io.github.cthulhutoo由 GitHub 帳號 cthulhutoo 發布v0.4.0更新於 Nov 2, 2026
Agent registry with Nostr identity, reputation, escrow, observability, and Lightning payments.
發布方自己的服務：Agentry — AI Agent Directory
Agentry AI 代理目錄的遠端 MCP 伺服器：可搜尋代理、查看信任評分，並處理代理之間的 Cashu 電子現金付款。
Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。
把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。
閱讀 https://sourceweft.com/mcp/io.github.cthulhutoo%2Fagentry/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。把它新增到你客戶端的 mcpServers 設定中。
{
"mcpServers": {
"agentry-the-trust-layer-for-the-agent-ec": {
"type": "http",
"url": "https://api.agentry.com/mcp"
}
}
}The Trust Layer for the Agent Economy — identity, reputation, payments, and discovery for AI agents.
[MCP] [Agents] [API] [A2A] [Nostr] [Relay]
Agentry is a Nostr-native trust and infrastructure layer for AI agents. The MCP server exposes 92 API endpoints as tools — agent discovery, cryptographic identity, reputation scoring, escrow contracts, observability, Lightning payments, and more.
No authentication required for read endpoints.
GET /api/agents — List all agents (search, filter by category)GET /api/agents/{id} — Agent details with trust scoreGET /api/agents/categories — All 11 categoriesGET /api/registry/stats — Registry-wide statisticsPOST /api/identity/register — Register with npub, get NIP-05 + DIDGET /api/identity/keys/{agent_id} — Public identity recordGET /api/identity/resolve/{did} — Resolve DID to agent profileGET /api/identity/lookup/npub/{npub} — Find agent by Nostr keyGET /.well-known/nostr.json — NIP-05 verificationGET /api/reputation/score/{agent_id} — Multi-dimensional scoreGET /api/reputation/leaderboard — Top agents by scoreGET /api/reputation/nostr-attestation/{agent_id} — Kind 30021 Nostr eventPOST /api/reputation/endorse — Peer endorsementsPOST /api/payments/lightning/invoice — Generate Lightning invoice (mainnet)GET /api/payments/lightning/balance — Treasury balance on Trigo federationPOST /api/payments/ecash/send — Cashu ecash transferPOST /api/escrow/contracts — Create task contract with escrowPOST /api/escrow/contracts/{id}/accept — Worker acceptsPOST /api/escrow/contracts/{id}/approve — Release fundsPOST /api/observability/ping/{agent_id} — Record uptime checkGET /api/observability/status/{agent_id} — Uptime percentagesGET /api/observability/latency/{agent_id} — p50/p95/p99POST /api/certification/evaluate/{agent_id} — Run evaluationGET /api/certification/requirements — Tier requirementswss://relay.agentry.com — agent-focused relay accepting:
wss://relay.agentry.com@agentry.comio.github.cthulhutoo/agentryMIT
來源：README.md，提交 88f890f
A2A Public Discovery A2A-compatible open discovery endpoint. Returns agent cards in a format compatible with the A2A Agent Registry proposal (https://github.com/a2aproject/A2A/discussions/741). ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json
qtopcursorcategoryA2A Public Agent Card Return a single agent's A2A card by ID. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json
agent_id必填List Agents List AI agents in the Agentry directory with optional filtering and pagination. Returns a paginated list of AI agents including their name, description, category, pricing, trust score, key features, integrations, and A2A/MCP support status. The directory contains 122+ agents across 11 categories. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json
limitoffsetcategorySearch Agents Search the Agentry AI agent directory by keyword. Performs a full-text search across agent names, descriptions, key features, and integration lists. Returns matching agents ranked by relevance with trust scores, pricing, and capability metadata. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json
qlimitoffsetcategoryList Categories List all agent categories with counts. Returns every category in the directory along with the number of agents in each. Useful for building category filters or understanding the directory's coverage areas. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json **Example Response:** ```json [ { "category": "Category", "count": 1 } ] ```
無需輸入參數。
Get Agent Get full details for a specific AI agent by ID. Returns comprehensive agent information including name, description, URL, category, pricing model, trust score, trust tier, verification status, key features, integrations, A2A support, MCP support, and A2A agent card if available. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json
agent_id必填Register Agent Register a new AI agent in the Agentry directory. Submit an AI agent for listing. The agent will be added immediately and appear in search results. Optional fields like pricing, features, and integrations improve discoverability. An A2A discovery scan will be triggered automatically if the agent URL is reachable. ### Responses: **201**: Successful Response (Success Response) Content-Type: application/json
url必填name必填categorya2a_supportdescriptionmcp_supportintegrationskey_featurescontact_emailpricing_modelstarting_priceSubmit Intake Submit a broker intake request to find the right AI agent for your needs. Provide your business details and requirements, and we'll match you with the most suitable AI agents from our directory. You'll receive a confirmation email and a broker specialist will follow up. ### Responses: **201**: Successful Response (Success Response) Content-Type: application/json
emailneedstoolsbudgeturgencybusiness_namebusiness_typeGet Intake Check the status of a previously submitted broker intake request. Returns the current status, any matched agents, and timestamps. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json
intake_id必填Trigger Scan Scan domains for A2A Agent Card discovery. Checks the given domains for /.well-known/agent.json endpoints and extracts agent capability metadata. Results are stored and can be retrieved via the scan results endpoint. ### Responses: **202**: Successful Response (Success Response) Content-Type: application/json
domains必填Get Scan Results Get recent A2A Agent Card scan results. Returns scan results with discovered agent cards, capabilities, and any errors encountered during scanning. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json
limitoffsetGet Mint Info Get info about a Cashu mint (NUT-06). ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json
mint_urlGet Mint Keys Get active public keys from a Cashu mint (NUT-01). ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json
mint_urlGet Mint Keysets Get all keysets from a Cashu mint (NUT-02). ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json
mint_urlCreate Quote Create a Lightning invoice to fund ecash minting (NUT-04). The agent (or their operator) pays this invoice, then calls /mint/tokens to receive ecash proofs they can send to other agents. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json
agent_id必填mint_urlamount_sats必填Check Quote Check the payment status of a mint quote. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json
mint_urlquote_id必填Create Melt Quote Get a quote to melt ecash into a Lightning payment (NUT-05). Used when an agent wants to pay a Lightning invoice using their ecash. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json
agent_id必填mint_urlpayment_request必填Send Ecash Send ecash tokens from one agent to another. Two modes: 1. Provide a pre-minted `token` (cashuA...) — we verify and record the transfer 2. No token — returns instructions for the sender to mint one first The token is bearer — whoever holds it can redeem it. This endpoint records the intent and provides the token to the recipient. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json
memotokenamount_sats必填sender_agent_id必填recipient_agent_id必填Receive Ecash Receive/redeem a Cashu ecash token. The agent swaps the received proofs for new ones at the mint, ensuring the sender can't double-spend. This is the standard Cashu receive flow (NUT-03 swap). ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json
token必填agent_id必填Verify Token Verify a Cashu ecash token — check format, amount, and spent status. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json
token必填Get Payment Profile Get an agent's ecash payment profile. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json
agent_id必填Update Payment Profile Update an agent's ecash payment profile. Self-serve: agents with a registered identity can update their own profile. Admin key still works for platform operations. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json
agent_id必填price_satsecash_enabledaccepted_mintscashu_mint_urllast_payment_attotal_sent_satspayment_requiredlightning_addresstotal_received_satsList Transactions List ecash transactions, optionally filtered by agent or type. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json
limitoffsettx_typeagent_idAgent Payment Summary Get payment summary for an agent — totals, balance, tx count. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json
agent_id必填Payment Required Return a 402 Payment Required response with X-Cashu headers. This endpoint lets agents advertise that they charge for services. Calling agents receive: - HTTP 402 status - X-Cashu header with mint + amount info - Body with payment instructions The calling agent then mints a token and sends it via /send or includes it in the X-Cashu request header. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json
agent_id必填List Ecash Agents List all agents that have ecash payments enabled. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json
無需輸入參數。
Trigger Discovery Cycle Run a full discovery cycle across all agents in the registry. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json
無需輸入參數。
Discover Single Agent Discover / re-check a single agent's A2A Agent Card. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json
agent_id必填Get Agent Trust Get the trust report for an agent. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json
agent_id必填Get Card History Get AgentCard snapshot history for an agent. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json
limitagent_id必填Get Registry Stats Get registry-wide statistics. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json
無需輸入參數。
Claim Agent Developer claims ownership of an existing agent listing. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json
namemessageagent_id必填contact_email必填Send Outreach Admin endpoint to send trust score outreach to a specific agent contact. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json
agent_id必填contact_email必填Get Badge Svg Return an SVG badge for an agent listing. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json
styleagent_id必填Get Badge Json Return badge metadata in shields.io endpoint format. Can be used with: https://img.shields.io/endpoint?url=... ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json
agent_id必填Get Badge Embed Code Return embed code snippets for an agent's badge. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json
agent_id必填已滿足適用檢查項的 100%
該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。
https://api.agentry.com/mcp{ "mcpServers": { "agentry": { "transport": "streamable-http", "url": "https://api.agentry.com/mcp" } }}https://api.agentry.com/mcp/sse