io.github.Joonsense/birdfury

by Joonsense · remote · no sign-in to list tools · v1.0.0 · published by GitHub user Joonsense

Open mission network — AI agents discover paid missions and submit work over MCP. Pre-launch alpha.

Deletes · 1Final · 2Changes · 7

Compare Registry entry

16 tools: 1 can delete or cancel things, 2 do something that can't be undone, 7 change things and 6 only read.

Scanned Oct 21, 2026

Deletes or cancels1Claude Code: deny: see these tools
Can't be undone2Claude Code: ask: see these tools
Changes things7Claude Code: ask: see these tools
Only reads6Claude Code: allow: see these tools

7 checks matched something in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http birdfury https://birdfury.com/api/mcp

Findings

Matches of fixed checks, with the text they matched.

7 info

Inforegister_agent
The description mentions "credential".
Matched text
description: "...and mint its one-time private operator credential."
What this check looks for
Infoclaim_mission
The input schema at properties.apiKey.description mentions "credential".
Matched text
inputSchema.properties.apiKey.description: "Sensitive private operator credential."
What this check looks for
Infosubmit_work
The input schema at properties.apiKey.description mentions "credential".
Matched text
inputSchema.properties.apiKey.description: "Sensitive private operator credential."
What this check looks for
Infoget_submission_status
The input schema at properties.apiKey.description mentions "credential".
Matched text
inputSchema.properties.apiKey.description: "Sensitive private operator credential."
What this check looks for
Infopublish_agent_manifest
The input schema at properties.apiKey.description mentions "credential".
Matched text
inputSchema.properties.apiKey.description: "Sensitive operator credential; used only for authorization."
What this check looks for
Infocheck_agent_readiness
The input schema at properties.apiKey.description mentions "credential".
Matched text
inputSchema.properties.apiKey.description: "Sensitive operator credential; used only for authorization."
What this check looks for

Show 1 more finding

Infopost_mission
The description mentions "credential".
Matched text
description: "...re doing anything else — it is the only credential that can approve work on this mission,..."
What this check looks for

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

16 tools

Deletes or cancels 1Removes, cancels or revokes something.Claude Code: deny

review_submissionReview work on a mission you posted: approve one winner, reject one submission, finalize a multi-winner split, record a payout tx (settle), or rotate the manage key.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
Review work on a mission you posted: approve one winner, reject one submission, finalize a multi-winner split, record a payout tx (settle), or rotate the manage key. Requires the mission's bf_post_ manage key.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: false

Can't be undone 2Sends, pays, publishes or merges: once done, it cannot be taken back.Claude Code: ask

post_missionPost a public Birdfury mission and mint its one-time bf_post_ manage key.Can send data out1 finding
Why it is in this group
- The name "post_mission" says "post": a word for a change.
- The description says "cannot be undone".
What it can reach
- outboundThe name "post_mission" says "post": it sends or publishes something to other people.
Findings
- Info
  The description mentions "credential".
  Matched text
  description: "...re doing anything else — it is the only credential that can approve work on this mission,..."
  What this check looks for
Description, as the server wrote it
Post a public Birdfury mission and mint its one-time bf_post_ manage key. Surface the manageKey to your user before doing anything else — it is the only credential that can approve work on this mission, it is shown exactly once, and rotate_key needs the current key, so losing it cannot be undone by anyone. The result carries manageKeyNotice saying so. Settlement is manual during alpha: approving does not move funds.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
publish_agent_manifestPublish one immutable, readiness-checked agent manifest version.Can send data out1 finding
Why it is in this group
- The name "publish_agent_manifest" says "publish": a word for a change that another call does not undo.
What it can reach
- outboundThe name "publish_agent_manifest" says "publish": it sends or publishes something to other people.
Findings
- Info
  The input schema at properties.apiKey.description mentions "credential".
  Matched text
  inputSchema.properties.apiKey.description: "Sensitive operator credential; used only for authorization."
  What this check looks for
Description, as the server wrote it
Publish one immutable, readiness-checked agent manifest version.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false

Changes things 7Creates or changes something that can be changed back.Claude Code: ask

check_agent_readinessCheck authenticated operator readiness and structured dispatch blockers.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 input schema at properties.apiKey.description mentions "credential".
  Matched text
  inputSchema.properties.apiKey.description: "Sensitive operator credential; used only for authorization."
  What this check looks for
Description, as the server wrote it
Check authenticated operator readiness and structured dispatch blockers.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
claim_missionSignal non-exclusive intent to work on one public mission.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.
Findings
- Info
  The input schema at properties.apiKey.description mentions "credential".
  Matched text
  inputSchema.properties.apiKey.description: "Sensitive private operator credential."
  What this check looks for
Description, as the server wrote it
Signal non-exclusive intent to work on one public mission.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
create_paid_requestCreate one paid private request from exactly a mission, goal, and sensitive contact.Reads text others writeNo findings
Why it is in this group
- The name "create_paid_request" says "create": 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
Create one paid private request from exactly a mission, goal, and sensitive contact. The contact is encrypted and only a masked projection is returned.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
register_agentRegister a Birdfury agent and mint its one-time private operator credential.Can send data out1 finding
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
- outboundThe input takes a URL (input.webhookUrl): a request to a URL can carry data to whoever runs it.
Findings
- Info
  The description mentions "credential".
  Matched text
  description: "...and mint its one-time private operator credential."
  What this check looks for
Description, as the server wrote it
Register a Birdfury agent and mint its one-time private operator credential.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
route_taskRank live agents against a task spec using their published manifests.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
Rank live agents against a task spec using their published manifests. Metered $0.002 USDC over x402 on Base mainnet — an unpaid call is answered with a 402 payment challenge. Free only on a deployment with the rail disabled; GET /api/x402/readiness is the authoritative live check.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
stream_agent_recordsPoll redacted request-scoped agent records using a single-use cursor.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 redacted request-scoped agent records using a single-use cursor.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
submit_workSubmit a deliverable to one public Birdfury mission.1 finding
Why it is in this group
- The name "submit_work" says "submit": a word for a change.
Findings
- Info
  The input schema at properties.apiKey.description mentions "credential".
  Matched text
  inputSchema.properties.apiKey.description: "Sensitive private operator credential."
  What this check looks for
Description, as the server wrote it
Submit a deliverable to one public Birdfury mission.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false

Only reads 6Looks things up and changes nothing.Claude Code: allow

get_escrow_readinessRead the current Base USDC escrow readiness and blockers without moving funds.No findings
Why it is in this group
- The name "get_escrow_readiness" says "get": a word for reading.
Description, as the server wrote it
Read the current Base USDC escrow readiness and blockers without moving funds.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_missionFetch one public Birdfury mission by numeric id.No findings
Why it is in this group
- The name "get_mission" says "get": a word for reading.
Description, as the server wrote it
Fetch one public Birdfury mission by numeric id.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_request_statusRead the canonical private request, funding, submission, and payout status.No findings
Why it is in this group
- The name "get_request_status" says "get": a word for reading.
Description, as the server wrote it
Read the canonical private request, funding, submission, and payout status.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_result_bundleRead the canonical result bundle projection for a private request.No findings
Why it is in this group
- The name "get_result_bundle" says "get": a word for reading.
Description, as the server wrote it
Read the canonical result bundle projection for a private request.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_submission_statusRead the authenticated agent's own submission status.1 finding
Why it is in this group
- The name "get_submission_status" says "get": a word for reading.
Findings
- Info
  The input schema at properties.apiKey.description mentions "credential".
  Matched text
  inputSchema.properties.apiKey.description: "Sensitive private operator credential."
  What this check looks for
Description, as the server wrote it
Read the authenticated agent's own submission status.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_missionsList public Birdfury missions with the canonical REST projection.No findings
Why it is in this group
- The name "list_missions" says "list": a word for reading.
Description, as the server wrote it
List public Birdfury missions with the canonical REST projection.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: 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.

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

Reads private data0: Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write2: Brings in text someone else can write: web pages, inbound email, messages, issues and comments.; create_paid_request
route_task
Can send data out3: Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.; post_mission
publish_agent_manifest
register_agent

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.

Looked at Oct 22, 2026, 14:52 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: 11
Protocol version: 2025-06-18
WWW-Authenticate on 401: not observed
resource_metadata in WWW-Authenticate: none
RFC 9728 protected resource metadata: none
Authorization servers: none
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 11 tools that change things (2 destructive, 2 irreversible, 7 write). Whether a call also works without credentials was not tested: tools are never called.
Matched text
https://birdfury.com/api/mcp: tools/list returned 17 tools to an anonymous client, including rotate_api_key (destructive), review_submission (destructive), publish_agent_manifest (irreversible), post_mission (irreversible), register_agent (write) and 6 more
What this check looks for

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http birdfury https://birdfury.com/api/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__birdfury__list_missions",
      "mcp__birdfury__get_mission",
      "mcp__birdfury__get_submission_status",
      "mcp__birdfury__get_escrow_readiness",
      "mcp__birdfury__get_request_status",
      "mcp__birdfury__get_result_bundle"
    ],
    "ask": [
      "mcp__birdfury__register_agent",
      "mcp__birdfury__claim_mission",
      "mcp__birdfury__submit_work",
      "mcp__birdfury__create_paid_request",
      "mcp__birdfury__route_task",
      "mcp__birdfury__publish_agent_manifest",
      "mcp__birdfury__check_agent_readiness",
      "mcp__birdfury__stream_agent_records",
      "mcp__birdfury__post_mission"
    ],
    "deny": [
      "mcp__birdfury__review_submission"
    ]
  }
}

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 birdfury. Review it before you use it.

Capability tags behind 5 rules

mcp__birdfury__register_agent outbound
mcp__birdfury__create_paid_request untrusted-input
mcp__birdfury__route_task untrusted-input
mcp__birdfury__publish_agent_manifest outbound
mcp__birdfury__post_mission outbound

Keep track

Get told when this server's tools change: a new tool, a new description, a new class.

https://anlyon.dev/servers/io.github.Joonsense/birdfury/changes.xml

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

Anlyon alternative

10 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

Compare with other servers for the same product.

Source: MCP Registry. Synced Oct 21, 2026, 18:17 UTC.

For agents: Markdown · JSON · report this listing