TuringMind MCP Server
OfficialThe TuringMind MCP Server enables Claude to integrate with the TuringMind cloud platform for AI-powered code review workflows, authentication, and repository memory management.
Initiate Login: Start a device code authentication flow, returning a verification URL and user code to sign in via browser without needing an API key upfront.
Complete Login: Poll for authentication completion and automatically save the API key to
~/.turingmind/configupon success.Validate Authentication: Check the current API key's validity and retrieve account details such as tier (free, pro, team, enterprise), remaining quota, and user ID.
Upload Code Reviews: Submit detailed findings including issues (title, severity, category, file, line, CWE, confidence), summary counts, full markdown content, and repository/commit metadata.
Fetch Repository Context: Retrieve memory for a specific repository — recent open issues, hotspot files, known false positive patterns, and team conventions — to avoid duplicate reports before starting a review.
Submit Feedback: Mark issues as
fixed,dismissed, orfalse_positive, optionally providing patterns and reasons to improve future reviews.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@TuringMind MCP Serverupload my code review for the auth system in turingmind/backend"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
TuringMind MCP Server
Model Context Protocol (MCP) server for TuringMind cloud integration. Provides type-safe tools for Claude to authenticate, upload code reviews, fetch repository context, and submit feedback.
Requires Python 3.10+ (MCP SDK requirement)
Why MCP?
Instead of Claude generating raw JSON and curl commands (which can fail silently due to field name mismatches or malformed data), MCP provides:
Type-safe tool definitions — Claude sees the exact schema
Validated input — Errors caught before sending
No endpoint guessing — Correct URLs hardcoded
Better error messages — Clear feedback on failures
Simplified login — Device code flow handled by the server
Related MCP server: PR Reviewer MCP Server
Installation
From PyPI
pip install turingmind-mcpWith pipx (recommended for CLI tools)
pipx install turingmind-mcpFrom Source
git clone https://github.com/turingmindai/turingmind-mcp.git
cd turingmind-mcp
pip install -e .Verify Installation
turingmind-mcp --helpQuick Start
Unified Setup (Recommended)
# Install
pip install turingmind-mcp
# Setup for your platform
turingmind setup claude_desktop # Claude Desktop
turingmind setup cursor # Cursor IDE/CLI
turingmind setup claude_cli # Claude Code CLI
# Diagnose installation
turingmind diagnosePlatform-Specific Setup
TuringMind-MCP supports multiple platforms. Choose your platform:
Claude Desktop - Native MCP integration
Claude Code CLI - Command-line with MCP or Skills
Claude SDK - Programmatic Python access
Cursor IDE - Native MCP integration
Cursor CLI - Command-line integration
Manual Setup (Claude Desktop Example)
Configure Claude Desktop
Add to your Claude Desktop config file:
Platform | Path |
macOS |
|
Windows |
|
Linux |
|
{
"mcpServers": {
"turingmind": {
"command": "turingmind-mcp"
}
}
}Restart Claude Desktop
Login to TuringMind
In Claude, say: "Log me into TuringMind"
Claude will guide you through the device code flow.
Available Tools
Authentication
Tool | Description |
| Start device code auth flow (no API key needed) |
| Complete login and save API key |
| Check API key and account status |
Code Review
Tool | Description |
| Upload review results to cloud |
| Get memory context for a repository |
| Mark issues as fixed, dismissed, or false positive |
Tool Reference
turingmind_initiate_login
Start device code authentication flow. No API key required.
Parameters: None
Returns:
verification_url— URL to open in browseruser_code— Code to enter when prompteddevice_code— Use withturingmind_poll_login
turingmind_poll_login
Poll for authentication completion.
Parameters:
Name | Type | Required | Description |
| string | ✅ | Device code from |
Returns:
On success: API key (automatically saved to
~/.turingmind/config)On pending: Status message to wait and retry
On expired: Error message to restart flow
turingmind_validate_auth
Validate API key and get account info.
Parameters: None
Returns:
Tier (free, pro, team, enterprise)
Quota remaining
User ID
turingmind_upload_review
Upload code review results to TuringMind cloud.
Parameters:
Name | Type | Required | Description |
| string | ✅ | Repository (owner/repo) |
| string | Git branch name | |
| string | Git commit SHA | |
|
| Review type (default: quick) | |
| array | List of issues found | |
| string | Full review as markdown | |
| object | {critical, high, medium, low} counts | |
| array | Files that were reviewed |
Issue Schema:
{
"title": "SQL Injection vulnerability",
"severity": "critical",
"category": "security",
"file": "src/db.py",
"line": 42,
"description": "User input passed directly to query",
"cwe": "CWE-89",
"confidence": 95
}turingmind_get_context
Get memory context for a repository.
Parameters:
Name | Type | Required | Description |
| string | ✅ | Repository (owner/repo) |
Returns:
Recent open issues
Hotspot files (frequent issues)
Team conventions
Known false positive patterns
turingmind_submit_feedback
Submit feedback on a code review issue.
Parameters:
Name | Type | Required | Description |
| string | ✅ | Issue ID (e.g., |
| string | ✅ | One of: |
| string | ✅ | Repository (owner/repo) |
| string | File path where issue was found | |
| integer | Line number of the issue | |
| string | For false_positive: pattern to skip in future | |
| string | Explanation for the feedback |
Actions:
fixed— Issue was resolved (tracks time-to-fix metrics)dismissed— Issue isn't important (lowers future priority)false_positive— Not a real issue (adds pattern to memory)
Usage Examples
Login Flow
User: Log me into TuringMind
Claude: I'll start the authentication flow.
[Calls turingmind_initiate_login]
🧠 TuringMind Login Started
Step 1: Open this URL in your browser:
https://app.turingmind.ai/cli-auth?device_code=...
Step 2: Sign in with Google or GitHub
User: Done!
Claude: [Calls turingmind_poll_login with device_code]
✅ Login Successful!
API key has been saved to ~/.turingmind/configReview with Upload
User: Review my code changes and upload to TuringMind
Claude: [Calls turingmind_validate_auth]
✅ TuringMind Authentication Valid
- Tier: team
- Quota: 495/500 reviews remaining
[Reviews code...]
[Calls turingmind_upload_review]
🧠 Review Uploaded to TuringMind
- Review ID: rev_abc123
- Issues: 3False Positive Feedback
User: That SQL injection issue was a false positive, we use parameterized queries
Claude: [Calls turingmind_submit_feedback]
🚫 Feedback Submitted
Issue iss_abc123 has been marked as false positive.
Pattern saved: `db.query(sql, params)`
This pattern will be skipped in future reviews.Configuration
Environment Variables
Variable | Description | Default |
| API server URL |
|
| API key | Read from |
| Enable debug logging |
|
Config File
API credentials are stored in ~/.turingmind/config:
export TURINGMIND_API_KEY=tmk_your_key_here
export TURINGMIND_API_URL=https://api.turingmind.aiClaude Desktop with Custom API URL
{
"mcpServers": {
"turingmind": {
"command": "turingmind-mcp",
"env": {
"TURINGMIND_API_URL": "https://api.turingmind.ai"
}
}
}
}Development
Setup
git clone https://github.com/turingmindai/turingmind-mcp.git
cd turingmind-mcp
pip install -e ".[dev]"Run Locally
python -m turingmind_mcp.serverTest with MCP Inspector
npx @modelcontextprotocol/inspector turingmind-mcpRun Tests
pytestLint & Format
ruff check .
black .
mypy src/Troubleshooting
"TURINGMIND_API_KEY not configured"
Run the login flow in Claude, or set the environment variable:
export TURINGMIND_API_KEY=tmk_your_key_here"Permission Denied"
API key lacks required permission. Re-run login to create a new key with proper permissions.
"Connection Error"
Check that
TURINGMIND_API_URLis correctVerify network connectivity
For local development, ensure backend is running
Claude doesn't see the tools
Verify
turingmind-mcpis in your PATH:which turingmind-mcpCheck Claude Desktop config is valid JSON
Restart Claude Desktop completely (Cmd+Q / close from tray)
License
MIT — see LICENSE for details.
Documentation
Getting Started
Quick Start Guide - Get started in 5 minutes
Platform Guides - Platform-specific setup
User Documentation
Features - Complete feature list and user flows
Compatibility Matrix - Platform compatibility
Developer Documentation
Development Guide - Architecture and implementation
Testing Guide - Testing documentation
See Documentation Index for complete documentation structure.
Links
TuringMind — AI-powered code review
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseAqualityDmaintenanceWraps Claude Code as tools for MCP clients, enabling autonomous coding tasks via a 4-tool lifecycle with session management, async polling, and permission controls.411818MIT
- FlicenseAqualityBmaintenanceConnects Claude to GitHub, enabling listing repositories, browsing open pull requests, and inspecting PR diffs for code review.4
- Flicense-qualityCmaintenanceEnables to interact with GitHub repositories directly from Claude, supporting actions like viewing repos, checking status, committing and pushing changes, and managing pull requests.
- FlicenseAqualityDmaintenanceEnables Claude to access and manage GitHub repositories dynamically at runtime, including private repos, with tools for browsing files, searching code, and viewing commits, pull requests, and issues.111
Related MCP Connectors
Provides cloud browser automation capabilities using Stagehand and Browserbase, enabling LLMs to i…
Runtime permission, approval, and audit layer for AI agent tool execution.
Operate Linux, macOS and Windows from your LLM. Every action runs through an auditable allowlist.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/turingmindai/turingmind-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server