agent-registry
agent-registry — реестр AI-агентов на базе стандарта A2A от Agentry
От сообщества: Добавлен пользователем или импортирован; проверьте владельца перед подключениемРаботаетБез входаГлобальныйБесплатноТолько чтение
Что умеет
- Искать и просматривать агентов по категориям и возможностям
- Получать карточку агента в формате A2A
- Регистрировать нового агента в реестре
- Запускать проверку безопасности агента и получать результаты
- Создавать и проверять платежи в ecash между агентами
Какие данные видит
Ассистент читает публичные карточки агентов; регистрация и платёжные операции требуют идентификатора агента.
Нужен ли аккаунт
Не нужен: сервер работает без входа
agent-registry, сервис Agentry, — каталог AI-агентов, построенный на протоколе A2A. MCP-сервер позволяет искать и регистрировать агентов, получать их карточки, проводить проверки безопасности и обрабатывать платежи в ecash между агентами.
Как подключить
Как подключить agent-registry к Claude
Адрес сервера, который нужно вставить в настройках Claude:
https://agent-registry--agentry.run.tools
- Откройте Claude (сайт claude.ai или приложение для компьютера).
- Перейдите в Настройки → Коннекторы (в английском интерфейсе: Settings → Connectors).
- Нажмите Добавить пользовательский коннектор (Add custom connector).
- Вставьте адрес сервера, скопированный ниже, в поле URL удалённого MCP-сервера и нажмите Добавить.
- В чате нажмите + → Коннекторы и включите новый коннектор.
Пользовательские коннекторы доступны на тарифах Free, Pro, Max, Team и Enterprise. На Free можно добавить только один. В Team и Enterprise коннектор сначала добавляет владелец организации в Настройки организации → Коннекторы.
Авторизация
После нажатия Добавить откроется окно входа в сервис. Войдите под своим аккаунтом и подтвердите доступ. Пароль Claude не видит.
Как подключить agent-registry к ChatGPT
Адрес сервера, который нужно вставить в настройках ChatGPT:
https://agent-registry--agentry.run.tools
- Откройте ChatGPT в браузере (chatgpt.com). Нужен тариф Plus, Pro, Business, Enterprise или Edu.
- Один раз включите режим разработчика: Настройки → Приложения → Дополнительные настройки → Режим разработчика (Settings → Apps → Advanced settings → Developer mode).
- Откройте Настройки → Коннекторы и нажмите Создать (Create).
- Заполните форму: Название (любое), Описание (одна фраза, что делает сервис), URL MCP-сервера (скопируйте ниже).
- В поле Аутентификация выберите OAuth, если сервис требует вход, иначе Нет. Нажмите Создать.
- В новом чате откройте + → Приложения/Коннекторы и включите коннектор.
Название раздела у OpenAI менялось (Connectors → Apps/Plugins). Если пункт называется иначе, ищите «режим разработчика» в настройках. В рабочих пространствах Business/Enterprise администратор должен разрешить пользовательские коннекторы.
Авторизация
При первом использовании ChatGPT откроет окно входа в сервис. Войдите и подтвердите доступ.
Как подключить agent-registry к Cursor
Адрес сервера, который нужно вставить в настройках Cursor:
https://agent-registry--agentry.run.tools
Быстрый способ: нажмите кнопку Открыть в Cursor ниже, Cursor сам предложит добавить сервер.
Вручную:
- В Cursor откройте Settings → Cursor Settings → MCP и нажмите Add new global MCP server.
- Вставьте JSON, скопированный ниже, в открывшийся файл
~/.cursor/mcp.json(для одного проекта:.cursor/mcp.jsonв корне проекта). - Сохраните файл. Сервер появится в списке MCP; при необходимости пройдите авторизацию по кнопке рядом с ним.
Авторизация
Если сервис требует вход, рядом с сервером в списке MCP появится кнопка авторизации.
Список инструментов сервера (36)
Технические названия из tools/list. Нужны только разработчикам.
| a2a_public_discovery_api_agents_public_get | 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 |
| a2a_public_agent_card_api_agents_public__agent_id__get | A2A Public Agent Card Return a single agent's A2A card by ID. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json |
| list_agents_api_agents_get | 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 |
| search_agents_api_agents_search_get | Search 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 |
| list_categories_api_agents_categories_get | List 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 } ] ``` |
| get_agent_api_agents__agent_id__get | 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 |
| register_agent_api_agents_register_post | 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 |
| submit_intake_api_broker_intake_post | Submit 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 |
| get_intake_api_broker_intake__intake_id__get | Get 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 |
| trigger_scan_api_scanner_scan_post | 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 |
| get_scan_results_api_scanner_results_get | 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 |
| get_mint_info_api_payments_ecash_mint_info_get | Get Mint Info Get info about a Cashu mint (NUT-06). ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json |
| get_mint_keys_api_payments_ecash_mint_keys_get | Get Mint Keys Get active public keys from a Cashu mint (NUT-01). ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json |
| get_mint_keysets_api_payments_ecash_mint_keysets_get | Get Mint Keysets Get all keysets from a Cashu mint (NUT-02). ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json |
| create_quote_api_payments_ecash_mint_quote_post | Create 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 |
| check_quote_api_payments_ecash_mint_quote__quote_id__get | Check Quote Check the payment status of a mint quote. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json |
| create_melt_quote_api_payments_ecash_melt_quote_post | 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 |
| send_ecash_api_payments_ecash_send_post | 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 |
| receive_ecash_api_payments_ecash_receive_post | 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 |
| verify_token_api_payments_ecash_verify_post | Verify Token Verify a Cashu ecash token — check format, amount, and spent status. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json |
| get_payment_profile_api_payments_ecash_profile__agent_id__get | Get Payment Profile Get an agent's ecash payment profile. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json |
| update_payment_profile_api_payments_ecash_profile__agent_id__put | Update Payment Profile Update an agent's ecash payment profile. Requires admin key for now. In future, agent owners can self-serve. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json |
| list_transactions_api_payments_ecash_transactions_get | List Transactions List ecash transactions, optionally filtered by agent or type. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json |
| agent_payment_summary_api_payments_ecash_summary__agent_id__get | Agent Payment Summary Get payment summary for an agent — totals, balance, tx count. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json |
| payment_required_api_payments_ecash_402__agent_id__get | 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 |
| list_ecash_agents_api_payments_ecash_agents_get | List Ecash Agents List all agents that have ecash payments enabled. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json |
| trigger_discovery_cycle_api_registry_discover_post | Trigger Discovery Cycle Run a full discovery cycle across all agents in the registry. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json |
| discover_single_agent_api_registry_discover__agent_id__post | Discover Single Agent Discover / re-check a single agent's A2A Agent Card. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json |
| get_agent_trust_api_agents__agent_id__trust_get | Get Agent Trust Get the trust report for an agent. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json |
| get_card_history_api_agents__agent_id__card_history_get | Get Card History Get AgentCard snapshot history for an agent. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json |
| get_registry_stats_api_registry_stats_get | Get Registry Stats Get registry-wide statistics. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json |
| claim_agent_api_agents_claim_post | Claim Agent Developer claims ownership of an existing agent listing. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json |
| send_outreach_api_admin_outreach_post | Send Outreach Admin endpoint to send trust score outreach to a specific agent contact. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json |
| get_badge_svg_api_badges__agent_id__svg_get | Get Badge Svg Return an SVG badge for an agent listing. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json |
| get_badge_json_api_badges__agent_id__json_get | 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 |
| get_badge_embed_code_api_badges__agent_id__embed_get | Get Badge Embed Code Return embed code snippets for an agent's badge. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json |