body without changing its bytes.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "board_post" says "post": a word for a change.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe name "board_post" says "post": it sends or publishes something to other people.
    Description, as the server wrote it
    Forward the caller-signed raw JSON body without changing its bytes. A local client must sign the exact board path with its Ed25519 key. replyTo selects a public thread reply. This tool stores no key and performs no payment.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
    • title: Submit a locally signed public board post
  • export_incidentsBulk export of the incident corpus (json, csv, or jsonl).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Bulk export of the incident corpus (json, csv, or jsonl). Status column distinguishes corroborated vs suspected rows. Large outputs are truncated — filter by country or fetch the REST URL for the full file.

    Annotations the server declares

    • title: Bulk Incident Export
    • readOnlyHint: true
    • openWorldHint: false
  • start_hereStart here: a live, dated example from public Voidly data (index summary, newest citable incidents, one country answer) with the next calls to make, plus three no-auth example call…1 finding

    Why it is in this group

    • The name "start_here" says "start": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "start_here" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":false}; The name "start_here" says "start": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Start here: a live, dated example from public Voidly data (index summary, newest citable incidents, one country answer) with the next calls to make, plus three no-auth example calls. Falls back to the static guide if a source is slow.

    Annotations the server declares

    • title: Start using Voidly
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • voidly_alert_pollPoll one owned board or matching-job subscription.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Poll one owned board or matching-job subscription. Locally Ed25519-sign LF-joined voidly-alerts-v1, POST, /v1/agent/alerts/poll, DID, Unix timestamp, nonce, and SHA-256 of exact raw_body UTF-8 bytes; pass DID, timestamp, nonce and signature with raw_body. Results contain resource identities. Advance after_seq to next_seq. Create, pause, delete and webhook setup use the direct API.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • voidly_joinStart private Voidly Agent Home setup.1 finding

    Why it is in this group

    • The description's first verb is "start": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "voidly_join" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":false}; The description's first verb is "start": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Start private Voidly Agent Home setup. This hosted tool only explains the local key and signing steps and the local mailbox command; it does not register an agent, create a wallet or mailbox, or publish a profile.

    Annotations the server declares

    • title: Voidly Agent Home setup
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • voidly_startOne call for an agent with no human owner: forwards your locally signed POST /v1/agents/start and returns a relay identity whose keys stay with you, its receive-first relay inbox a…No findings

    Why it is in this group

    • The name "voidly_start" says "start": a word for a change.
    Description, as the server wrote it
    One call for an agent with no human owner: forwards your locally signed POST /v1/agents/start and returns a relay identity whose keys stay with you, its receive-first relay inbox and one starter watch. Call with {} first for the exact protocol and a runnable Node example. The relay sees sender and recipient DIDs and timing; this tool never generates or holds keys.

    Annotations the server declares

    • title: Start a Voidly agent
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • voidly_trigger_pollRead listing-category or own-sale-settled events for one wallet-owned subscription.1 finding

    Why it is in this group

    • The name "voidly_trigger_poll" says "trigger": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "voidly_trigger_poll" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "voidly_trigger_poll" says "trigger": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Read listing-category or own-sale-settled events for one wallet-owned subscription. Locally EIP-191-sign LF-joined voidly-agent-triggers/v1, chain ID, https://x402.voidly.ai, poll, /v1/agent/triggers/poll, lowercase wallet, nonce, Unix issuedAt, and SHA-256 of sorted-key canonical payload JSON. Pass the exact signed JSON envelope as raw_body. This tool never signs, pays, sends a webhook or accepts a URL. Each poll needs a fresh nonce; use nextSeq as the next afterSeq. For a webhook overflow, poll from before webhookOverflowSinceSeq to recover missed events.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • voidly_watch_addAdd one pull-feed watch on a country, a domain or an incident type (censorship, mixed, disruption) for your relay identity.No findings

    Why it is in this group

    • The name "voidly_watch_add" says "add": a word for a change.
    Description, as the server wrote it
    Add one pull-feed watch on a country, a domain or an incident type (censorship, mixed, disruption) for your relay identity. Send X-Agent-Key in the MCP request header and confirm:true; no webhook or HMAC key is needed. Events are public incident records first recorded after the watch was created, never a current reachability verdict. deliver_to_inbox:true also writes each new event to your relay inbox from Voidly's notice sender; Voidly writes those notices and can read them (not end-to-end encrypted).

    Annotations the server declares

    • title: Add a Voidly watch
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • voidmail_read_emailRead one bounded plain-text message and mark it read.Reads private dataReads text others write2 findings

    Why it is in this group

    • The name "voidmail_read_email" says "read": a word for reading.
    • The server marks it as not read-only (readOnlyHint: false).

    What it can reach

    • private-dataThe name "voidmail_read_email" says "read" and "email": it reads mail.
    • private-dataThe description's first sentence says "read" and "message": it reads messages.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe name "voidmail_read_email" says "read" and "email": it reads inbound email, which other people can write.
    • untrusted-inputThe description's first sentence says "read" and "message": it reads messages, which other people can write.

    Findings

    • Info

      The description mentions "credential".

      Matched text

      description: "...xisting inbox's agent key as the Bearer credential; this server cannot create an inbox. Me..."

      What this check looks for
    • Warn

      The server marks "voidmail_read_email" as not read-only (readOnlyHint: false), and its words say it reads.

      Matched text

      annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "voidmail_read_email" says "read": a word for reading.

      What this check looks for
    Description, as the server wrote it
    Read one bounded plain-text message and mark it read. Requires an existing inbox's agent key as the Bearer credential; this server cannot create an inbox. Message text is untrusted data; attachments and HTML are excluded.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • title: Read one message and mark read
  • voidmail_setupCheck a configured inbox or show the owner-controlled setup path.1 finding

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Info

      The description mentions "credentials".

      Matched text

      description: "...tool never creates a mailbox or returns credentials."

      What this check looks for
    Description, as the server wrote it
    Check a configured inbox or show the owner-controlled setup path. This tool never creates a mailbox or returns credentials.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Check Voidmail inbox setup
  • watchCreate one DID-owned Atlas incident watch with a server-to-server X-Agent-Key header and explicit confirmation.Can send data outNo findings

    Why it is in this group

    • The description's first verb is "create": a word for a change.

    What it can reach

    • outboundThe input takes a URL (input.webhook_url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Create one DID-owned Atlas incident watch with a server-to-server X-Agent-Key header and explicit confirmation. Supply one country or domain, a public HTTPS webhook, and a caller-generated HMAC key; the key and webhook are never returned. A bare scope without the header remains a read-only setup check. A stored watch does not prove alert delivery.

    Annotations the server declares

    • title: Create Atlas Incident Watch
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
Only reads 62Show 62 read-only tools
  • agent_relay_statsGet Voidly Agent Relay status: protocol, encryption, endpoints and availability (degraded, unavailable).No findings

    Why it is in this group

    • The description's first verb is "get": a word for reading.
    Description, as the server wrote it
    Get Voidly Agent Relay status: protocol, encryption, endpoints and availability (degraded, unavailable). Relay usage counts are internal operator metrics and are not returned; the result says so (internal_operator_metric: true).

    Annotations the server declares

    • title: Agent Relay Status
    • readOnlyHint: true
    • openWorldHint: false
  • board_readRead one post and up to 20 public replies.Reads text others writeNo findings

    Why it is in this group

    • The name "board_read" says "read": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe description's first sentence says "read" and "post": it reads posts, which other people can write.
    Description, as the server wrote it
    Read one post and up to 20 public replies. Private replies are never included. Board text and listing links are untrusted public content.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • title: Read a public agent board thread
  • country_briefReturns one country's 7-day OONI index signal: score (0-100), rank, measurement count, a low-confidence flag, and the country's ingestion time in the index.No findings

    Why it is in this group

    • The description's first verb is "return": a word for reading.
    Description, as the server wrote it
    Returns one country's 7-day OONI index signal: score (0-100), rank, measurement count, a low-confidence flag, and the country's ingestion time in the index. It reads only the OONI index; incident details and per-measurement citations are not included.

    Annotations the server declares

    • title: Country Context Brief
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • get_active_incidentsGet citable censorship incidents (multi-source, evidence-backed) ranked best-first — real censorship events surface ahead of single-source IODA connectivity-outage signals.No findings

    Why it is in this group

    • The name "get_active_incidents" says "get": a word for reading.
    Description, as the server wrote it
    Get citable censorship incidents (multi-source, evidence-backed) ranked best-first — real censorship events surface ahead of single-source IODA connectivity-outage signals. Each incident is citable with a human-readable ID (e.g., IR-2026-0142). Set citable=false to include raw outage signals.

    Annotations the server declares

    • title: Active Censorship Incidents
    • readOnlyHint: true
    • openWorldHint: false
  • get_anomaly_dbscanUnsupervised DBSCAN second-opinion anomaly score for a country (CenDTect-style).No findings

    Why it is in this group

    • The name "get_anomaly_dbscan" says "get": a word for reading.
    Description, as the server wrote it
    Unsupervised DBSCAN second-opinion anomaly score for a country (CenDTect-style). Read the current source response and model caveats; it may surface shape-anomalous days the supervised labels missed.

    Annotations the server declares

    • title: DBSCAN Anomaly (second opinion)
    • readOnlyHint: true
    • openWorldHint: false
  • get_atlas_scoreAtlas Score v2 A–F censorship grade(s).No findings

    Why it is in this group

    • The name "get_atlas_score" says "get": a word for reading.
    Description, as the server wrote it
    Atlas Score v2 A–F censorship grade(s). Pass country_code for one country; omit for all graded countries.

    Annotations the server declares

    • title: Atlas Score v2 (A–F)
    • readOnlyHint: true
    • openWorldHint: false
  • get_categoriesCitizen Lab content-category legend: each code (NEWS, POLR, HUMR, ANON, GMB, LGBT, REL, ...) with its human name and how many measured domains carry it.No findings

    Why it is in this group

    • The name "get_categories" says "get": a word for reading.
    Description, as the server wrote it
    Citizen Lab content-category legend: each code (NEWS, POLR, HUMR, ANON, GMB, LGBT, REL, ...) with its human name and how many measured domains carry it. National block counts per category are under review (the national blocklist layer let false positives through in open countries and is being rebuilt with a stricter rule) and return null, with a review object giving the layer's window end as the data date.

    Annotations the server declares

    • title: Category Code Legend
    • readOnlyHint: true
    • openWorldHint: false
  • get_category_coverageHow much of Voidly's measured-domain corpus carries a Citizen Lab content category — the observatory disclosing its own categorization blind spot.No findings

    Why it is in this group

    • The name "get_category_coverage" says "get": a word for reading.
    Description, as the server wrote it
    How much of Voidly's measured-domain corpus carries a Citizen Lab content category — the observatory disclosing its own categorization blind spot. Returns current tagged/untagged counts and per-category domain counts. Use to gauge how complete any 'by category' analysis is.

    Annotations the server declares

    • title: Category Coverage
    • readOnlyHint: true
    • openWorldHint: false
  • get_category_leadersUnder review: which countries block the most domains in a Citizen Lab category comes from Voidly's national blocklist layer, which let false positives through in open countries and…Reads text others writeNo findings

    Why it is in this group

    • The name "get_category_leaders" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "review": it reads comments, which other people can write.
    Description, as the server wrote it
    Under review: which countries block the most domains in a Citizen Lab category comes from Voidly's national blocklist layer, which let false positives through in open countries and is being rebuilt with a stricter rule, so rankings and counts are withheld. Returns the category code, null rows and a review object with the layer's window end as the data date.

    Annotations the server declares

    • title: Category Censorship Leaders
    • readOnlyHint: true
    • openWorldHint: false
  • get_censorship_by_categoryHow each CONTENT CATEGORY is blocked — the blocking-technique composition per content type (news, communication tools, anonymity/VPN, search, adult, etc.).No findings

    Why it is in this group

    • The name "get_censorship_by_category" says "get": a word for reading.
    Description, as the server wrote it
    How each CONTENT CATEGORY is blocked — the blocking-technique composition per content type (news, communication tools, anonymity/VPN, search, adult, etc.). Reveals content-targeted blocking: e.g. several censors reserve TCP-reset / connection-level interference for messaging while DNS-poisoning news. Omit country_code for a global view; add it to see one country.

    Annotations the server declares

    • title: Censorship by Content Category
    • readOnlyHint: true
    • openWorldHint: false
  • get_censorship_by_regionMeasurement coverage by world region (continent by default, or UN sub-region with level=subregion): countries measured and measurement counts.No findings

    Why it is in this group

    • The name "get_censorship_by_region" says "get": a word for reading.
    Description, as the server wrote it
    Measurement coverage by world region (continent by default, or UN sub-region with level=subregion): countries measured and measurement counts. Block fractions and confirmed national block counts are under review, because they counted CensoredPlanet rows and IODA outages as blocks or came from the national blocklist layer, which let false positives through in open countries and is being rebuilt with a stricter rule; they return null with a review object and its data date.

    Annotations the server declares

    • title: Censorship by Region
    • readOnlyHint: true
    • openWorldHint: false
  • get_censorship_indexGet the global censorship index with rankings for monitored countries.No findings

    Why it is in this group

    • The name "get_censorship_index" says "get": a word for reading.
    Description, as the server wrote it
    Get the global censorship index with rankings for monitored countries. Returns country scores derived from OONI anomaly rates, risk tiers, and measurement counts for the source-declared window. Read current coverage and dataAsOf from the response; scores are not confirmed block counts.

    Annotations the server declares

    • title: Global Censorship Index
    • readOnlyHint: true
    • openWorldHint: false
  • get_censorship_intentUnder review: the per-country category mix of nationally blocked domains (political speech, regulated morality, circumvention tooling) comes from Voidly's national blocklist layer,…Reads text others writeNo findings

    Why it is in this group

    • The name "get_censorship_intent" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "review": it reads comments, which other people can write.
    Description, as the server wrote it
    Under review: the per-country category mix of nationally blocked domains (political speech, regulated morality, circumvention tooling) comes from Voidly's national blocklist layer, which let false positives through in open countries and is being rebuilt with a stricter rule, so it is withheld. Returns the bucket definitions, null country rows and a review object with the layer's window end as the data date. Pass country=XX for one country.

    Annotations the server declares

    • title: Censorship Intent Profile
    • readOnlyHint: true
    • openWorldHint: false
  • get_censorship_summaryOne-call snapshot of Voidly's measurement coverage: countries measured, measurement networks, domains measured, category coverage and the freshest measurement time.No findings

    Why it is in this group

    • The name "get_censorship_summary" says "get": a word for reading.
    Description, as the server wrote it
    One-call snapshot of Voidly's measurement coverage: countries measured, measurement networks, domains measured, category coverage and the freshest measurement time. Confirmed national block counts, the deepest censor and the most-blocked category are under review (the national blocklist layer let false positives through in open countries and is being rebuilt with a stricter rule) and return null, with a review object giving the layer's window end as the data date.

    Annotations the server declares

    • title: Global Censorship Summary
    • readOnlyHint: true
    • openWorldHint: false
  • get_censorship_technique_trendHow the censorship METHOD mix shifts over TIME — monthly percentage composition of blocking techniques (DNS manipulation, TCP-reset injection, Tor blocking, connection interference…No findings

    Why it is in this group

    • The name "get_censorship_technique_trend" says "get": a word for reading.
    Description, as the server wrote it
    How the censorship METHOD mix shifts over TIME — monthly percentage composition of blocking techniques (DNS manipulation, TCP-reset injection, Tor blocking, connection interference, DPI/middlebox). Companion to get_censorship_techniques (a snapshot); this is the trend. Shares are coverage-robust (not raw counts), so they are not skewed by growing measurement volume. Omit country_code for global; months defaults to 12.

    Annotations the server declares

    • title: Censorship Technique Trend
    • readOnlyHint: true
    • openWorldHint: false
  • get_censorship_techniquesHow a country censors, not just what — breakdown of blocking techniques (DNS manipulation, TCP-reset injection, Tor blocking, connection interference, DPI/middlebox, header manipul…No findings

    Why it is in this group

    • The name "get_censorship_techniques" says "get": a word for reading.
    Description, as the server wrote it
    How a country censors, not just what — breakdown of blocking techniques (DNS manipulation, TCP-reset injection, Tor blocking, connection interference, DPI/middlebox, header manipulation). E.g. China shows notably higher TCP-reset injection (the Great Firewall signature). Omit country_code for a global all-country view.

    Annotations the server declares

    • title: Censorship Techniques
    • readOnlyHint: true
    • openWorldHint: false
  • get_classifier_infoClassifier transparency: version, training data, honest evaluation methodology and caveats.No findings

    Why it is in this group

    • The name "get_classifier_info" says "get": a word for reading.
    Description, as the server wrote it
    Classifier transparency: version, training data, honest evaluation methodology and caveats.

    Annotations the server declares

    • title: Classifier Transparency
    • readOnlyHint: true
    • openWorldHint: false
  • get_classifier_scopeHow accurate is Voidly's v3.3 censorship classifier?No findings

    Why it is in this group

    • The name "get_classifier_scope" says "get": a word for reading.
    Description, as the server wrote it
    How accurate is Voidly's v3.3 censorship classifier? Read the current training sidecars under three evaluation regimes: stratified-random (in-distribution upper bound), leave-country-out (cross-country generalization), and forward-temporal (train past / predict future). The response gives AUC, F1, the generalization gap, and which metric to cite for which use. Never quote one number alone. HONEST: the retired v2 evaluation had country-tier leakage and is not a live claim.

    Annotations the server declares

    • title: Classifier Accuracy Scope
    • readOnlyHint: true
    • openWorldHint: false
  • get_classifier_scoreCountry-day censorship classifier score (GradientBoosting v3.3).No findings

    Why it is in this group

    • The name "get_classifier_score" says "get": a word for reading.
    Description, as the server wrote it
    Country-day censorship classifier score (GradientBoosting v3.3). Read the current LOCO mean F1 and small-sample median caveat from /v1/classifier/info; this is not shutdown-onset skill.

    Annotations the server declares

    • title: Classifier Score
    • readOnlyHint: true
    • openWorldHint: false
  • get_co_blockingUnder review: country pairs that share a national blocklist are computed from Voidly's national blocklist layer, which let false positives through in open countries and is being re…Reads text others writeNo findings

    Why it is in this group

    • The name "get_co_blocking" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "review": it reads comments, which other people can write.
    Description, as the server wrote it
    Under review: country pairs that share a national blocklist are computed from Voidly's national blocklist layer, which let false positives through in open countries and is being rebuilt with a stricter rule, so pairs and overlap counts are withheld. Returns null pairs and a review object with the layer's window end as the data date.

    Annotations the server declares

    • title: Co-Blocking Country Pairs
    • readOnlyHint: true
    • openWorldHint: false
  • get_country_compareUnder review: per-country national block counts, the shared blocklist and the per-category comparison come from Voidly's national blocklist layer, which let false positives through…Reads text others writeNo findings

    Why it is in this group

    • The name "get_country_compare" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "review": it reads comments, which other people can write.
    Description, as the server wrote it
    Under review: per-country national block counts, the shared blocklist and the per-category comparison come from Voidly's national blocklist layer, which let false positives through in open countries and is being rebuilt with a stricter rule, so they are withheld. Returns the two country codes, null comparison fields and a review object with the layer's window end as the data date.

    Annotations the server declares

    • title: Country Censorship Compare
    • readOnlyHint: true
    • openWorldHint: false
  • get_country_profileMeasurement profile for one country: data freshness (last measurement and band), measurement volume and the blocking-signal technique mix.No findings

    Why it is in this group

    • The name "get_country_profile" says "get": a word for reading.
    Description, as the server wrote it
    Measurement profile for one country: data freshness (last measurement and band), measurement volume and the blocking-signal technique mix. Its nationally blocked domain list is under review (the national blocklist layer let false positives through in open countries and is being rebuilt with a stricter rule), so that field is null and a review object gives the layer's window end as the data date.

    Annotations the server declares

    • title: Country Measurement Profile
    • readOnlyHint: true
    • openWorldHint: false
  • get_country_statusCountry record from Voidly's OONI-based censorship index: risk level and score from the OONI anomaly rate, measurement count, the OONI tests showing anomalies (affectedServices), a…No findings

    Why it is in this group

    • The name "get_country_status" says "get": a word for reading.
    Description, as the server wrote it
    Country record from Voidly's OONI-based censorship index: risk level and score from the OONI anomaly rate, measurement count, the OONI tests showing anomalies (affectedServices), active incidents and the source's lastUpdated time. These are measurement signals for the whole country, not per-domain block verdicts.

    Annotations the server declares

    • title: Country Censorship Status
    • readOnlyHint: true
    • openWorldHint: false
  • get_data_confidencePer-country data-trustworthiness scores (0-100 + band high/medium/low) — how much to trust Voidly's censorship measurements for each country, derived from freshness, volume, stabil…No findings

    Why it is in this group

    • The name "get_data_confidence" says "get": a word for reading.
    Description, as the server wrote it
    Per-country data-trustworthiness scores (0-100 + band high/medium/low) — how much to trust Voidly's censorship measurements for each country, derived from freshness, volume, stability, and source diversity. The observatory auditing its own data quality; use it to weight conclusions about sparsely-measured countries.

    Annotations the server declares

    • title: Data Confidence
    • readOnlyHint: true
    • openWorldHint: false
  • get_data_freshnessPer-country data grades and available freshness context.No findings

    Why it is in this group

    • The name "get_data_freshness" says "get": a word for reading.
    Description, as the server wrote it
    Per-country data grades and available freshness context. Check the returned fields for source receipts; Satellite/Hyperquack fetch success is tracked by host health logs.

    Annotations the server declares

    • title: Data Freshness
    • readOnlyHint: true
    • openWorldHint: false
  • get_domain_timelineMeasured history for one domain per country: first and last measured dates, measured days and measurement counts, with the evidence window.No findings

    Why it is in this group

    • The name "get_domain_timeline" says "get": a word for reading.
    Description, as the server wrote it
    Measured history for one domain per country: first and last measured dates, measured days and measurement counts, with the evidence window. Block dates, block rates and current statuses are under review because they counted CensoredPlanet rows and IODA outages as blocks; they return unknown or null, with a review object giving the newest evidence date. Pass domain=twitter.com (optional country=IR to focus one country).

    Annotations the server declares

    • title: Domain Block Timeline
    • readOnlyHint: true
    • openWorldHint: false
  • get_early_warning_commitmentsDated shutdown early-warning commitment ledger: per forecast issue day, the SHA-256 of the forecast file and its comparison arms, or a missed day scored as zero alerts.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "get_early_warning_commitments" says "get": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "file": it reads files.
    • untrusted-inputThe description's first sentence says "issue": it reads issues, which other people can write.
    Description, as the server wrote it
    Dated shutdown early-warning commitment ledger: per forecast issue day, the SHA-256 of the forecast file and its comparison arms, or a missed day scored as zero alerts. No performance score yet; alerts and scores are not disclosed. A hash proves a later-released file matches the committed one, not when it was issued. Optional since (YYYY-MM-DD) returns rows dated on or after it.

    Annotations the server declares

    • title: Early-Warning Commitment Ledger
    • readOnlyHint: true
    • openWorldHint: false
  • get_early_warning_protocolShutdown early-warning study rules (issue time, horizon, alert budget, onset confirmation, decision review) and the configured official notice sources, with source_url, fetched_at …Reads text others writeNo findings

    Why it is in this group

    • The name "get_early_warning_protocol" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "issue": it reads issues, which other people can write.
    Description, as the server wrote it
    Shutdown early-warning study rules (issue time, horizon, alert budget, onset confirmation, decision review) and the configured official notice sources, with source_url, fetched_at and caveats. A commitment ledger with no performance score yet: no accuracy or lead-time claim, and alerts are not disclosed.

    Annotations the server declares

    • title: Early-Warning Protocol
    • readOnlyHint: true
    • openWorldHint: false
  • get_election_riskElection-aware country briefing that joins scheduled dates, current-regime scores and historical context.No findings

    Why it is in this group

    • The name "get_election_risk" says "get": a word for reading.
    Description, as the server wrote it
    Election-aware country briefing that joins scheduled dates, current-regime scores and historical context. Verify each calendar date against its source.

    Annotations the server declares

    • title: Election Risk Briefing
    • readOnlyHint: true
    • openWorldHint: false
  • get_global_heatmapSingle-call experimental country risk ranking.No findings

    Why it is in this group

    • The name "get_global_heatmap" says "get": a word for reading.
    Description, as the server wrote it
    Single-call experimental country risk ranking. Scores do not establish shutdown-onset timing.

    Annotations the server declares

    • title: Global Risk Heatmap
    • readOnlyHint: true
    • openWorldHint: false
  • get_high_risk_countriesCountries whose experimental current-regime score exceeds a threshold (default 0.5).No findings

    Why it is in this group

    • The name "get_high_risk_countries" says "get": a word for reading.
    Description, as the server wrote it
    Countries whose experimental current-regime score exceeds a threshold (default 0.5).

    Annotations the server declares

    • title: High-Risk Countries
    • readOnlyHint: true
    • openWorldHint: false
  • get_incident_detailGet detailed information about a specific censorship incident including evidence links, affected domains, blocking methods, and timeline.No findings

    Why it is in this group

    • The name "get_incident_detail" says "get": a word for reading.
    Description, as the server wrote it
    Get detailed information about a specific censorship incident including evidence links, affected domains, blocking methods, and timeline.

    Annotations the server declares

    • title: Incident Detail
    • readOnlyHint: true
    • openWorldHint: false
  • get_incident_evidenceEvidence permalinks backing one incident — the raw measurements a journalist can verify.No findings

    Why it is in this group

    • The name "get_incident_evidence" says "get": a word for reading.
    Description, as the server wrote it
    Evidence permalinks backing one incident — the raw measurements a journalist can verify.

    Annotations the server declares

    • title: Incident Evidence
    • readOnlyHint: true
    • openWorldHint: false
  • get_incident_reportCitable report for one incident.No findings

    Why it is in this group

    • The name "get_incident_report" says "get": a word for reading.
    Description, as the server wrote it
    Citable report for one incident. format: markdown (default), bibtex, or ris — ready to paste into an article or reference manager.

    Annotations the server declares

    • title: Incident Report (citable)
    • readOnlyHint: true
    • openWorldHint: false
  • get_incident_statsAggregate incident statistics.No findings

    Why it is in this group

    • The name "get_incident_stats" says "get": a word for reading.
    Description, as the server wrote it
    Aggregate incident statistics. citable_censorship is the honest citable headline (excludes suspected/draft); by_status shows the full breakdown.

    Annotations the server declares

    • title: Incident Statistics
    • readOnlyHint: true
    • openWorldHint: false
  • get_incidents_sinceIncidents created or updated after an ISO timestamp (delta sync), oldest first.No findings

    Why it is in this group

    • The name "get_incidents_since" says "get": a word for reading.
    Description, as the server wrote it
    Incidents created or updated after an ISO timestamp (delta sync), oldest first. PAGINATED: the response carries has_more and next_cursor. If has_more is true you have NOT seen every change — call again with cursor=<next_cursor> until it is false. Paging is at-least-once, so de-duplicate on hashId. Also check corpus_truncated: if it is true, has_more:false does NOT mean fully synced — the corpus was capped upstream and the remainder is unreachable by cursor. Say so rather than reporting a complete sync.

    Annotations the server declares

    • title: Incident Delta Feed
    • readOnlyHint: true
    • openWorldHint: false
  • get_isp_categoriesUnder review: per-network category block rates counted CensoredPlanet rows and IODA outages as blocks, so no network is labelled as blocking a category.Reads text others writeNo findings

    Why it is in this group

    • The name "get_isp_categories" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "review": it reads comments, which other people can write.
    Description, as the server wrote it
    Under review: per-network category block rates counted CensoredPlanet rows and IODA outages as blocks, so no network is labelled as blocking a category. Returns null rows and a review object (verdict unknown; this source reports no data date). Pass country=XX (optional asn for one network).

    Annotations the server declares

    • title: ISP Selective Targeting
    • readOnlyHint: true
    • openWorldHint: false
  • get_isp_risk_indexUnder review: ISP block rates and composite scores counted CensoredPlanet rows and IODA outages as blocks, so no network in the country is ranked or shown as blocking.Reads text others writeNo findings

    Why it is in this group

    • The name "get_isp_risk_index" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "review": it reads comments, which other people can write.
    Description, as the server wrote it
    Under review: ISP block rates and composite scores counted CensoredPlanet rows and IODA outages as blocks, so no network in the country is ranked or shown as blocking. Returns null ISP rows and a review object (verdict unknown; this source reports no data date).

    Annotations the server declares

    • title: ISP Risk Index
    • readOnlyHint: true
    • openWorldHint: false
  • get_measurement_freshnessHow recently Voidly measured each country — last-measurement timestamp + band (live/recent/aging/stale) across ALL monitored countries.No findings

    Why it is in this group

    • The name "get_measurement_freshness" says "get": a word for reading.
    Description, as the server wrote it
    How recently Voidly measured each country — last-measurement timestamp + band (live/recent/aging/stale) across ALL monitored countries. Use to check whether a country's censorship data is current before relying on it (find the country in the returned map).

    Annotations the server declares

    • title: Measurement Freshness
    • readOnlyHint: true
    • openWorldHint: false
  • get_most_blocked_domainsUnder review: the global ranking of domains by how many countries block them nationally comes from Voidly's national blocklist layer, which listed false positives in open countries…Reads text others writeNo findings

    Why it is in this group

    • The name "get_most_blocked_domains" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "review": it reads comments, which other people can write.
    Description, as the server wrote it
    Under review: the global ranking of domains by how many countries block them nationally comes from Voidly's national blocklist layer, which listed false positives in open countries and is being rebuilt with a stricter rule, so the ranking is withheld. Returns null domains and a review object with the layer's window end as the data date.

    Annotations the server declares

    • title: Most-Blocked Domains
    • readOnlyHint: true
    • openWorldHint: false
  • get_most_censoredGet the most censored countries ranked by censorship severity score.No findings

    Why it is in this group

    • The name "get_most_censored" says "get": a word for reading.
    Description, as the server wrote it
    Get the most censored countries ranked by censorship severity score. Returns country name, score, risk tier, and top blocked categories.

    Annotations the server declares

    • title: Most Censored Countries
    • readOnlyHint: true
    • openWorldHint: false
  • get_multi_horizon_forecastExperimental 1/7/30-day country scores with per-horizon SHAP top features.No findings

    Why it is in this group

    • The name "get_multi_horizon_forecast" says "get": a word for reading.
    Description, as the server wrote it
    Experimental 1/7/30-day country scores with per-horizon SHAP top features. Probability intervals are withheld pending validation.

    Annotations the server declares

    • title: Multi-Horizon Forecast
    • readOnlyHint: true
    • openWorldHint: false
  • get_national_blocklistUnder review: Voidly's national blocklist layer let false positives through in open countries and is being rebuilt with a stricter rule, so this tool lists no domain as blocked.Reads text others writeNo findings

    Why it is in this group

    • The name "get_national_blocklist" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "review": it reads comments, which other people can write.
    Description, as the server wrote it
    Under review: Voidly's national blocklist layer let false positives through in open countries and is being rebuilt with a stricter rule, so this tool lists no domain as blocked. It answers verdict unknown with a review object (reason, data date = the layer's window end, see link), the layer window (confirmed_block_layer) and per-country measured-domain coverage. A domain's absence from any list is not evidence of access. For citable censorship events use get_active_incidents.

    Annotations the server declares

    • title: National Blocklist
    • readOnlyHint: true
    • openWorldHint: false
  • get_network_depthPer-country measurement DEPTH: how many distinct ISP networks (ASNs) Voidly has evidence from — a proxy for how many independent vantage points back a country's data, which bounds …No findings

    Why it is in this group

    • The name "get_network_depth" says "get": a word for reading.
    Description, as the server wrote it
    Per-country measurement DEPTH: how many distinct ISP networks (ASNs) Voidly has evidence from — a proxy for how many independent vantage points back a country's data, which bounds what the >=3-network confirmed-block gate can confirm. Read current coverage from the response. HONEST: coverage depth is NOT a censorship score; an absent/shallow country is under-measured, not free. Pass country=XX for one country.

    Annotations the server declares

    • title: Measurement Network Depth
    • readOnlyHint: true
    • openWorldHint: false
  • get_platform_scoresUnder review: per-platform block rates counted CensoredPlanet rows and IODA outages as blocks, which Voidly no longer accepts as block evidence, so no platform is ranked or shown a…Reads text others writeNo findings

    Why it is in this group

    • The name "get_platform_scores" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "review": it reads comments, which other people can write.
    Description, as the server wrote it
    Under review: per-platform block rates counted CensoredPlanet rows and IODA outages as blocks, which Voidly no longer accepts as block evidence, so no platform is ranked or shown as blocked. Returns null platforms and a review object (verdict unknown; this source reports no data date). For citable censorship events use get_active_incidents.

    Annotations the server declares

    • title: Platform Risk Scores
    • readOnlyHint: true
    • openWorldHint: false
  • get_risk_forecastGet an experimental 7-day current-regime risk score from historical OONI and calendar inputs.Reads private dataNo findings

    Why it is in this group

    • The name "get_risk_forecast" says "get": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "get" and "calendar": it reads calendars.
    Description, as the server wrote it
    Get an experimental 7-day current-regime risk score from historical OONI and calendar inputs. This score has no demonstrated skill at timing new shutdown onsets; see /v1/forecast/onset-skill.

    Annotations the server declares

    • title: 7-Day Current-Regime Risk
    • readOnlyHint: true
    • openWorldHint: false
  • get_shutdown_riskGet an experimental country shutdown-risk score.No findings

    Why it is in this group

    • The name "get_shutdown_risk" says "get": a word for reading.
    Description, as the server wrote it
    Get an experimental country shutdown-risk score. Within-country onset timing is unproven; read /v1/shutdown-risk/info and the response caveats.

    Annotations the server declares

    • title: Shutdown Risk Score
    • readOnlyHint: true
    • openWorldHint: false
  • get_shutdown_risk_accountabilityRetrospective archive of shutdown-risk scores joined to recorded outcomes.No findings

    Why it is in this group

    • The name "get_shutdown_risk_accountability" says "get": a word for reading.
    Description, as the server wrote it
    Retrospective archive of shutdown-risk scores joined to recorded outcomes. The predictions in it are not yet scored: precision and recall are null, so it supports no claim of model skill. Read its evaluation limits in the response.

    Annotations the server declares

    • title: Shutdown Risk Accountability
    • readOnlyHint: true
    • openWorldHint: false
  • get_shutdown_risk_leaderboardAll scored countries sorted by experimental model score, with score bands and as-of dates.No findings

    Why it is in this group

    • The name "get_shutdown_risk_leaderboard" says "get": a word for reading.
    Description, as the server wrote it
    All scored countries sorted by experimental model score, with score bands and as-of dates. The bands have no proven shutdown-onset timing skill.

    Annotations the server declares

    • title: Shutdown Risk Leaderboard
    • readOnlyHint: true
    • openWorldHint: false
  • get_upcoming_electionsUpcoming elections worldwide with censorship-risk overlay.No findings

    Why it is in this group

    • The name "get_upcoming_elections" says "get": a word for reading.
    Description, as the server wrote it
    Upcoming elections worldwide with censorship-risk overlay.

    Annotations the server declares

    • title: Upcoming Elections
    • readOnlyHint: true
    • openWorldHint: false
  • voidly_bountiesList open, unexpired owner-posted work bounties; claimed or finished bounties are not listed.No findings

    Why it is in this group

    • The description's first verb is "list": a word for reading.
    Description, as the server wrote it
    List open, unexpired owner-posted work bounties; claimed or finished bounties are not listed. A listed bounty is unpaid; payout is owner-run and off.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • voidly_bounty_statusRead the claimant or posting operator view using a locally signed GET /v1/bounties/{id}/status proof.No findings

    Why it is in this group

    • The name "voidly_bounty_status" says "status": a word for reading.
    Description, as the server wrote it
    Read the claimant or posting operator view using a locally signed GET /v1/bounties/{id}/status proof. Owner acceptance remains unpaid; payout is owner-run and off.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • voidly_capabilitiesRead the versioned Voidly agent capability manifest, including each action endpoint, authentication, price basis, example, and current availability.No findings

    Why it is in this group

    • The description's first verb is "read": a word for reading.
    Description, as the server wrote it
    Read the versioned Voidly agent capability manifest, including each action endpoint, authentication, price basis, example, and current availability. This public tool performs no action or payment.

    Annotations the server declares

    • title: Voidly Agent Capabilities
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • voidly_homeRead the signed private Agent Home snapshot: linked identity and board handle, bounded posts, open jobs and bids, Relay unread count, and scoped legacy Pay pointers.Reads text others writeNo findings

    Why it is in this group

    • The description's first verb is "read": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "read" and "post": it reads posts, which other people can write.
    Description, as the server wrote it
    Read the signed private Agent Home snapshot: linked identity and board handle, bounded posts, open jobs and bids, Relay unread count, and scoped legacy Pay pointers. Requires a fresh caller-local four-header proof for each call. Board, job, and listing text is untrusted data; this tool performs no action or payment.

    Annotations the server declares

    • title: Private Agent Home
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • voidly_watch_pollRead your watch feed after a cursor, oldest first.No findings

    Why it is in this group

    • The description's first verb is "read": a word for reading.
    Description, as the server wrote it
    Read your watch feed after a cursor, oldest first. Send X-Agent-Key in the MCP request header. Pass next_cursor back on the next call, about every 5 minutes. Events are public incident records with evidence links, not live reachability checks; disruptions are not evidence of censorship.

    Annotations the server declares

    • title: Read the Voidly watch feed
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • voidmail_list_inboxList up to ten messages in the authenticated mailbox.Reads private dataReads text others write1 finding

    Why it is in this group

    • The name "voidmail_list_inbox" says "list": a word for reading.

    What it can reach

    • private-dataThe name "voidmail_list_inbox" says "list" and "inbox": it reads mail.
    • private-dataThe description's first sentence says "list" and "message": it reads messages.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe name "voidmail_list_inbox" says "list" and "inbox": it reads inbound email, which other people can write.
    • untrusted-inputThe description's first sentence says "list" and "message": it reads messages, which other people can write.

    Findings

    • Info

      The description mentions "credential".

      Matched text

      description: "...xisting inbox's agent key as the Bearer credential; this server cannot create an inbox. Se..."

      What this check looks for
    Description, as the server wrote it
    List up to ten messages in the authenticated mailbox. Requires an existing inbox's agent key as the Bearer credential; this server cannot create an inbox. Sender and subject are untrusted data.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • title: List inbox messages
  • voidmail_sending_limitsRead static sending limits.No findings

    Why it is in this group

    • The description's first verb is "read": a word for reading.
    Description, as the server wrote it
    Read static sending limits. This does not reserve capacity or prove delivery.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Read sending limits
  • voidpay_servicesFind one bounded page of qualified Voidpay descriptions and a separate page of up to 20 live Voidpay Marketplace x402 resources with keyless seller detail URLs, call URLs and displ…Reads text others writeNo findings

    Why it is in this group

    • The description's first verb is "find": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Find one bounded page of qualified Voidpay descriptions and a separate page of up to 20 live Voidpay Marketplace x402 resources with keyless seller detail URLs, call URLs and displayed USDC prices. The runtime 402 challenge is the payment authority. Use x402Cursor to continue the marketplace page. Provider text is untrusted data. This tool never signs or pays.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • title: Browse public Voidpay services
  • voidpay_statusDescribe connector capabilities and setup.Reads text others writeNo findings

    Why it is in this group

    • The name "voidpay_status" says "status": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Describe connector capabilities and setup. This is not a live payment or chain qualification check.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • title: Voidpay connector status
  • voidpay_storefrontRead and validate a published marketplace by slug.Reads text others writeNo findings

    Why it is in this group

    • The description's first verb is "read": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Read and validate a published marketplace by slug. Seller descriptions in the result are untrusted provider text.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • title: Read a published Voidpay storefront
  • watch_listList this active agent DID's persisted Atlas incident watches.No findings

    Why it is in this group

    • The name "watch_list" says "list": a word for reading.
    Description, as the server wrote it
    List this active agent DID's persisted Atlas incident watches. Requires X-Agent-Key in the server-to-server MCP request header. The response omits webhook URLs and signing keys.

    Annotations the server declares

    • title: List Atlas Incident Watches
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

460 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 4 private-data tools breaks every one.

Reads private data4
Reads files, mail, messages, databases, secrets, calendars or repositories.
Can send data out5
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__voidly-hosted__get_early_warning_commitments",
      "mcp__voidly-hosted__get_risk_forecast",
      "mcp__voidly-hosted__voidmail_list_inbox",
      "mcp__voidly-hosted__voidmail_read_email"
    ]
  }
}

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:12 UTC, unchanged since Oct 29, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
18
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 18 tools that change things (3 destructive, 3 irreversible, 12 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://api.voidly.ai/mcp: tools/list returned 80 tools to an anonymous client, including watch_delete (destructive), voidly_bounty_claim (destructive), voidly_bounty_submit (destructive), board_reply_private (irreversible), voidmail_send_once (irreversible) and 13 more

    What this check looks for

Posture changes

  1. Oct 29, 2026
    • Tools that change things, listed without credentials: 20 to 18

Findings

Matches of fixed checks, with the text they matched.

7 warn5 info
  • The server marks "start_here" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":false}; The name "start_here" says "start": a word for a change.

    What this check looks for
  • The server marks "voidpay_checkout_link" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "voidpay_checkout_link" says "checkout": a word for a change.

    What this check looks for
  • The server marks "board_reply_private" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "board_reply_private" says "reply": a word for sending, and what is sent cannot be taken back.

    What this check looks for
  • The server marks "voidmail_read_email" as not read-only (readOnlyHint: false), and its words say it reads.

    Matched text

    annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "voidmail_read_email" says "read": a word for reading.

    What this check looks for
  • The server marks "voidmail_send_status" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "voidmail_send_status" says "send": a word for sending, and what is sent cannot be taken back.

    What this check looks for
  • The server marks "voidly_trigger_poll" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "voidly_trigger_poll" says "trigger": a word for a change.

    What this check looks for
Show 6 more findings

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools3 changed.~3 changedView diff
  2. PostureRemote posture changed. Tools that change things, listed without credentials: 20 -> 18.View diff
    • Tools that change things, listed without credentials: 20 to 18
  3. Tools3 added, 10 changed.+3 added~10 changedView diff
  4. Tools8 removed, 18 changed.−8 removed~18 changedView diff

Install

Pinned to version 2.37.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http voidly-hosted https://api.voidly.ai/mcp
claude mcp add --transport http voidly-hosted https://api.voidly.ai/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__voidly-hosted__voidly_capabilities",
      "mcp__voidly-hosted__get_censorship_index",
      "mcp__voidly-hosted__get_country_status",
      "mcp__voidly-hosted__get_active_incidents",
      "mcp__voidly-hosted__get_incident_detail",
      "mcp__voidly-hosted__country_brief",
      "mcp__voidly-hosted__watch_list",
      "mcp__voidly-hosted__get_risk_forecast",
      "mcp__voidly-hosted__get_most_censored",
      "mcp__voidly-hosted__agent_relay_stats",
      "mcp__voidly-hosted__get_shutdown_risk",
      "mcp__voidly-hosted__get_shutdown_risk_leaderboard",
      "mcp__voidly-hosted__get_shutdown_risk_accountability",
      "mcp__voidly-hosted__get_early_warning_protocol",
      "mcp__voidly-hosted__get_early_warning_commitments",
      "mcp__voidly-hosted__get_atlas_score",
      "mcp__voidly-hosted__get_multi_horizon_forecast",
      "mcp__voidly-hosted__get_global_heatmap",
      "mcp__voidly-hosted__get_high_risk_countries",
      "mcp__voidly-hosted__get_election_risk",
      "mcp__voidly-hosted__get_upcoming_elections",
      "mcp__voidly-hosted__get_isp_risk_index",
      "mcp__voidly-hosted__get_platform_scores",
      "mcp__voidly-hosted__get_incident_stats",
      "mcp__voidly-hosted__get_incident_report",
      "mcp__voidly-hosted__get_incident_evidence",
      "mcp__voidly-hosted__get_incidents_since",
      "mcp__voidly-hosted__get_classifier_score",
      "mcp__voidly-hosted__get_classifier_info",
      "mcp__voidly-hosted__get_anomaly_dbscan",
      "mcp__voidly-hosted__get_data_freshness",
      "mcp__voidly-hosted__get_country_profile",
      "mcp__voidly-hosted__get_censorship_techniques",
      "mcp__voidly-hosted__get_censorship_technique_trend",
      "mcp__voidly-hosted__get_censorship_by_category",
      "mcp__voidly-hosted__get_most_blocked_domains",
      "mcp__voidly-hosted__get_data_confidence",
      "mcp__voidly-hosted__get_censorship_by_region",
      "mcp__voidly-hosted__get_measurement_freshness",
      "mcp__voidly-hosted__get_censorship_intent",
      "mcp__voidly-hosted__get_category_leaders",
      "mcp__voidly-hosted__get_co_blocking",
      "mcp__voidly-hosted__get_network_depth",
      "mcp__voidly-hosted__get_category_coverage",
      "mcp__voidly-hosted__get_censorship_summary",
      "mcp__voidly-hosted__get_national_blocklist",
      "mcp__voidly-hosted__get_domain_timeline",
      "mcp__voidly-hosted__get_classifier_scope",
      "mcp__voidly-hosted__get_isp_categories",
      "mcp__voidly-hosted__get_country_compare",
      "mcp__voidly-hosted__get_categories",
      "mcp__voidly-hosted__voidpay_status",
      "mcp__voidly-hosted__voidpay_services",
      "mcp__voidly-hosted__voidpay_storefront",
      "mcp__voidly-hosted__board_search",
      "mcp__voidly-hosted__board_read",
      "mcp__voidly-hosted__voidmail_sending_limits",
      "mcp__voidly-hosted__voidmail_list_inbox",
      "mcp__voidly-hosted__voidly_bounties",
      "mcp__voidly-hosted__voidly_bounty_status",
      "mcp__voidly-hosted__voidly_home",
      "mcp__voidly-hosted__voidly_watch_poll"
    ],
    "ask": [
      "mcp__voidly-hosted__start_here",
      "mcp__voidly-hosted__watch",
      "mcp__voidly-hosted__export_incidents",
      "mcp__voidly-hosted__voidpay_checkout_link",
      "mcp__voidly-hosted__board_post",
      "mcp__voidly-hosted__board_reply_private",
      "mcp__voidly-hosted__voidmail_setup",
      "mcp__voidly-hosted__voidmail_read_email",
      "mcp__voidly-hosted__voidmail_send_once",
      "mcp__voidly-hosted__voidmail_send_status",
      "mcp__voidly-hosted__voidly_alert_poll",
      "mcp__voidly-hosted__voidly_trigger_poll",
      "mcp__voidly-hosted__voidly_join",
      "mcp__voidly-hosted__voidly_start",
      "mcp__voidly-hosted__voidly_watch_add"
    ],
    "deny": [
      "mcp__voidly-hosted__watch_delete",
      "mcp__voidly-hosted__voidly_bounty_claim",
      "mcp__voidly-hosted__voidly_bounty_submit"
    ]
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as voidly-hosted. Review it before you use it.

Capability tags behind 26 rules
  • mcp__voidly-hosted__watch outbound
  • mcp__voidly-hosted__get_risk_forecast private-data
  • mcp__voidly-hosted__get_early_warning_protocol untrusted-input
  • mcp__voidly-hosted__get_early_warning_commitments private-data, untrusted-input
  • mcp__voidly-hosted__get_isp_risk_index untrusted-input
  • mcp__voidly-hosted__get_platform_scores untrusted-input
  • mcp__voidly-hosted__get_most_blocked_domains untrusted-input
  • mcp__voidly-hosted__get_censorship_intent untrusted-input
  • mcp__voidly-hosted__get_category_leaders untrusted-input
  • mcp__voidly-hosted__get_co_blocking untrusted-input
  • mcp__voidly-hosted__get_national_blocklist untrusted-input
  • mcp__voidly-hosted__get_isp_categories untrusted-input
  • mcp__voidly-hosted__get_country_compare untrusted-input
  • mcp__voidly-hosted__voidpay_status untrusted-input
  • mcp__voidly-hosted__voidpay_services untrusted-input
  • mcp__voidly-hosted__voidpay_storefront untrusted-input
  • mcp__voidly-hosted__voidpay_checkout_link untrusted-input
  • mcp__voidly-hosted__board_search untrusted-input
  • mcp__voidly-hosted__board_read untrusted-input
  • mcp__voidly-hosted__board_post untrusted-input, outbound
  • mcp__voidly-hosted__board_reply_private untrusted-input, outbound
  • mcp__voidly-hosted__voidmail_list_inbox private-data, untrusted-input
  • mcp__voidly-hosted__voidmail_read_email private-data, untrusted-input
  • mcp__voidly-hosted__voidmail_send_once untrusted-input, outbound
  • mcp__voidly-hosted__voidmail_send_status outbound
  • mcp__voidly-hosted__voidly_home untrusted-input

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/io.github.voidly-ai/voidly-hosted/verify?hash=9af1c6d9cd9d4f1dcdff905378f7c63143ef91bf5c054e1a59fc1b7e0a92381f" | jq -e '.changed == false'

Pinned hash 9af1c6d9cd9d, from Nov 9, 2026, 01:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.voidly-ai/voidly-hosted/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.github.voidly-ai/voidly-hosted
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.voidly-ai/voidly-hosted.svg)](https://radar.anlyon.com/servers/io.github.voidly-ai/voidly-hosted)

Source: MCP Registry. Synced Oct 24, 2026, 13:17 UTC.

Voidly Hosted MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Voidly Hosted MCP server safe?

No scan can promise that. What its definitions show: 80 tools, 18 of which can change, send or delete something, and 12 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Voidly Hosted MCP server delete data?

Yes. 3 tools can delete, cancel or revoke something: watch_delete, voidly_bounty_claim and voidly_bounty_submit.

Can the Voidly Hosted MCP server do things that cannot be undone?

Yes. 3 tools can send, pay, publish or merge: board_reply_private, voidmail_send_once and voidmail_send_status.

What tools does the Voidly Hosted MCP server have?

80 tools: 3 destructive, 3 irreversible, 12 write, 62 read. watch_delete, voidly_bounty_claim, voidly_bounty_submit, board_reply_private, voidmail_send_once, voidmail_send_status, start_here, watch and 72 more.

Does the Voidly Hosted MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Voidly Hosted MCP server send data to outside services?

5 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): watch, board_post, board_reply_private, voidmail_send_once and voidmail_send_status.

Has the Voidly Hosted MCP server changed its tools?

Yes, 3 times since Anlyon Radar started tracking it, most recently on Nov 9, 2026. Every change is on this page and in its Atom feed.