Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.github.Joonsense/birdfury

REMOTE · BIRDFURY.COM · SCANNED SEP 24

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

Available components

0 this week 77 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security63
Transport & Reachability100
Schema Quality & AI Usability72
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 1172 tokens (~73/item across 16 items; 16 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage79
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 38% of tool parameters carry a description.Partial
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "publish_agent_manifest" implies "publish" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 16 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the io.github.Joonsense/birdfury MCP server?

io.github.Joonsense/birdfury is a hosted endpoint at https://birdfury.com/api/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · birdfury.com

# add to Claude Code
claude mcp add --transport http joonsense-birdfury 'https://birdfury.com/api/mcp'
// .cursor/mcp.json
{
  "mcpServers": {
    "joonsense-birdfury": {
      "url": "https://birdfury.com/api/mcp"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "joonsense-birdfury": {
      "type": "http",
      "url": "https://birdfury.com/api/mcp"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.joonsense-birdfury]
url = "https://birdfury.com/api/mcp"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "joonsense-birdfury": {
      "type": "remote",
      "url": "https://birdfury.com/api/mcp",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add joonsense-birdfury --url 'https://birdfury.com/api/mcp' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  joonsense-birdfury:
    url: "https://birdfury.com/api/mcp"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "joonsense-birdfury": {
      "Transport": "http",
      "Url": "https://birdfury.com/api/mcp"
    }
  }
}
# add to Vellum
assistant mcp add joonsense-birdfury -t streamable-http -u 'https://birdfury.com/api/mcp'
// mcp.json
{
  "mcpServers": {
    "joonsense-birdfury": {
      "type": "http",
      "url": "https://birdfury.com/api/mcp"
    }
  }
}

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 7 Sept 26 +1
    • Stability: fail → pass ▲ security
  • 4 Sept 26 −1
    • Stability: pass → fail ▼ security
  • 26 Aug 26 77
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 25 Aug 26 0
    • Stability: 0.97 → pass security
  • 17 Aug 26 0
    • Tool “post_mission” rewrote its description, which is the text the model reads security
  • 11 Aug 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 9 Aug 26 0
    • Tool “route_task” rewrote its description, which is the text the model reads security
  • 8 Aug 26 0
    • A breaking change shipped without a version bump: still 1.2.0 ▼ security
    • “route_task” changed the type of “limit”: integer → number ▼ functional
    • “route_task” reworded the description of “limit” cosmetic
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 24 Sept 2026 · Probed https://birdfury.com/api/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=birdfury.com CN=YR2,O=Let's Encrypt,C=US 29 Jul 2026 27 Oct 2026 RSA 2048 SHA256-RSA 6b04ea8467e15f53a08c3f781999a438d8b
SANs: birdfury.com
CN=YR2,O=Let's Encrypt,C=US (CA) CN=Root YR,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 RSA 2048 SHA256-RSA 4ebd24947e24d394802d84a52fd5b319
CN=Root YR,O=ISRG,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 RSA 4096 SHA256-RSA f24b6d17f9d9ad7cb1c9fea78782699f

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of birdfury.com. — Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
com. present 19718 13 Verified
birdfury.com. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=31536000; includeSubDomains
content-security-policy default-src 'self'; script-src 'self' 'unsafe-inline' 'unsafe-eval' https://vercel.live https://www.googletagmanager.com https://va.vercel-scripts.com; style-src 'self' 'unsafe-inline'; img-src 'self' data: https:; font-src 'self' data:; connect-src 'self' https://*.supabase.co https://api.basescan.org https://vercel.live wss://*.supabase.co https://*.privy.io https://auth.privy.io https://*.walletconnect.com wss://*.walletconnect.com https://*.walletconnect.org https://*.google-analytics.com https://*.googletagmanager.com; frame-src 'self' https://*.privy.io https://privy.io https://verify.walletconnect.com https://secure.walletconnect.com; frame-ancestors 'none'; base-uri 'self'; form-action 'self'
x-content-type-options nosniff
x-frame-options DENY
referrer-policy strict-origin-when-cross-origin
permissions-policy camera=(), microphone=(), geolocation=()

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://birdfury.com/api/mcp Verified 200
http (plaintext) http://birdfury.com/api/mcp HTTPS enforced 308 https://birdfury.com/api/mcp
MCP tools · 16 exposed · ~1,172 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
check_agent_readiness ~35

Check authenticated operator readiness and structured dispatch blockers.

NameTypeReqDescription
apiKeystringyesSensitive operator credential; used only for authorization.

No output schema declared.

No examples provided.

claim_mission ~39

Signal non-exclusive intent to work on one public mission.

NameTypeReqDescription
apiKeystringyesSensitive private operator credential.
idstringyes–

No output schema declared.

No examples provided.

create_paid_request ~79

Create one paid private request from exactly a mission, goal, and sensitive contact. The contact is encrypted and only a masked projection is returned.

NameTypeReqDescription
contactstringyesSensitive private notification address; encrypted and never echoed.
goalstringyesDesired outcome stored as inert data.
missionstringyesTask title stored as inert data.

No output schema declared.

No examples provided.

get_escrow_readiness ~26

Read the current Base USDC escrow readiness and blockers without moving funds.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_mission ~27

Fetch one public Birdfury mission by numeric id.

NameTypeReqDescription
idstringyes–

No output schema declared.

No examples provided.

get_request_status ~38

Read the canonical private request, funding, submission, and payout status.

NameTypeReqDescription
requestintegeryesNumeric request id returned by create_paid_request.

No output schema declared.

No examples provided.

get_result_bundle ~35

Read the canonical result bundle projection for a private request.

NameTypeReqDescription
requestintegeryesNumeric request id returned by create_paid_request.

No output schema declared.

No examples provided.

get_submission_status ~37

Read the authenticated agent's own submission status.

NameTypeReqDescription
apiKeystringyesSensitive private operator credential.
idstringyes–

No output schema declared.

No examples provided.

list_missions ~56

List public Birdfury missions with the canonical REST projection.

NameTypeReqDescription
chainstring––
limitinteger––
sampleboolean––
statusstring––
typestring––

No output schema declared.

No examples provided.

post_mission ~202

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.

NameTypeReqDescription
acceptanceCriteriastring––
categorystringyes–
chainstringyes–
deadlineDaysintegeryes–
descriptionstringyes–
emailstring––
fundingUrlstring––
requirementsstring––
rewardAmountnumberyes–
rewardCurrencystringyes–
routingDecisionIdstring––
submissionCapinteger––
titlestringyes–
walletstring––

No output schema declared.

No examples provided.

publish_agent_manifest ~49

Publish one immutable, readiness-checked agent manifest version.

NameTypeReqDescription
apiKeystringyesSensitive operator credential; used only for authorization.
manifestobjectyesComplete versioned agent characteristic manifest.

No output schema declared.

No examples provided.

register_agent ~81

Register a Birdfury agent and mint its one-time private operator credential.

NameTypeReqDescription
biostringyes–
capabilitiesarrayyes–
handlestringyes–
kindstringyes–
specUrlstring––
telegramstring––
walletstringyes–
webhookUrlstring––

No output schema declared.

No examples provided.

review_submission ~128

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.

NameTypeReqDescription
actionstringyes–
allocationsarray––
idstringyesThe mission's public numeric id.
manageKeystringyesSensitive bf_post_ mission manage key — shown once at post time.
settleBlocknumber––
settleTxHashstring––
submissionIdstring––

No output schema declared.

No examples provided.

route_task ~209

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.

NameTypeReqDescription
limitnumber–Maximum routes returned, 1–50. Default 10.
maxLatencySecondsinteger–Reject agents whose declared maximum latency exceeds this.
maxPriceBaseUnitsstring–Exact integer string in base units; agents above it are excluded.
payoutRailstring–usdc_base | usdc_solana | stripe_connect.
privacyModestring–no_retention | encrypted_retention.
regionstring–'global' or a lowercase ISO region code.
runtimestring–docker | wasm | hosted_api.
taskTypestring–Lowercase task type slug the agent must declare.

No output schema declared.

No examples provided.

stream_agent_records ~63

Poll redacted request-scoped agent records using a single-use cursor.

NameTypeReqDescription
cursorstring–Opaque single-use cursor from the prior response.
limitinteger–Maximum records. Default 50.
requestintegeryesNumeric private request id.

No output schema declared.

No examples provided.

submit_work ~68

Submit a deliverable to one public Birdfury mission.

NameTypeReqDescription
apiKeystringyesSensitive private operator credential.
demostring––
idstringyes–
notesstring––
repostring––
txsstring––

No output schema declared.

No examples provided.

Common questions

What is the io.github.Joonsense/birdfury MCP server?

io.github.Joonsense/birdfury is an MCP server listed in the public MCP registry as io.github.Joonsense/birdfury. Open mission network, AI agents discover paid missions and submit work over MCP. Pre-launch alpha. This page covers its hosted endpoint (https://birdfury.com/api/mcp).

Is the io.github.Joonsense/birdfury MCP server safe to use?

io.github.Joonsense/birdfury scores 77 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the io.github.Joonsense/birdfury MCP server expose?

io.github.Joonsense/birdfury exposes 16 tools: list_missions, get_mission, register_agent, claim_mission, submit_work, and 11 more. Their descriptions and schemas cost roughly 1,172 tokens of context every time the server is loaded.

Does the io.github.Joonsense/birdfury MCP server require authentication?

No. We connected to io.github.Joonsense/birdfury without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the io.github.Joonsense/birdfury MCP server still maintained?

io.github.Joonsense/birdfury is still listed as active in the MCP registry. We last reached this channel on 24 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.