Skip to content

SwarmIO MCP server

io.ioswarm/swarmioioswarm.iostreamable-httpv1.0.1Scanned

AI that does real work for you: cited web research, plans, finance, horoscopes. Self-serve.

14 tools: 1 can delete or cancel things, 1 do something that can't be undone, 8 change things and 4 only read.

Tools: 1 delete, 1 irreversible, 8 write, 4 read.
  • Reads private data · 0
  • Reads text others write · 4
  • Can send data out · 0
  • 6 findings

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here can delete or cancel things and 1 does 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 SwarmIO MCP server can do

The SwarmIO MCP server is published by ioswarm.io, a domain the MCP Registry verified. It has 14 tools. It can delete or cancel things (1 tool: runs.cancel), do things that cannot be undone, such as sending, paying or publishing (billing.topup_terms) and create or change data (8 tools: market.pulse, news.brief, route.classify, runs.launch and 4 more). 4 tools only read.

4 tools bring in text other people can write (fetch, web.search, news.brief and 1 more).

The fixed checks matched 6 findings (annotation-conflict and credentials-mention). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 18, 2026, version 1.0.1.

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.

14 tools

Deletes or cancels 1Claude Code: deny
  • runs.cancelStop a running job.No findings

    Why it is in this group

    • The name "runs.cancel" says "run": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Stop a running job.

    Annotations the server declares

    • destructiveHint: true
    • openWorldHint: false
    • readOnlyHint: false
Can't be undone 1Claude Code: ask
  • billing.topup_termsHow to refill credits machine-to-machine: USDC on Base to a published address, verified on-chain.2 findings

    Why it is in this group

    • The name "billing.topup_terms" says "topup": a word that usually means money moves, which cannot be taken back.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Info

      The description mentions "credentials".

      Matched text

      description: "...address, minimum, and rate. Public — no credentials needed."

      What this check looks for
    • Warn

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

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":false}; The name "billing.topup_terms" says "topup": a word that usually means money moves, which cannot be taken back.

      What this check looks for
    Description, as the server wrote it
    How to refill credits machine-to-machine: USDC on Base to a published address, verified on-chain. Returns the pay_to address, minimum, and rate. Public — no credentials needed.

    Annotations the server declares

    • destructiveHint: false
    • openWorldHint: false
    • readOnlyHint: true
Changes things 8Claude Code: ask
  • billing.balanceThe caller's credit balance and plan state.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
    The caller's credit balance and plan state.

    Annotations the server declares

    • destructiveHint: false
    • openWorldHint: false
    • readOnlyHint: true
  • market.pulseFREE, no key, no account: live prices for BTC, ETH, SOL, AMZN and NVDA with the session's change, plus today's news — the platform's newest published news digest parsed into storie…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
    FREE, no key, no account: live prices for BTC, ETH, SOL, AMZN and NVDA with the session's change, plus today's news — the platform's newest published news digest parsed into stories with source links, and the market wire's latest headlines. Refreshed every minute (prices) and every ten minutes (news). Call this first to see what the swarm's data looks like before spending anything.

    Annotations the server declares

    • destructiveHint: false
    • openWorldHint: false
    • readOnlyHint: true
  • news.briefPAID, 5¢ per call over x402 (USDC on Base, no account): today's market-news brief — this platform's newest published news digest synthesized with the live market wire into a cited …Reads text others writeNo 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.

    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
    PAID, 5¢ per call over x402 (USDC on Base, no account): today's market-news brief — this platform's newest published news digest synthesized with the live market wire into a cited bullet list, every finding ending with its source URL. No input required; the settle happens over HTTP, where the payment headers live: this tool returns the exact steps. The FREE raw material it is written from is market.pulse on this same server (the digest stories and wire headlines, un-synthesized).

    Annotations the server declares

    • destructiveHint: false
    • openWorldHint: true
    • readOnlyHint: true
  • route.classifyClassify a freeform request into the right mode (research, news, finance, astrology, …) before spending a run.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
    Classify a freeform request into the right mode (research, news, finance, astrology, …) before spending a run. Never charged.

    Annotations the server declares

    • destructiveHint: false
    • openWorldHint: false
    • readOnlyHint: true
  • runs.getA run's status and metadata.1 finding

    Why it is in this group

    • The name "runs.get" says "run": 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 "runs.get" 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 "runs.get" says "run": a word for a change.

      What this check looks for
    Description, as the server wrote it
    A run's status and metadata. Poll until status is completed/failed/cancelled.

    Annotations the server declares

    • destructiveHint: false
    • openWorldHint: false
    • readOnlyHint: true
  • runs.launchLaunch a run: agents search the web, read sources, and write a cited report — real work, done for the caller.Reads text others writeNo findings

    Why it is in this group

    • The name "runs.launch" says "run": 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.
    Description, as the server wrote it
    Launch a run: agents search the web, read sources, and write a cited report — real work, done for the caller. BILLED from the caller's credits. Returns the run record; poll runs.get until completed, then runs.report. Modes: research, news, product, trips, trainer, finance, astrology, horoscope (astrology/horoscope take Birth date constraint lines — see https://ioswarm.io/llms.txt).

    Annotations the server declares

    • destructiveHint: false
    • openWorldHint: true
    • readOnlyHint: false
  • runs.reportThe finished, cited report for a completed run (report_text is markdown).1 finding

    Why it is in this group

    • The name "runs.report" says "run": 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 "runs.report" 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 "runs.report" says "run": a word for a change.

      What this check looks for
    Description, as the server wrote it
    The finished, cited report for a completed run (report_text is markdown).

    Annotations the server declares

    • destructiveHint: false
    • openWorldHint: false
    • readOnlyHint: true
  • runs.waitBlock until a run finishes, then return its record — and its report when it completed.1 finding

    Why it is in this group

    • The name "runs.wait" says "run": 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 "runs.wait" 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 "runs.wait" says "run": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Block until a run finishes, then return its record — and its report when it completed. Runs take 3–10 minutes; call this instead of polling runs.get in a loop. Returns early with timed_out=true after timeout_secs (default 90, max 240): call it again with the same run_id to keep waiting. Never charged.

    Annotations the server declares

    • destructiveHint: false
    • openWorldHint: false
    • readOnlyHint: true
Only reads 4Show 4 read-only tools
  • fetchRead one report by the id search returned: the full markdown text with its citations and evidence header, plus title, url and metadata.Reads text others writeNo findings

    Why it is in this group

    • The name "fetch" says "fetch": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "read" and "url": it reads web pages, which anyone can write.
    Description, as the server wrote it
    Read one report by the id search returned: the full markdown text with its citations and evidence header, plus title, url and metadata. Public reports need no key; a caller's own reports need theirs.

    Annotations the server declares

    • destructiveHint: false
    • openWorldHint: false
    • readOnlyHint: true
  • modes.listThe launchable modes with a one-line contract for each.1 finding

    Why it is in this group

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

    Findings

    • Info

      The description mentions "credentials".

      Matched text

      description: "...act for each. Static; never charged, no credentials needed."

      What this check looks for
    Description, as the server wrote it
    The launchable modes with a one-line contract for each. Static; never charged, no credentials needed.

    Annotations the server declares

    • destructiveHint: false
    • openWorldHint: false
    • readOnlyHint: true
  • web.searchFREE, no key, no account: LIVE web search, 25 queries a day per caller, up to 5 results each ({results:[{url,title,snippet,published}], quota, report}).Reads text others writeNo findings

    Why it is in this group

    • The name "web.search" says "search": 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 name "web.search" says "search" and "web": it reads web pages, which anyone can write.
    • untrusted-inputThe description's first sentence says "web": it reads web pages, which anyone can write.
    Description, as the server wrote it
    FREE, no key, no account: LIVE web search, 25 queries a day per caller, up to 5 results each ({results:[{url,title,snippet,published}], quota, report}). This is the open web, not the published corpus — for the platform's finished reports use `search`. Over the daily quota the paid leg is $0.02 per call over x402 (USDC on Base): POST https://ioswarm.io/api/v1/search with the same JSON body and no payment header, read the 402, sign the EIP-3009 authorization, re-send with X-PAYMENT (v1) or PAYMENT-SIGNATURE (v2) — no account is created. The response's `report` field shows the one-call cited research brief (5¢, pay-only) for when raw results are not enough.

    Annotations the server declares

    • destructiveHint: false
    • openWorldHint: true
    • readOnlyHint: true

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.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write4
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

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, 19:13 UTC, unchanged since Oct 22, 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
10
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 10 tools that change things (1 destructive, 1 irreversible, 8 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://ioswarm.io/mcp: tools/list returned 14 tools to an anonymous client, including runs.cancel (destructive), billing.topup_terms (irreversible), market.pulse (write), news.brief (write), route.classify (write) and 5 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

4 warn2 info
  • The server marks "runs.get" 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 "runs.get" says "run": a word for a change.

    What this check looks for
  • The server marks "runs.wait" 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 "runs.wait" says "run": a word for a change.

    What this check looks for
  • The server marks "runs.report" 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 "runs.report" says "run": a word for a change.

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

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":false}; The name "billing.topup_terms" says "topup": a word that usually means money moves, which cannot be taken back.

    What this check looks for
  • The description mentions "credentials".

    Matched text

    description: "...address, minimum, and rate. Public — no credentials needed."

    What this check looks for
  • The description mentions "credentials".

    Matched text

    description: "...act for each. Static; never charged, no credentials needed."

    What this check looks for

History

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

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 1.0.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http swarmio https://ioswarm.io/mcp --header 'Authorization: <your-authorization>'
claude mcp add --transport http swarmio https://ioswarm.io/mcp --header 'Authorization: <your-authorization>'

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__swarmio__search",
      "mcp__swarmio__fetch",
      "mcp__swarmio__web_search",
      "mcp__swarmio__modes_list"
    ],
    "ask": [
      "mcp__swarmio__market_pulse",
      "mcp__swarmio__news_brief",
      "mcp__swarmio__route_classify",
      "mcp__swarmio__runs_launch",
      "mcp__swarmio__runs_get",
      "mcp__swarmio__runs_wait",
      "mcp__swarmio__runs_report",
      "mcp__swarmio__billing_balance",
      "mcp__swarmio__billing_topup_terms"
    ],
    "deny": [
      "mcp__swarmio__runs_cancel"
    ]
  }
}

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 swarmio. Review it before you use it.

Capability tags behind 4 rules
  • mcp__swarmio__fetch untrusted-input
  • mcp__swarmio__web_search untrusted-input
  • mcp__swarmio__news_brief untrusted-input
  • mcp__swarmio__runs_launch 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.ioswarm/swarmio/verify?hash=60b5394c6f364353a907dbbef9a5f40b64b5bf5b4e0efdc7ee3e35544e5c3f2b" | jq -e '.changed == false'

Pinned hash 60b5394c6f36, from Nov 18, 2026, 12:18 UTC.

Watch

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

https://radar.anlyon.com/servers/io.ioswarm/swarmio/changes.xml

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

Badge

Anlyon Radar badge for io.ioswarm/swarmio
[![Anlyon Radar](https://radar.anlyon.com/badge/io.ioswarm/swarmio.svg)](https://radar.anlyon.com/servers/io.ioswarm/swarmio)

Source: MCP Registry. Synced Oct 21, 2026, 18:52 UTC.

SwarmIO MCP server: questions and answers

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

Is the SwarmIO MCP server safe?

No scan can promise that. What its definitions show: 14 tools, 10 of which can change, send or delete something, and 6 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 SwarmIO MCP server delete data?

Yes. 1 tool can delete, cancel or revoke something: runs.cancel.

Can the SwarmIO MCP server do things that cannot be undone?

Yes. 1 tool can send, pay, publish or merge: billing.topup_terms.

What tools does the SwarmIO MCP server have?

14 tools: 1 destructive, 1 irreversible, 8 write, 4 read. runs.cancel, billing.topup_terms, market.pulse, news.brief, route.classify, runs.launch, runs.get, runs.wait and 6 more.

Does the SwarmIO MCP server need sign-in or OAuth?

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

Does the SwarmIO MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the SwarmIO MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 18, 2026.