Version Control

Model Context Protocol server exposing GitLab to AI agents, built on @simplysf/simply-gitlab-core

Configurable tool bundle for AI coding agents — use via MCP server, CLI, or agent skills. npm wrapper for the Rust binary.

Pi (π) coding-agent extension: project-aware system prompt for any repo (stack, commands, conventions, AGENTS.md/CLAUDE.md rules) plus a gate that runs the project's own typecheck/lint/tests after every agent turn, with self-repair and diff review.

Model Context Protocol server for GitLab API integration

Model Context Protocol server for FerrTrack: issues, labels, comments

Diff MCP server public interfaces - CLI tool and GitHub Action

Install AI-agent Skills & MCP servers with a verified, independent SaferSkills trust score — across Claude Code, Cursor, Windsurf, Copilot, Codex, Gemini, Cline & OpenClaw.

AI-native version control where intent, operation, evidence and decision are first-class objects.

Resolve a company domain to its GitHub organization with repo, language and activity signals.

Read-only codebase audits for coding agents: secrets, RLS, deps, review verdicts. No writes.

Standalone stdio MCP server for Diversion (dv). Exposes Diversion source-control operations to Claude Code, Codex, Claude Desktop, Cursor, and any other MCP-aware AI client.

Local-first CLI for auditing AI agent skills, rules, instructions, and MCP configuration for duplicates, conflicts, security risks, and context cost.

Architecture docs from a repo: overview, modules, API surface, routes, dependency graph, diffs.

A Model Context Protocol (MCP) server that provides a clean interface for Perforce (P4) operations in Claude Desktop. This server wraps P4 commands to make them more reliable and easier for Claude to use, eliminating issues with interactive prompts and co

OpsContext for AI Agents — read-only fleet visibility (PM2/nginx/Docker/git/cron) + tamper-evident audit log + policy-as-code hooks. The ops + compliance layer Claude Code can't grow natively.

MCP server for code archaeology: git blame, file history, contributors, and co-change analysis

Open-source security scanner for Model Context Protocol (MCP) servers. Audits Claude Desktop, VS Code, Cursor, Windsurf, and 12 more AI tools for secrets, prompt injection, supply-chain risks, and 17 security checks.

Give AI agents Git history tools: commit search, file history, blame, contributors, ref diffs.

Modern TypeScript MCP server for AI-powered code search and querying with Greptile API

See what your AI editor sends to your MCP server: a pass-through proxy that records every JSON-RPC message for the Moka inspector. Works with GitHub Copilot, Cursor, Claude Desktop and any client that starts MCP servers.