# Attio MCP MCP Server > **Attio MCP MCP Server** is a hosted, multitenant Model Context Protocol (MCP) server run by **MewCP** (https://mewcp.com), giving AI agents managed access to Attio MCP. > > MewCP takes care of all MCP infrastructure for you — credential storage, OAuth flows, > token refresh, and production-grade auto-scaling — so your AI agents can connect to > third-party services and run freely without you managing any MCP server yourself. > > Server page: https://mewcp.com/mcp/attio-mcp > MewCP docs: https://docs.mewcp.com > Full catalog: https://mewcp.com/llms.txt --- ## About Connect AI agents to Attio CRM to search, create, and update contacts, companies, deals, tasks, notes, emails, meetings, and sales pipelines using natural language. --- ## Details - Server ID: `attio-mcp` - Version: 0.1.0 - Tools: 40 - Authentication: OAuth, managed by MewCP - Transport: http --- ## Access The gateway URL below serves your **entire MewCP toolset**, not this server on its own. Pasting a config snippet is not enough — Attio MCP has to be in the toolset first. In order: 1. Add Attio MCP to your toolset at https://mewcp.com/mcp/attio-mcp 2. Connect your Attio MCP account (OAuth); MewCP stores the credential and attaches it to each call 3. Copy your MewCP API key from the dashboard (Developer) 4. Configure your client with the snippet for it below Once connected, an agent does **not** see this server's tools as top-level tools. It sees four meta-tools and reaches everything through them: - `search(query)` — find tools by keyword across the toolset - `get_schema(tools)` — full description and arguments for the tools you picked - `list_accounts(provider)` — only when one app has several connected accounts - `call_tool(server_maskedId, tool_name, args)` — execute So the list below is what `search` can return for this server, not a set of callable tool names on their own. --- ## Tools (40) Descriptions are truncated to 160 characters; call `get_schema` for the full text and the argument schema. Where a tool is annotated, its type is shown — treat `destructive` as irreversible. - `create-comment` _(destructive)_ — Creates a new comment on a record, list entry, or as a reply to an existing comment thread. Provide exactly one of: (parent_object + parent_record_id) for… - `add-record-to-list` _(destructive)_ — Add a record to a list as a new list entry. IMPORTANT: Before calling this tool: 1) You should call list-list-attribute-definitions for the target list to… - `create-list` _(destructive)_ — Creates a new list in Attio. Lists are used to group and track records of a single object type (e.g. a sales pipeline of companies). The list is created… - `create-note` _(destructive)_ — Creates a new note attached to a record. Returns the created note's ID. - `create-record` _(destructive)_ — Create a new record in a given object. IMPORTANT: Before calling this tool, you should call list-attribute-definitions for the target object to understand… - `create-task` _(destructive)_ — Creates a new task in Attio. Tasks can optionally have a deadline, an assignee (workspace member), and be linked to a record (e.g., a person or company). To… - `delete-comment` _(destructive)_ — Deletes a comment. You can only delete comments that you created. Deleting a parent comment will also delete all of its replies. - `get-call-recording` _(read)_ — Retrieves the full details of a call recording by ID, including its status, timestamps, and complete transcript. - `get-email-content` _(read)_ — Retrieves the full content/body of an email. Requires the mailbox_id and email_header_id, which can be obtained from email search results. - `get-note-body` _(read)_ — Get the body of a note by its ID - `get-records-by-ids` _(read)_ — Retrieve a given set of records by their IDs for a given object. Returns an array of records with their attribute values. If a record is not found, it will not… - `list-attribute-definitions` _(read)_ — List attribute definitions for a given object - `list-comment-replies` _(read)_ — Lists replies to a comment. Provide the comment_id of a top-level comment to fetch its replies. Cannot be used with reply comments - only top-level comments… - `list-comments` _(read)_ — Lists comments on a record or list entry. Returns paginated top-level comments with up to 5 replies each. If a thread has more replies, use… - `list-list-attribute-definitions` _(read)_ — List attribute definitions for a given list - `list-lists` _(read)_ — List all lists in the Attio workspace. Returns list metadata including ID, name, API slug, and parent object types. Use the query parameter to filter by name… - `list-objects` _(read)_ — List all objects in the Attio workspace. Objects are the types of record the workspace stores, such as companies, people and deals. Returns object metadata… - `list-records-in-list` _(read)_ — List entries in a given list with optional filtering and sorting. Returns paginated results. Use this tool to retrieve entries within a list that match… - `list-records` _(read)_ — List records in a given object with optional filtering and sorting. Returns paginated results. Use this tool to retrieve records that match specific criteria.… - `list-tasks` _(read)_ — Lists tasks in the workspace with optional filters. Returns paginated results with task content, completion status, assignees, linked records, and deadlines.… - `list-workspace-members` _(read)_ — List members in the Attio workspace. Returns a list of matching members with their ID, email address, name, access level, and team memberships. Use the query… - `list-workspace-teams` _(read)_ — List teams in the workspace. Teams are groups of workspace members used primarily for permission management. Returns an array of teams, each with:… - `merge-records` _(destructive)_ — Merges two records of the same object into one. Where both records have a value for the same attribute, the primary record's value takes precedence. Merging… - `run-basic-report` _(read)_ — Run an aggregate report on records in an object or entries in a list. Use this tool when you need totals, averages, minimums, maximums, or grouped breakdowns.… - `search-call-recordings-by-metadata` _(read)_ — Searches all call recordings across the workspace by their metadata. Useful for finding call recordings based on who was on the call (workspace members or… - `search-emails-by-metadata` _(read)_ — Searches emails visible to the user by their metadata. Useful for finding emails based on participants, domain, and time range. The participant and domain… - `search-meetings` _(read)_ — Search across past and future meetings in the workspace. Returns paginated results with meeting metadata and associated call recording IDs. Useful for finding… - `search-notes-by-metadata` _(read)_ — Searches for notes by their metadata. Useful for finding notes based on parent record, meeting, author (workspace member), and creation time. Returns paginated… - `search-records` _(read)_ — Perform a full-text search for records in a given object. Only searches indexed attributes: domains, email addresses, phone numbers, name/title, description,… - `semantic-search-call-recordings` _(read)_ — Searches all call recordings across the workspace using semantic similarity. Returns call recordings that are most semantically similar to the query, even if… - `semantic-search-emails` _(read)_ — Searches emails visible to the user using semantic similarity. Returns up to 20 emails that are most semantically similar to the query, even if exact keywords… - `semantic-search-notes` _(read)_ — Searches all notes across the workspace using semantic similarity. Returns up to 20 notes that are most semantically similar to the query, even if the exact… - `update-list-entry-by-id` _(destructive)_ — Update attribute values on an existing list entry by its entry ID. Before calling this tool, you must: - Call list-records-in-list to find the entry you want… - `update-list-entry-by-record-id` _(destructive)_ — Update attribute values on a list entry by finding it via its parent record ID. IMPORTANT: This tool will error if the record has zero or multiple entries in… - `update-list` _(destructive)_ — Update a list's name, API slug, or permissions. - `update-note` _(destructive)_ — Appends or prepends plain-text content to an existing note and/or updates its title. At least one of `operation` or `updated_title` must be provided. - `update-record` _(destructive)_ — Use this tool to update people, companies, and other records by `record_id`. - `update-task` _(destructive)_ — Updates an existing task in Attio. You can update the deadline, completion status, assignee, and linked record. To update the assignee, provide their… - `upsert-record` _(destructive)_ — Use this tool to create or update people, companies and other records. A matching attribute is used to search for existing records. If a record is found with… - `whoami` _(read)_ — Returns information about the current user's identity and workspace membership, including their email, name, workspace member ID, access level, workspace name,… --- ## Connect Gateway URL: https://gateway.mewcp.com/personal/mcp Every request carries one header: Authorization: Bearer Replace `API_KEY` with your own key from the dashboard (Developer). ## Apps ### Claude Desktop Mac & Windows app - macOS: `~/Library/Application Support/Claude/claude_desktop_config.json` - Windows: `%APPDATA%\Claude\claude_desktop_config.json` ```json { "mcpServers": { "mewcp": { "command": "npx", "args": [ "-y", "mcp-remote@latest", "https://gateway.mewcp.com/personal/mcp", "--header", "Authorization: Bearer API_KEY" ] } } } ``` Already have an "mcpServers" section in your config? Just add the server entry inside it. 1. Open Claude Desktop → Settings → Developer → "Edit Config" 2. Paste the snippet inside the outer { } of the config file (merge with your existing "mcpServers" section if you have one) 3. Save the file and restart Claude Desktop 4. Start a new conversation — your tool will be available ### VS Code Copilot / Cline - Command Palette → "MCP: Open User Configuration" (opens mcp.json). For one project only, use .vscode/mcp.json instead. ```json { "mcp.servers": { "mewcp": { "type": "http", "url": "https://gateway.mewcp.com/personal/mcp", "headers": { "Authorization": "Bearer API_KEY" } } } } ``` Already have a "servers" section in your mcp.json? Just add the server entry inside it. 1. Open VS Code → Command Palette (Cmd+Shift+P / Ctrl+Shift+P) 2. Run "MCP: Open User Configuration" to open your mcp.json 3. Paste the snippet and save 4. Start the server when prompted (or from the MCP servers view) and use it in Copilot Chat ### Cursor AI-first editor - macOS: `~/.cursor/mcp.json` - Windows: `%USERPROFILE%\.cursor\mcp.json` ```json { "mcpServers": { "mewcp": { "url": "https://gateway.mewcp.com/personal/mcp", "headers": { "Authorization": "Bearer API_KEY" } } } } ``` Already have an "mcpServers" section in your mcp.json? Just add the server entry inside it. 1. Open Cursor → Settings → Cursor Settings → MCP 2. Click "Add new global MCP server" 3. Paste the snippet and save 4. Restart Cursor ### Codex OpenAI's CLI agent - Add the snippet to your Codex MCP config or your standard MCP config file for the CLI tool you use. ```json { "mcpServers": { "mewcp": { "type": "http", "url": "https://gateway.mewcp.com/personal/mcp", "headers": { "Authorization": "Bearer API_KEY" } } } } ``` Codex generally reads a standard MCP server block, so you can add this alongside your other configured servers. 1. Open your Codex MCP config or project-level config file 2. Paste the MewCP server block inside the config JSON/TOML structure your tool expects 3. Save the file and restart Codex 4. Verify the tool is available inside a fresh session ### Claude Code Anthropic's CLI agent - ~/.claude.json (user scope) or .mcp.json in your project root — create it if it doesn't exist. Or skip the file and use the CLI command below. ```json { "mcpServers": { "mewcp": { "type": "http", "url": "https://gateway.mewcp.com/personal/mcp", "headers": { "Authorization": "Bearer API_KEY" } } } } ``` Already have an "mcpServers" section in your config? Just add the server entry inside it. 1. Open ~/.claude.json (or .mcp.json in your project root) in a text editor 2. Paste the snippet inside the outer { } (merge with your existing "mcpServers" section if you have one) 3. Save the file and start (or restart) Claude Code 4. Or skip the file entirely and run the CLI command below instead ### OpenCode Open-source terminal agent - ~/.config/opencode/opencode.json (global) or opencode.json in your project root — create it if it doesn't exist. ```json { "$schema": "https://opencode.ai/config.json", "mcp": { "mewcp": { "type": "remote", "url": "https://gateway.mewcp.com/personal/mcp", "enabled": true, "headers": { "Authorization": "Bearer API_KEY" } } } } ``` Already have an "mcp" section in your opencode.json? Just add the server entry inside it. 1. Open ~/.config/opencode/opencode.json (or opencode.json in your project root) in a text editor 2. Paste the snippet inside the outer { } (merge with your existing "mcp" section if you have one) 3. Save the file and start (or restart) OpenCode ### OpenClaw Self-hosted agent gateway - ~/.openclaw/openclaw.json — create it if it doesn't exist. ```json { "mcp": { "servers": { "mewcp": { "transport": "streamable-http", "url": "https://gateway.mewcp.com/personal/mcp", "enabled": true, "headers": { "Authorization": "Bearer API_KEY" } } } } } ``` Already have an "mcp" section in your openclaw.json? Just add the server entry inside "servers". 1. Open ~/.openclaw/openclaw.json in a text editor 2. Paste the snippet inside the outer { } (merge with your existing "mcp" section if you have one) 3. Save the file and restart OpenClaw ### Antigravity Google's agentic IDE - ~/.gemini/config/mcp_config.json (global) or .agents/mcp_config.json (workspace-local) — create it if it doesn't exist. ```json { "mcpServers": { "mewcp": { "serverUrl": "https://gateway.mewcp.com/personal/mcp", "headers": { "Authorization": "Bearer API_KEY" } } } } ``` Already have an "mcpServers" section in your config? Just add the server entry inside it. Remote servers must use the "serverUrl" field — the legacy "url"/"httpUrl" fields aren't supported. 1. In the editor's agent side panel, click "…" → "MCP Servers" → "Manage MCP Servers" → "View raw config" (Antigravity CLI: type /mcp instead to open the Interactive MCP Manager) 2. Paste the snippet inside the outer { } (merge with your existing "mcpServers" section if you have one) 3. Save the file — the server connects automatically ### Hermes Nous Research's CLI agent - config.yaml in your Hermes config directory (~/.hermes) — add this under a top-level "mcp_servers:" key. ```yaml mcp_servers: mewcp: url: "https://gateway.mewcp.com/personal/mcp" headers: Authorization: "Bearer API_KEY" ``` Already have an "mcp_servers" section in your config.yaml? Just add the server entry inside it. 1. Open config.yaml in your Hermes config directory 2. Paste the snippet under the top-level "mcp_servers:" key (merge with existing entries if you have any) 3. Save the file, then run /reload-mcp in Hermes (or start a fresh session) 4. Ask Hermes "Tell me which MCP-backed tools are available right now" to confirm it connected ### DeepSeek Harness DeepSeek's agent harness - cordis.yml in your DSH project — or the patch file you mount plugins from. ```yaml - id: mcp-mewcp name: '@deepseek-ai/dsh-mcp-client' config: serverName: mewcp transport: streamable-http url: https://gateway.mewcp.com/personal/mcp headers: Authorization: "Bearer API_KEY" ``` One plugin instance = one MCP server. Add this entry to your plugin list; don't nest it inside another entry. 1. Open cordis.yml (or your patch file) in your DSH project 2. Paste the entry into your plugin list, keeping the leading dash and indentation 3. Restart DSH (or let HMR reload) — tools register as mcp__mewcp__ 4. Verify with: dsh web --dump-config | grep -A3 mcp ## SDKs ### Python fastmcp client ```python import asyncio from fastmcp import Client from fastmcp.client.transports import StreamableHttpTransport SERVER_URL = "https://gateway.mewcp.com/personal/mcp" API_KEY = "API_KEY" transport = StreamableHttpTransport( url=SERVER_URL, headers={ "Authorization": f"Bearer {API_KEY}", } ) async def main(): client = Client(transport) async with client: tools = await client.list_tools() print(tools) asyncio.run(main()) ``` 1. Install fastmcp: pip install fastmcp 2. Copy the snippet into your project 3. Replace API_KEY with your key from the dashboard 4. Run your script ### TypeScript MCP SDK ```typescript import { Client } from "@modelcontextprotocol/sdk/client/index.js"; import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp.js"; const SERVER_URL = "https://gateway.mewcp.com/personal/mcp"; const API_KEY = "API_KEY"; const transport = new StreamableHTTPClientTransport(new URL(SERVER_URL), { requestInit: { headers: { Authorization: `Bearer ${API_KEY}`, }, }, }); const client = new Client({ name: "mewcp-client", version: "1.0.0" }); await client.connect(transport); const tools = await client.listTools(); console.log(tools.tools.map((t) => t.name)); ``` 1. Install: npm install @modelcontextprotocol/sdk 2. Copy the snippet into your project 3. Replace API_KEY with your key from the dashboard 4. Run with Node 18+ as an ES module (e.g. npx tsx script.ts)