crewio-mcp
Hosted HTTP MCP server that exposes Crewio CRM as tools for AI assistants, enabling CRUD operations on deals, contacts, companies, comments, and full-text search.
README
crewio-mcp
Hosted HTTP MCP server that exposes your Crewio CRM as tools for AI assistants (Cursor, Claude Desktop, etc.).
Tools
| Tool | Description |
|---|---|
list_deals |
List deals with optional search, status filter, and pagination |
get_deal |
Get full deal details by ID |
create_deal |
Create a new deal |
update_deal |
Update an existing deal |
list_contacts |
List contacts with optional search and pagination |
get_contact |
Get full contact details by ID |
create_contact |
Create a new contact |
update_contact |
Update an existing contact |
list_companies |
List companies with optional search and pagination |
get_company |
Get full company details by ID |
create_company |
Create a new company |
update_company |
Update an existing company |
list_comments |
List comments on a deal, contact, or company |
create_comment |
Post a comment on a deal, contact, or company |
search |
Full-text search across deals, contacts, and companies |
Setup
cp .env.example .env
# Edit .env and set CREWIO_API_URL
npm install
npm run dev
Connecting to Cursor
Add to your Cursor MCP settings (.cursor/mcp.json):
{
"mcpServers": {
"crewio": {
"url": "http://localhost:3002/mcp",
"headers": {
"Authorization": "Bearer <your_crewio_api_token>",
"X-Workspace-Id": "<your_workspace_id>"
}
}
}
}
The server is stateless — each request is authenticated independently via the Authorization and X-Workspace-Id headers, so multiple users can share a single hosted instance with their own tokens.
Authentication
Requests must include two headers:
Authorization: Bearer <token>— your Crewio API tokenX-Workspace-Id: <id>— your workspace ID
These are forwarded as-is to the Crewio backend on every tool call.
Development
npm run dev # Start with hot-reload
npm run typecheck # TypeScript type check
npm run lint # oxlint
npm run lint:fix # oxlint --fix
npm run format # oxfmt
npm run format:check # oxfmt --check
npm run build # Compile to dist/
Docker
The image runs with NODE_ENV=production (JSON logs, no pino-pretty). Do not override it from .env.
docker build -t crewio-mcp .
docker run -p 3002:3002 -e CREWIO_API_URL=http://host.docker.internal:3000 crewio-mcp
Coolify: Dockerfile at repo root, expose port 3002. Runtime env: CREWIO_API_URL=https://api.yourapp.com (no trailing slash).
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.