Attio Simple

Provides an MCP server to manage Attio CRM objects via AI clients, with schema discovery and type-safe operations.

typescript

1

GitHub Stars

typescript

Language

4 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "mlemos-attio-simple-mcp-server": {
      "command": "node",
      "args": [
        "/absolute/path/to/attio-mcp/dist/index.js"
      ],
      "env": {
        "ATTIO_API_KEY": "your_api_key_here",
        "ATTIO_WORKSPACE_SLUG": "your-workspace-slug"
      }
    }
  }
}

You run an MCP server that connects Attio CRM to AI clients, enabling natural language tools to manage your workspace data. This server provides a type-safe bridge with tools for discovering your schema and performing common Attio operations across companies, people, and notes, all controllable via AI assistants.

How to use

You interact with the Attio MCP Server through your chosen AI client. The server exposes tools that let you search, read, create, and update Attio objects, while translating responses into concise, AI-friendly formats. Start the server locally or point your AI client to a running MCP endpoint, then configure your client to use the provided tools. You will be able to perform actions like finding companies or people, creating notes, and adjusting attributes in a structured, type-safe way.

How to install

Prerequisites: Node.js and npm must be installed on your system.

# 1. Install Dependencies
npm install

# 2. Configure Environment
cp .env.example .env

# Edit .env and add your Attio API key
ATTIO_API_KEY="your_api_key_here"
ATTIO_WORKSPACE_SLUG="your-workspace-slug"  # Optional: for web URLs

# 3. Build
npm run build

# 4. Configure Your AI Client (examples shown below are configurations you can adapt)

Configuration and usage notes

The server integrates Attio via an API key, and you can point AI clients to the built distribution once the build completes. For AI clients, there are ready-made configurations for popular tools, and you can add your own objects by discovering your workspace schema and creating corresponding tools.

Adding Custom Objects

To add tools for custom Attio objects, follow these steps:

1. Use `get_workspace_schema` to discover your workspace's objects and attributes
2. Copy an existing tool (e.g., `search_companies.ts`) as a template
3. Modify the API endpoint, fields, and types for your custom object
4. Register the new tool in `src/tools/index.ts

Development

For ongoing development, you can run in watch mode, build, and test as you refine tools and configurations.

npm run dev          # Watch mode
npm run build        # Build
npm test             # Run tests
npm run test:watch   # Watch tests

Available tools

get_workspace_schema

Discovers the objects and attributes available in your Attio workspace, enabling schema discovery and dynamic tool generation.

search_companies

Searches for companies in Attio based on your query and filters.

get_company

Fetches details for a specific company by ID or attribute.

create_company

Creates a new company with specified fields.

update_company

Updates fields for an existing company.

manage_company_domains

Manages domains associated with a company.

search_people

Searches for people in Attio based on your query and filters.

get_person

Fetches details for a specific person by ID or attribute.

create_person

Creates a new person with specified fields.

update_person

Updates fields for an existing person.

manage_person_emails

Manages email addresses associated with a person.

manage_person_tags

Manages tags associated with a person.

create_note

Creates a new note linked to a workspace entity.

get_note

Retrieves a note by its ID.