mcp-remote-server by saurav-rcrm - MCP Server

RecruitCRM MCP Server

This project is an MCP (Model-Controlled Program) server for interacting with the RecruitCRM API. It can be run locally for development or deployed as a remote web service to be used with any LLM platform.

Local Development

To run the server on your local machine for testing and development:

Create a virtual environment:

python -m venv venv
source venv/bin/activate

Install dependencies:
```
pip install -r requirements.txt
```
Set up your environment variables: Create a file named .env in the project root and add your RecruitCRM API token:
```
RCRM_TOKEN="your-api-token-here"
```
Run the server:
```
python recruitcrm_mcp.py
```
The server will start on http://0.0.0.0:8000.

Deployment to Render

This application is configured for production deployment on Render.

Push your code to GitHub: Create a new repository on GitHub and push this project's code.
Create a New Web Service on Render:
- Go to your Render Dashboard and click New + > Web Service.
- Connect your GitHub account and select your repository.
Configure the Service:
- Name: A name for your service (e.g., recruitcrm-mcp-server).
- Runtime: Render should automatically detect Python 3.
- Build Command: pip install -r requirements.txt
- Start Command: python3 recruitcrm_mcp.py. Render will use the command from the Procfile.
Add Environment Variables:
- Go to the Environment tab for your new service.
- Add a Secret File:
  - Filename: .env
  - Contents: RCRM_TOKEN="your-api-token-here"
- This keeps your API token secure.
Deploy:
- Click Create Web Service.
- Render will build and deploy your application. Once complete, you will get a public URL (e.g., https://your-app-name.onrender.com).

Using the Remote MCP Server

Once deployed, you can use your MCP server as a custom tool in any LLM platform that supports them (like OpenAI's Assistants API).

Use the following configuration:

URL: https://your-app-name.onrender.com/mcp
Transport: sse (Server-Sent Events)