- Penholder @penholder/penholderPreventive human-approval write-gate for AI agents: writes commit only after a human approves.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Shipstar @shipstar/mcpGenerate changelogs, release emails, help-center articles, banners, and social posts from commits.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- reapx GitHub repos - repository metadata and activity @reapx/github-reposScrape GitHub repository metadata, stars, forks, topics, licences and activity. Pay per row.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- RepoPilot @repopilot/repopilotRepository evidence for agents before they adopt dependencies, enter codebases, compare, or merge.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- LeakRank Guard @prototeemo/leakrank-guardScans code changes for leaked secrets and insecure config, with actionable fixes for AI agents.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Idencify @jospnunes/idencifyWhole-repo code graph for AI agents: impact analysis, dead code, cycles, semantic search — 14 tools.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Gluecron @gluecron/gluecronAI-native git hosting — repos, PRs, issues, CI gates, and AI code review over MCP (60 tools).6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- RepoFold @repofold/repofoldA cited wiki of your GitHub repo: search, read pages, find symbols and ask, with line citations.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Dev Changes @openhelm/dev-changesTurn described changes into reviewed pull requests: propose, triage, review, dependency audits.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Code Synapse — Fit Repo Finder @leewaystudio/code-synapseFinds real, maintained open-source repos that fit your project. MCP grounding for coding agents.3% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Tangled MCP @zzstoatzz/tangled-mcpMCP server for Tangled git platform. Manage repositories, branches, and issues on tangled.org.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Code Context Gate @wisdomrock/code-context-gateContext-aware code retrieval MCP server — ranked, gated results for AI coding agents5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Changelog Hq @therealmrfunguy/changelog-hqAuto-generate changelogs from GitHub PRs with AI-powered categorization and rewriting.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- GitHubInsights @therealmrfunguy/github-insightsGitHub repo analytics, trending repos, contributor stats, and language breakdowns.12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Srclight @srclight/srclightDeep code indexing for AI agents. FTS5 + embeddings + call graphs + git intelligence. Fully local.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Perceptdot GitHub @perceptdot/githubAI agent vision for GitHub repository monitoring — with ROI measurement.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Universalbench @nikhilgogulwar/universalbenchRun code, query databases, call any LLM, and commit to GitHub from your AI, safely. Free tier.23% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- QuantumScan PQC Scanner @gaiabio12-design/quantumscan-pqc-scannerPQC scanner for GitHub repos and smart contracts. Detects quantum-vulnerable ECDSA/RSA.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Claudetest @fasteningcode/claudetestPlaywright & Appium test automation for Claude. Generate tests, diagnose failures, open fix PRs.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Perseus: MCP server and live context engine @perseus-computing-llc/perseusLive context MCP server: resolves git, services, and tests into agent context. Local-first, MIT.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Bitbucket MCP @matanyemini/bitbucket-mcpModel Context Protocol (MCP) server for Bitbucket Cloud and Server API integration5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Repo-to-RAG @evozim/repo-to-ragGitHub repository vectorizer and context synthesizer for RAG pipelines.20% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Shebe @rhobimd/shebeFast BM25 full-text search for code repositories. 14 MCP tools, 2ms search latency.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- Nodejsmcp @steeped/nodejsmcpA Forgejo MCP Server7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
