@attrove/mcp
v0.1.6
Published
MCP server for Attrove - AI-powered context retrieval for Claude and Cursor
Maintainers
Readme
@attrove/mcp
MCP (Model Context Protocol) server for Attrove. Enables AI assistants like Claude and Cursor to access your users' unified context from Gmail, Slack, Google Calendar, and more.
Installation
npm install @attrove/mcp
# or
yarn add @attrove/mcp
# or
pnpm add @attrove/mcpQuick Start
Claude Desktop
Add to your Claude Desktop configuration (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"attrove": {
"command": "npx",
"args": ["@attrove/mcp"],
"env": {
"ATTROVE_API_KEY": "sk_...",
"ATTROVE_USER_ID": "user-uuid"
}
}
}
}Cursor
- Open Cursor Settings (
Cmd+,on macOS,Ctrl+,on Windows/Linux) - Search for "MCP" or navigate to Features > MCP Servers
- Click "Edit in settings.json" or add directly:
{
"mcpServers": {
"attrove": {
"command": "npx",
"args": ["@attrove/mcp"],
"env": {
"ATTROVE_API_KEY": "sk_...",
"ATTROVE_USER_ID": "user-uuid"
}
}
}
}- Restart Cursor for changes to take effect
- In the chat, you can now ask questions about your connected integrations
Claude Code (Terminal)
If using Claude Code in the terminal, the MCP server is configured via environment variables:
export ATTROVE_API_KEY="sk_..."
export ATTROVE_USER_ID="user-uuid"Direct CLI Usage
ATTROVE_API_KEY=sk_... ATTROVE_USER_ID=user-uuid npx @attrove/mcpCommon Use Cases
Once connected, you can ask your AI assistant natural language questions. Here are some examples:
Meeting prep:
"What context do I need for my 2pm meeting with the marketing team?"
Email follow-ups:
"Are there any emails from last week that I haven't responded to?"
Project status:
"What's the latest on the Q4 roadmap discussions?"
People search:
"What has John from Acme Corp been asking about recently?"
Historical context:
"Find the thread where we discussed the pricing changes last month"
Available Tools
attrove_query
Ask questions about the user's communications and get AI-generated answers.
Parameters:
query(required): The question to askintegration_ids(optional): Filter to specific integration IDs (UUIDs, e.g.,["550e8400-e29b-41d4-a716-446655440000"])include_sources(optional): Include source snippets
Example prompts:
- "What did Sarah say about the Q4 budget?"
- "Summarize my meeting with the engineering team"
- "What are the action items from yesterday's standup?"
- "When is my next meeting with the product team?"
- "What context do I need before my 3pm call?"
attrove_search
Search for specific messages or conversations.
Parameters:
query(required): The search queryafter_date(optional): Only messages after this date (ISO 8601)before_date(optional): Only messages before this datesender_domains(optional): Filter by sender domainsinclude_body_text(optional): Include message content (default: true)
Example prompts:
- "Find all emails about the product launch"
- "Show me conversations with the marketing team"
- "Search for messages mentioning the deadline extension"
- "Find discussions with acme.com from last month"
attrove_integrations
List the user's connected integrations.
Parameters: None
Example prompts:
- "What services are connected?"
- "Show me my integrations"
Environment Variables
| Variable | Required | Description |
|----------|----------|-------------|
| ATTROVE_API_KEY | Yes | Your Attrove API key (sk_...) |
| ATTROVE_USER_ID | Yes | User ID to scope API calls |
| ATTROVE_BASE_URL | No | Custom API base URL |
| ATTROVE_DEBUG | No | Set to true for verbose error logging |
Programmatic Usage
You can also use the server programmatically:
import { createServer, startServer } from '@attrove/mcp';
// Create a server instance
const server = createServer({
apiKey: 'sk_...',
userId: 'user-uuid'
});
// Or start directly with stdio transport
await startServer({
apiKey: 'sk_...',
userId: 'user-uuid'
});Getting API Credentials
- Sign up at attrove.com
- Create an organization in the dashboard
- Generate an API key (
sk_...) - Provision a user to get a user ID
import { Attrove } from '@attrove/sdk';
const admin = Attrove.admin({
clientId: 'your-client-id',
clientSecret: 'your-client-secret'
});
// Create a user
const { id, apiKey } = await admin.users.create({
email: '[email protected]'
});
// Use `apiKey` as ATTROVE_API_KEY and `id` as ATTROVE_USER_IDTroubleshooting
"ATTROVE_API_KEY environment variable is required"
Make sure you've set the environment variables correctly in your MCP configuration.
Tools not showing up
- Restart Claude/Cursor after configuration changes
- Check the MCP server logs for errors
- Verify your API key is valid
Debugging errors
Set ATTROVE_DEBUG=true to enable verbose error logging with stack traces:
{
"mcpServers": {
"attrove": {
"command": "npx",
"args": ["@attrove/mcp"],
"env": {
"ATTROVE_API_KEY": "sk_...",
"ATTROVE_USER_ID": "user-uuid",
"ATTROVE_DEBUG": "true"
}
}
}
}Rate limiting
The Attrove API has rate limits. If you're making many requests, you may need to wait before trying again.
Requirements
- Node.js 18.0.0 or later
AI-Friendly Documentation
For AI assistants and code generation tools, Attrove provides machine-readable documentation:
- llms.txt:
https://attrove.com/llms.txt- Condensed API reference for LLMs - Quickstart:
https://github.com/attrove/quickstart- Example code with CLAUDE.md context
Links
License
MIT
