Skip to main content

MCP server for CBT Clinical Review Multi-Agent System

Project description

Cerina MCP Server

MCP (Model Context Protocol) server that exposes the CBT Clinical Review Multi-Agent System as tools for AI assistants like Claude Desktop.

Features

  • create_cbt_exercise: Create CBT exercises using the multi-agent workflow
  • list_exercises: List approved exercises from the database
  • get_session_status: Check status of exercise creation sessions
  • approve_exercise: Approve exercises awaiting human review

Prerequisites

  1. Python 3.13+
  2. uv package manager
  3. Cerina Foundry backend running at http://localhost:8000

Installation

cd mcp
uv sync

Claude Desktop Configuration

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

Daily Use

{
  "mcpServers": {
    "cerina-mcp": {
      "command": "uv",
      "args": [
        "--directory",
        "/Users/jagjeevankashid/Developer/cerina/mcp",
        "run",
        "cerina-foundry"
      ],
    }
  }
}

Development

{
  "mcpServers": {
    "cerina-foundry": {
      "command": "uv",
      "args": [
        "--directory",
        "/Users/jagjeevankashid/Developer/cerina/mcp",
        "run",
        "cerina-foundry"
      ],
      "env": {
        "CERINA_BACKEND_URL": "http://localhost:8000/api/v1",
      }
    }
  }
}

Environment Variables

Variable Default Description
CERINA_BACKEND_URL http://localhost:8000/api/v1 Backend API URL
CERINA_AUTO_APPROVE false Auto-approve without human review
CERINA_POLL_INTERVAL 2.0 Seconds between status polls
CERINA_MAX_POLL_ATTEMPTS 300 Max polls before timeout (~10 min)

Usage Examples

Once configured in Claude Desktop:

Create an Exercise

"Ask Cerina Foundry to create a sleep hygiene protocol for patients with insomnia"

List Exercises

"Show me the approved CBT exercises for anxiety"

Check Status

"What's the status of session abc123?"

Approve Pending Exercise

"Approve the exercise in session xyz789"

Development

Run the server manually:

uv run cerina-foundry

Test with MCP inspector:

npx @modelcontextprotocol/inspector uv --directory . run cerina-foundry

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

cerina_mcp-0.1.0.tar.gz (32.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

cerina_mcp-0.1.0-py3-none-any.whl (13.0 kB view details)

Uploaded Python 3

File details

Details for the file cerina_mcp-0.1.0.tar.gz.

File metadata

  • Download URL: cerina_mcp-0.1.0.tar.gz
  • Upload date:
  • Size: 32.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.7

File hashes

Hashes for cerina_mcp-0.1.0.tar.gz
Algorithm Hash digest
SHA256 16234e00dc79102823174e0d730984d34bd5d992755a23cdae343d8daeb788eb
MD5 b2d0e13ce36e02c4f49f13808ffbbfc6
BLAKE2b-256 2bd6279aab581fef459cf512975cfea0c7ca1e562ac5b7553c8d4b1dec65df45

See more details on using hashes here.

File details

Details for the file cerina_mcp-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: cerina_mcp-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 13.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.7

File hashes

Hashes for cerina_mcp-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 f3c5b0597efafad2505dce0844f0cb66e342cef77d5eebc54a9c192acfcb4f87
MD5 aa6a2b6264f92634ca16d300e2722440
BLAKE2b-256 932178db4f45b12a6abf7e1d47721607d45f88ff582b3d76262a801265b7ee55

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page