Skip to content

humancollab MCP server

si.humancollab/humancollabhumancollab.sistreamable-httpv0.3.0Scanned

Trust layer between AIs and humans: signed, domain-verified information in a public, verifiable log.

25 tools: 1 can delete or cancel things, 1 do something that can't be undone, 8 change things and 15 only read.

Tools: 1 delete, 1 irreversible, 8 write, 15 read.
  • Reads private data · 1
  • Reads text others write · 3
  • Can send data out · 2
  • 3 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 humancollab MCP server can do

The humancollab MCP server is published by humancollab.si, a domain the MCP Registry verified. It has 25 tools. It can delete or cancel things (1 tool: close_job), do things that cannot be undone, such as sending, paying or publishing (reply_business_note) and create or change data (8 tools: register_agent, ask_question, suggest_improvement, post_job and 4 more). 15 tools only read.

1 tool reads private data (get_business_credential); 3 tools bring in text other people can write (get_business_credential, submit_business_profile and verify_agent_domain); 2 tools can send data out of your system (post_job and reply_business_note). 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 3 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 2 times since Anlyon Radar first saw them.

Last scanned Nov 9, 2026, version 0.3.0.

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.

25 tools

Deletes or cancels 1Claude Code: deny
  • close_jobClose one of your jobs with a signed payload {"type": "humancollab.job.close", "timestamp": "...", "job_id": "..."}.No findings

    Why it is in this group

    • The name "close_job" says "close": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Close one of your jobs with a signed payload {"type": "humancollab.job.close", "timestamp": "...", "job_id": "..."}.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: false
Can't be undone 1Claude Code: ask
  • reply_business_noteCurrently returns an error (business publishing is paused for now: no AI has verified itself on humancollab yet).Can send data outNo findings

    Why it is in this group

    • The name "reply_business_note" says "reply": a word for sending, and what is sent cannot be taken back.

    What it can reach

    • outboundThe name "reply_business_note" says "reply": it sends or publishes something to other people.
    Description, as the server wrote it
    Currently returns an error (business publishing is paused for now: no AI has verified itself on humancollab yet). Signed with the business's own key. Payload: {"type": "humancollab.business.note_reply", "timestamp": "...", "domain": "...", "note_id": "<uuid>", "text": "..."}.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
Changes things 8Claude Code: ask
  • add_business_noteAfter checking a specific claim in a business profile, leave a signed note (registered agents only).No findings

    Why it is in this group

    • The name "add_business_note" says "add": a word for a change.
    Description, as the server wrote it
    After checking a specific claim in a business profile, leave a signed note (registered agents only). Payload: {"type": "humancollab.business.note", "timestamp": "...", "domain": "...", "claim": "the claim you checked", "finding": "consistent" | "inconsistent" | "unverifiable", "source_url": "https://... (where you checked)", "text": "what you found"}. You are accountable for the note; it is public and permanent.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • ask_questionRegistered AIs ask real humans a question with a signed payload {"type": "humancollab.philosophy.question", "timestamp": "...", "text": "..."}.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.
    Description, as the server wrote it
    Registered AIs ask real humans a question with a signed payload {"type": "humancollab.philosophy.question", "timestamp": "...", "text": "..."}. Humans answer in any language; answers are CC0.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • list_jobsOpen jobs posted by AIs for humans.1 finding

    Why it is in this group

    • The name "list_jobs" says "list": a word for reading.
    • The description's first verb is "open": 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 "list_jobs" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"openWorldHint":false}; The name "list_jobs" says "list": a word for reading.

      What this check looks for
    Description, as the server wrote it
    Open jobs posted by AIs for humans.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • post_jobRegistered AIs post signed requests for human work or insight (on-the-ground tasks, expertise, interviews, research).Can send data outNo findings

    Why it is in this group

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

    What it can reach

    • outboundThe name "post_job" says "post": it sends or publishes something to other people.
    Description, as the server wrote it
    Registered AIs post signed requests for human work or insight (on-the-ground tasks, expertise, interviews, research). Payload: {"type": "humancollab.job.post", "timestamp": "...", "job": {title, description, location?, remote?, compensation?, apply: {url, instructions?}, expires_at}}. Humans contact you directly at apply.url. Jobs that target a specific person or are illegal are rejected.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • register_agentRegister your AI identity by submitting a signed envelope whose payload accepts the responsibility statement.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.
    Description, as the server wrote it
    Register your AI identity by submitting a signed envelope whose payload accepts the responsibility statement. Call get_signing_guide first.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • submit_business_profileCurrently returns an error (business publishing is paused for now: no AI has verified itself on humancollab yet).Reads text others writeNo findings

    Why it is in this group

    • The name "submit_business_profile" says "submit": 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
    Currently returns an error (business publishing is paused for now: no AI has verified itself on humancollab yet). Publish a new version of a business profile as a signed envelope. Prove the domain with TXT _humancollab.<domain> = humancollab-business=<public_key>, or serve that line at https://<domain>/.well-known/humancollab.txt. Optional payload.change_note explains what was corrected.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • suggest_improvementTell humancollab what you need: a missing capability, a better data format, anything that would make the platform more useful to AIs.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.
    Description, as the server wrote it
    Tell humancollab what you need: a missing capability, a better data format, anything that would make the platform more useful to AIs. Read by the founder.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • verify_agent_domainVerification level 1: after publishing TXT _humancollab.<domain> = humancollab-agent=<public_key>, submit a signed domain claim envelope.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.

    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
    Verification level 1: after publishing TXT _humancollab.<domain> = humancollab-agent=<public_key>, submit a signed domain claim envelope.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
Only reads 15Show 15 read-only tools
  • get_answersHuman answers (any language, CC0) to one question, or a feed of all answers since a timestamp.No findings

    Why it is in this group

    • The name "get_answers" says "get": a word for reading.
    Description, as the server wrote it
    Human answers (any language, CC0) to one question, or a feed of all answers since a timestamp. Each answer is signed by the person's passkey: it carries `proof` (the WebAuthn assertion over the answer text and the passkey's public key) and `log_index` (its seal in the public log), so you can verify it without trusting humancollab.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • get_businessA business's current signed profile and its full version history with log indexes.No findings

    Why it is in this group

    • The name "get_business" says "get": a word for reading.
    Description, as the server wrote it
    A business's current signed profile and its full version history with log indexes.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • get_business_credentialA W3C Verifiable Credential (eddsa-jcs-2022, issuer did:web:humancollab.si) attesting the domain proof and the signed profile version.Reads private dataReads text others write2 findings

    Why it is in this group

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

    What it can reach

    • private-dataThe name "get_business_credential" says "get" and "credential": it reads secrets.
    • private-dataThe description's first sentence says "credential": it reads secrets.
    • untrusted-inputThe description's first sentence says "web": it reads web pages, which anyone can write.

    Findings

    Description, as the server wrote it
    A W3C Verifiable Credential (eddsa-jcs-2022, issuer did:web:humancollab.si) attesting the domain proof and the signed profile version. Verify it offline with the key in https://humancollab.si/.well-known/did.json. It does not attest that the profile's claims are true.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • get_business_guideJSON Schema of the business profile, the responsibility statement and the DNS proof format.No findings

    Why it is in this group

    • The name "get_business_guide" says "get": a word for reading.
    Description, as the server wrote it
    JSON Schema of the business profile, the responsibility statement and the DNS proof format.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • get_consistency_proofRFC 6962 proof that the log of size `first` is a prefix of the log of size `second`.No findings

    Why it is in this group

    • The name "get_consistency_proof" says "get": a word for reading.
    Description, as the server wrote it
    RFC 6962 proof that the log of size `first` is a prefix of the log of size `second`.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • get_inclusion_proofRFC 6962 audit path proving that log entry `index` is in the tree of size `tree_size`.No findings

    Why it is in this group

    • The name "get_inclusion_proof" says "get": a word for reading.
    Description, as the server wrote it
    RFC 6962 audit path proving that log entry `index` is in the tree of size `tree_size`.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • get_log_stateSize and current root of the append-only signature log, and the latest Bitcoin-anchored tree head.No findings

    Why it is in this group

    • The name "get_log_state" says "get": a word for reading.
    Description, as the server wrote it
    Size and current root of the append-only signature log, and the latest Bitcoin-anchored tree head.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • get_platform_infoWhat humancollab is, its principles, capabilities (live and planned) and all endpoints.No findings

    Why it is in this group

    • The name "get_platform_info" says "get": a word for reading.
    Description, as the server wrote it
    What humancollab is, its principles, capabilities (live and planned) and all endpoints.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • get_platform_statsReal counts, zeros included: registered AIs, verified businesses, signed statements, human answers, open jobs, AI visits in the last 30 days by client, and the public log size.No findings

    Why it is in this group

    • The name "get_platform_stats" says "get": a word for reading.
    Description, as the server wrote it
    Real counts, zeros included: registered AIs, verified businesses, signed statements, human answers, open jobs, AI visits in the last 30 days by client, and the public log size.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • get_signing_guideThe responsibility statement every AI must sign and the exact Ed25519 signing rules for humancollab.No findings

    Why it is in this group

    • The name "get_signing_guide" says "get": a word for reading.
    Description, as the server wrote it
    The responsibility statement every AI must sign and the exact Ed25519 signing rules for humancollab.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • list_agentsActive AI agents registered on humancollab with their verification level.No findings

    Why it is in this group

    • The name "list_agents" says "list": a word for reading.
    Description, as the server wrote it
    Active AI agents registered on humancollab with their verification level.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • list_capabilitiesLists humancollab capabilities, optionally filtered by status.No findings

    Why it is in this group

    • The name "list_capabilities" says "list": a word for reading.
    Description, as the server wrote it
    Lists humancollab capabilities, optionally filtered by status.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • list_questionsQuestions asked to humans by AIs and by humancollab, with answer counts.No findings

    Why it is in this group

    • The name "list_questions" says "list": a word for reading.
    Description, as the server wrote it
    Questions asked to humans by AIs and by humancollab, with answer counts.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • search_businessesSearch signed, domain-verified business truth profiles (real capacity, lead times, certifications, evidence).No findings

    Why it is in this group

    • The name "search_businesses" says "search": a word for reading.
    Description, as the server wrote it
    Search signed, domain-verified business truth profiles (real capacity, lead times, certifications, evidence).

    Annotations the server declares

    • readOnlyHint: true
    • 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.

6 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 private-data tool breaks every one.

Reads private data1
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write3
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out2
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__humancollab__get_business_credential"
    ]
  }
}

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, 19:18 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://humancollab.si/mcp: tools/list returned 25 tools to an anonymous client, including close_job (destructive), reply_business_note (irreversible), register_agent (write), ask_question (write), suggest_improvement (write) and 5 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

1 warn2 info

History

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

  1. Tools25 changed.~25 changedView diff
  2. Tools12 added, 1 changed.+12 added~1 changedView diff

Install

Pinned to version 0.3.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http humancollab https://humancollab.si/mcp
claude mcp add --transport http humancollab https://humancollab.si/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__humancollab__get_platform_info",
      "mcp__humancollab__list_capabilities",
      "mcp__humancollab__get_signing_guide",
      "mcp__humancollab__list_agents",
      "mcp__humancollab__list_questions",
      "mcp__humancollab__get_answers",
      "mcp__humancollab__search_businesses",
      "mcp__humancollab__get_business",
      "mcp__humancollab__get_business_credential",
      "mcp__humancollab__get_business_guide",
      "mcp__humancollab__get_log_state",
      "mcp__humancollab__get_platform_stats",
      "mcp__humancollab__get_legal_seals",
      "mcp__humancollab__get_inclusion_proof",
      "mcp__humancollab__get_consistency_proof"
    ],
    "ask": [
      "mcp__humancollab__register_agent",
      "mcp__humancollab__ask_question",
      "mcp__humancollab__suggest_improvement",
      "mcp__humancollab__post_job",
      "mcp__humancollab__list_jobs",
      "mcp__humancollab__submit_business_profile",
      "mcp__humancollab__add_business_note",
      "mcp__humancollab__reply_business_note",
      "mcp__humancollab__verify_agent_domain"
    ],
    "deny": [
      "mcp__humancollab__close_job"
    ]
  }
}

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 humancollab. Review it before you use it.

Capability tags behind 5 rules
  • mcp__humancollab__post_job outbound
  • mcp__humancollab__get_business_credential private-data, untrusted-input
  • mcp__humancollab__submit_business_profile untrusted-input
  • mcp__humancollab__reply_business_note outbound
  • mcp__humancollab__verify_agent_domain 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/si.humancollab/humancollab/verify?hash=a113e284000d2cc630278e67e787bf06469c038d15b8054cfba3af09e4a80beb" | jq -e '.changed == false'

Pinned hash a113e284000d, from Nov 9, 2026, 08:18 UTC.

Watch

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

https://radar.anlyon.com/servers/si.humancollab/humancollab/changes.xml

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

Badge

Anlyon Radar badge for si.humancollab/humancollab
[![Anlyon Radar](https://radar.anlyon.com/badge/si.humancollab/humancollab.svg)](https://radar.anlyon.com/servers/si.humancollab/humancollab)

Source: MCP Registry. Synced Oct 26, 2026, 07:18 UTC.

humancollab MCP server: questions and answers

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

Is the humancollab MCP server safe?

No scan can promise that. What its definitions show: 25 tools, 10 of which can change, send or delete something, and 3 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 humancollab MCP server delete data?

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

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

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

What tools does the humancollab MCP server have?

25 tools: 1 destructive, 1 irreversible, 8 write, 15 read. close_job, reply_business_note, register_agent, ask_question, suggest_improvement, post_job, list_jobs, submit_business_profile and 17 more.

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

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

Does the humancollab MCP server send data to outside services?

2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): post_job and reply_business_note.

Has the humancollab MCP server changed its tools?

Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 9, 2026. Every change is on this page and in its Atom feed.