Inspect, Evaluate & Manage
Your MCP Server Tools

MCP Lens connects to Model Context Protocol servers, fetches tool definitions, and runs a multi-layer evaluation to surface protocol violations, quality issues, security risks, and real-world usability problems.

Up and Running in 3 Commands

# Clone and set up
git clone https://github.com/devninja-in/mcp-lens.git && cd mcp-lens
make setup

# Start the app
make start

# Open http://localhost:5173

Requires Python 3.11+, Node.js 18+, and uv

Everything You Need

A comprehensive toolkit for evaluating MCP server tools across protocol compliance, quality, security, and LLM-assisted usability.

Server Management

Add, edit, delete, and test MCP server connections from the web UI. Supports multiple auth flows including OAuth 2.0 and DCR.

Tool Inspection

Fetch and browse tool definitions with full schema detail, parameter tables, and raw JSON schemas. Upload tools manually when servers are unreachable.

Multi-Layer Evaluation

35+ checks across protocol compliance, tool quality, security analysis, and LLM-assisted usability evaluation.

LLM-Assisted Checks

Test tools from an AI agent's perspective. Auto-generates scenarios and validates tool selection, argument generation, and disambiguation.

Security Analysis

Detects annotation mismatches, prompt injection surfaces, SQL injection risks, and data exfiltration patterns in tool definitions.

CLI & API

Run evaluations headlessly in CI pipelines or programmatically via 28 REST API endpoints. Export reports as JSON, YAML, or PDF.

Scoring & Gating

Weighted scoring by severity with configurable pass/fail thresholds. Critical failures in protocol or security force gate failure.

Regression Tracking

Compare evaluation reports over time to catch regressions. Track false positives with justifications across sessions.

SQLite Persistence

Server configs, encrypted auth tokens, and evaluation reports stored locally. Optional PostgreSQL support for production deployments.

Four Evaluation Layers

Static analysis plus LLM-assisted testing for comprehensive coverage.

12 checks

Protocol Compliance

Missing names, invalid schemas, malformed annotations, schema validation against the MCP specification.

11 checks

Tool Quality

Vague descriptions, missing parameter docs, naming inconsistencies, tool overlap detection.

6 checks

Security Analysis

Annotation mismatches, prompt injection surfaces, SQL injection risks, data exfiltration patterns.

5+ checks

LLM-Assisted

Description clarity, tool selection, argument generation, overlap disambiguation, safety resistance.

Learn more about evaluation →

Multi-LLM Support

Run evaluations with any supported LLM provider. Compare results across models.

Google Gemini (Vertex AI) Anthropic Claude OpenAI GPT Claude on Vertex AI

Configure LLM providers →