MCPgee
MCPgee
MCPgeeMCPgee

Codeprism

v1.0.0•Developer Tools•stable

An experimental, 100% AI-generated, high-performance code intelligence server providing AI assistants with a graph-based understanding of codebases.

aiai-generated-codeai-toolscode-analysiscode-analyzer
Share:
27
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is Codeprism?

Codeprism is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to experimental, 100% ai-generated, high-performance code intelligence server providing ai assistants with a graph-based understanding of codebases.

An experimental, 100% AI-generated, high-performance code intelligence server providing AI assistants with a graph-based understanding of codebases.

This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • An experimental, 100% AI-generated, high-performance code in

Use Cases

Code intelligence graphs
Codebase understanding
AI exploration
rustic-ai

Maintainer

LicenseNOASSERTION
Languagerust
Versionv1.0.0
UpdatedMay 13, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx codeprism

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Codeprism

CodePrism is a high-performance Rust-based MCP server that builds a graph-based understanding of software codebases and exposes it to AI assistants through 20+ specialized tools. It can trace symbol definitions and references, analyze call graphs, detect code patterns, find security and performance issues, measure complexity, and suggest optimal analysis workflows for any repository. Developers use it to give Claude deep structural knowledge of large codebases so they can refactor confidently, onboard quickly, or perform thorough code reviews.

Prerequisites

  • Rust toolchain installed (cargo) for building from source, or a pre-built binary from GitHub Releases
  • The target code repository checked out locally and accessible as a file path
  • An MCP client such as Claude Desktop or Claude Code
  • Optional: Docker if using the container image
1

Install CodePrism

Install via Cargo (builds from source), download a pre-built binary from GitHub Releases, or use Docker. The Cargo method is recommended if you have Rust installed.

# Via Cargo (recommended)
cargo install codeprism-mcp-server

# Pre-built binary (macOS)
wget https://github.com/rustic-ai/codeprism/releases/latest/download/codeprism-macos-x86_64
chmod +x codeprism-macos-x86_64
mv codeprism-macos-x86_64 /usr/local/bin/codeprism

# Pre-built binary (Linux)
wget https://github.com/rustic-ai/codeprism/releases/latest/download/codeprism-linux-x86_64
chmod +x codeprism-linux-x86_64
mv codeprism-linux-x86_64 /usr/local/bin/codeprism
2

Verify the installation

Confirm the binary is working and check available options.

codeprism --help
3

Configure your MCP client

Add CodePrism to your Claude Desktop or Claude Code MCP configuration. Set REPOSITORY_PATH to the root of the codebase you want to analyze.

{
  "mcpServers": {
    "codeprism": {
      "command": "/usr/local/bin/codeprism",
      "args": ["--mcp"],
      "env": {
        "REPOSITORY_PATH": "/path/to/your/repo",
        "CODEPRISM_PROFILE": "development",
        "RUST_LOG": "info"
      }
    }
  }
}
4

Start with a repository overview

Once connected, use the repository_stats tool to get a high-level understanding of the codebase: language breakdown, file count, and symbol counts. This is the recommended starting point.

# Invoke via Claude:
# "Give me an overview of this repository using the repository_stats tool"
5

Explore symbols and trace relationships

Use the explain_symbol, trace_path, and find_dependencies tools to understand how specific classes, functions, or modules relate to each other across the codebase.

# Example tool calls Claude will make:
# explain_symbol: { "symbol": "UserManager" }
# search_symbols: { "pattern": "^Agent.*", "symbol_type": "class" }
# trace_inheritance: { "class_name": "Agent", "include_metaclasses": true }
6

Run batch analysis for comprehensive review

Use the batch_analysis tool to run multiple analysis tools in a single request, which is efficient for code review or security audits.

# Claude will call:
# batch_analysis: {
#   "tools": ["repository_stats", "analyze_complexity", "analyze_security", "find_unused_code"]
# }

Codeprism Examples

Client configuration

Claude Desktop configuration running CodePrism against a local repository with development profile logging.

{
  "mcpServers": {
    "codeprism": {
      "command": "/usr/local/bin/codeprism",
      "args": ["--mcp"],
      "env": {
        "REPOSITORY_PATH": "/Users/me/projects/my-repo",
        "CODEPRISM_PROFILE": "development",
        "RUST_LOG": "info"
      }
    }
  }
}

Prompts to try

These prompts leverage CodePrism's graph analysis, symbol tracing, and security scanning capabilities.

- "Give me a full overview of this repository including language breakdown and file count"
- "Explain what the UserManager class does and show me all its dependencies"
- "Find all classes that extend the Agent base class"
- "Analyze the security vulnerabilities in this codebase"
- "Find unused code and dead functions across the repository"
- "Measure cyclomatic complexity for the most complex modules"

Troubleshooting Codeprism

cargo install fails with compilation errors

Ensure your Rust toolchain is up to date with `rustup update stable`. CodePrism requires a recent stable Rust version. If compilation still fails, try downloading a pre-built binary from the GitHub Releases page instead.

CodePrism starts but returns empty results for symbol queries

Verify that REPOSITORY_PATH points to the actual root of the repository and that the path is readable by the process running the MCP server. On macOS, you may need to grant the terminal app Full Disk Access in System Settings > Privacy & Security.

Server is slow to respond on large repositories

CodePrism builds an in-memory graph on startup. For very large repositories (100k+ files) the initial indexing phase takes time. Wait for the server to finish indexing before issuing queries, or use the `suggest_analysis_workflow` tool to let CodePrism plan an efficient analysis sequence.

Frequently Asked Questions about Codeprism

What is Codeprism?

Codeprism is a Model Context Protocol (MCP) server that experimental, 100% ai-generated, high-performance code intelligence server providing ai assistants with a graph-based understanding of codebases. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Codeprism?

Follow the installation instructions on the Codeprism GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Codeprism?

Codeprism works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Codeprism free to use?

Yes, Codeprism is open source and available under the NOASSERTION license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

Codeprism Alternatives — Similar Developer Tools Servers

Looking for alternatives to Codeprism? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.

Ecc

★ 188.2k

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Javaguide

★ 155.8k

Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发

Gemini CLI

★ 104.5k

A secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in

Awesome MCP Servers

★ 87.3k

⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.

MCP Servers

★ 86.0k

Model Context Protocol Servers

CC Switch

★ 77.5k

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io

Browse More Developer Tools MCP Servers

Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Developer ToolsBrowse All Servers

Quick Config Preview

{ "mcpServers": { "codeprism": { "command": "npx", "args": ["-y", "codeprism"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Codeprism?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides