- Kin @kinlab/kinA graph-native code repository for people and AI agents.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.68 GitHub stars.
- CodeScene @codescene/codescene-mcp-serverAn MCP server that provides CodeScene Code Health analysis tools.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.68 GitHub stars.
- Gread @nitrorcr/greadAn MCP server that gives your AI access to the source code and docs of all public github repos5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.65 GitHub stars.
- Depwire @atef-ataya/depwireDependency graph + 24 MCP tools. Impact analysis, simulation, security, agent coordination3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.64 GitHub stars.
- Codebase @mikerecognex/mcp-codebase-indexStructural codebase indexer with 17 query tools. 87% token reduction. Zero dependencies.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.63 GitHub stars.
- LeanToken @morluto/leantokenToken-bounded repository context for coding agents over MCP.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from cargo.61 GitHub stars.
- DevLens @devlensio/devlensQuery a precomputed code graph (nodes, edges, summaries) of TS/JS/React/Next.js/Node repos via MCP.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.60 GitHub stars.
- Repo Graph @james-chahwan/repo-graphStructural graph map of any codebase so LLMs navigate by structure, not guesswork.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.58 GitHub stars.
- Agentmako @drhalto/agentmakoLocal-first codebase intelligence MCP server for AI coding agents.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.54 GitHub stars.
- siGit @sigit/sigitMCP server for siGit (sigit.si): browse repos, search code, manage PRs/issues, web search.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.51 GitHub stars.
- argot @get-tmonier/argotRead-only context and complete checks against patterns learned from git history. Local; no LLM.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.51 GitHub stars.
- Agentmap @raymondchins/agentmapThe TS/JS-accurate repo map for coding agents: ts-morph import/symbol/call graph + MCP query tools4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.49 GitHub stars.
- Code Memory @kapillamba4/code-memoryLocal semantic code search with Git history. Works offline, no API key needed.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.49 GitHub stars.
- ProofFlow @hyperion-gpu/proofflowAudit infrastructure for AI coding agents with evidence-backed review and policy gates.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.49 GitHub stars.
- Understand Quickly @looptech-ai/understand-quicklyPublic registry of code-knowledge graphs for AI agents with schema validation and drift detection.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.48 GitHub stars.
- Memoire @sarveshsea/memoireShadcn-native Design CI for Tailwind apps with registry export and MCP UI tools.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.47 GitHub stars.
- memi @memi-design/memiMemi is the design layer for agentic AI.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.47 GitHub stars.
- CodeInspectus @synvoya/codeinspectusLocal-first MCP security scanner and CLI for AI-generated applications.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.47 GitHub stars.
- Herald @btouchard/heraldStop copy-pasting between Claude Chat and Claude Code.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.46 GitHub stars.
- ContextStream MCP Server @contextstream/mcp-serverProject memory, semantic code search, and grounded agent context.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.44 GitHub stars.
- ContextStream MCP Server @contextstreamio/mcp-serverContextStream MCP server for code context, memory, search, and AI tools.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.44 GitHub stars.
- GitLab MCP Server @jmrplens/gitlab-mcp-serverGo MCP server for GitLab: 2 dynamic tools reach ~872 actions on Free/CE, up to ~1098 on Ultimate.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.44 GitHub stars.
- Git Courer @alejandro-m-p/git-courerFull git MCP server for LLM agents — 17 tools, AST annotator, auto-backups, real plumbing.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.43 GitHub stars.
- ontomics @etiennechollet/ontomicsIndex your codebase's domain knowledge. 20x fewer tokens, 10x faster.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.43 GitHub stars.
