MCP.so
Sign In

Lenspr

@kyrylopr

Repository

About Lenspr

Code intelligence MCP server that makes AI coding safer. Builds a dependency graph of your entire codebase so Claude, Cursor, or any MCP client knows what breaks before making changes. 60+ tools for impact analysis, health scoring, dead code detection, and architecture enforcemen

#code-analysis#developer-tools#code-graph#impact-analysis#python#typescript#mcp-server#vibecoding#code-quality#refactoring#claude-code#cursor

Basic information

Category

Developer Tools

Transports

stdio

Publisher

kyrylopr

Submitted by

Kyrylo Prymak

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "lenspr": {
      "command": "lenspr",
      "args": [
        "serve",
        "."
      ],
      "env": {}
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Lenspr?

Lenspr is an MCP server that parses your codebase into a dependency graph and gives AI coding assistants 60+ tools to understand the full picture before making changes. It provides impact analysis, health scoring, and context-aware intelligence for AI agents like Claude Code and Cursor. Designed for both individual vibecoders and professional teams, Lenspr runs entirely locally so your code never leaves your machine.

How to use Lenspr?

Install with pip install 'lenspr[all]', then run lenspr init . and lenspr setup . in your project root. Restart your IDE and your AI will have access to lens_* tools. No cloud dependency—everything runs on your machine.

Key features of Lenspr

  • Dependency graph parsing for complete code context
  • Health scoring (A to F) for codebase fitness
  • Impact analysis before any AI edit
  • Dead code detection across your project
  • NFR checks for security and error handling
  • Architecture rule enforcement per edit

Use cases of Lenspr

  • AI-powered refactoring with full caller-callee awareness
  • Preventing blind edits that break distant dependencies
  • Enforcing architecture boundaries (e.g., frontend must not import backend)
  • Detecting dead functions and untested code during development

FAQ from Lenspr

How is Lenspr different from a linter?

A linter says "function is too long." Lenspr says "function is too long AND 15 other functions depend on it AND it has 0 tests AND handles authentication—if it breaks, login, registration, and every admin page stop working."

What languages does Lenspr support?

Python, TypeScript, and JavaScript.

Does my code leave my machine?

No. Everything runs locally and your code never leaves your machine.

What AI tools does Lenspr work with?

Claude Code, Cursor, and any MCP-compatible client.

Comments

More Developer Tools MCP servers

MCP Framework

QuantGeekDev

The Typescript MCP Framework

924

mcp-excalidraw

yctimlin

MCP server and Claude Code skill for Excalidraw — programmatic canvas toolkit to create, edit, and export diagrams via AI agents with real-time canvas sync.

2.1K

MCP-Bridge

SecretiveShell

A middleware to provide an openAI compatible endpoint that can call MCP tools

928

test

prysmaticlabs

Go implementation of Ethereum proof of stake

3.8K

TalkToFigma

sonnylazuardi

TalkToFigma: MCP integration between AI Agent (Cursor, Claude Code, Codex) and Figma, allowing Agentic AI to communicate with Figma for reading designs and modifying them programmatically.

6.9K