Local-first, auto-injecting, self-aware-about-staleness context + memory layer for coding agents (Claude Code, Codex, MCP). Trust contract
6,118 MCP servers
Eyes and hands for AI agents on Android and iOS devices.
Code intelligence MCP server: impact analysis, dependency graphs, dead code detection.
MCP server for LinkTest — automate Google Play closed testing via AI
Local, deterministic review of Git changes: weakened tests and CI gates, risky flows, blast radius.
MCP server for Supermodel API - code graph generation for AI agents
AI code impact analysis MCP server — dependency graphs, cascade detection, and a mandatory build gate for AI coding agents
Repo intelligence: triage, fix PRs, SARIF reachability, recall. Free codna login to execute.
Spine — repository architecture with file-level proof: graph, paths, traces, and impact.
Keyless MCP server for Open VSX: VS Code extensions, versions, descriptions, download stats.
Committed, machine-readable codebase context and code map that tells agents where to look.
Find, install and enable MCP servers mid-session on any host, with consent and tool pinning
Aggregate local contract snapshot changes without exposing schema contents. Tools include...
Structured git operations (status, log, diff, branch, show) as typed JSON.
Summarize local dependency manifest and lockfile drift without returning package names,...
Inline review comments for markdown specs. Built-in MCP server hands feedback directly to your AI agent.
Search Stack Exchange questions, fetch Q&A threads as markdown, look up tag FAQs and user profiles.
Arduino MCP server for CLI setup, board detection, compile/upload, serial monitoring, and pin refs.
Codebase memory for AI agents: an AST index plus agent-written notes that self-stale.
Repository intelligence, code graph, history, papertrail, and cross-agent memory for coding agents.
Run code an AI wrote without handing it everything you can reach.