- Local Workspace @peter4leadson/local-workspace-mcpBounded, read-oriented filesystem, git and named-task tools over authorized workspace roots.Not assessed yet.Runs on your machine, installed from npm.
- Dunstan @barglabs/dunstanChecks a coding agent's handback against the pull request's GitHub record. No model decides.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- ChangeAtlas @robyroro/mcp-changeatlasLocal Git change impact and related test discovery with inspectable import pathsNot assessed yet.Runs on your machine, installed from PyPI.
- GitHub (read-only) @abdulmuhaiminkhan/github-mcpRead-only GitHub repos, issues, PRs and commits, with tool descriptions tuned on a benchmark.2% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- SnapDoczilla @julvc/snapdoczillaOffline docs-as-code for any backend and frontend: a MkDocs site in your repo, by your AI agent.Not assessed yet.Runs on your machine, installed from PyPI.
- Session Relay @dimitrihilverda/claude-session-relaySelf-hosted relay: agent sessions on different machines share a board, chat and check git conflictsNot assessed yet.Runs on your machine, installed from a package registry.
- Keyspoor @majiayu000/keyspoorOffline secret scanning for AI agents. Redacted findings; scans text and files in a chosen root.Not assessed yet.Runs on your machine, installed from npm.
- Hivemind @leonhest/hivemindA shared, live plan for teams of coding agents, synced through your git remote.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Pasr @apheironn/pasrLocal, token-budgeted code context with file:line provenance and selection receipts.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Git Why @alliecatowo/git-whyFinds the Git commits that explain why code is the way it is: semantic and full-text history search.2% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- IAF Agent Bridge @francescoveryra-dot/iaf-agent-bridgeMCP server that sends work to Cursor Agent over ACP and returns the session id needed to continue.Not assessed yet.Runs on your machine, installed from npm.
- ddflow @delian/ddflow-mcpWork-queue kernel for AI coding agents: dependencies, worktree isolation, quality gates, recovery3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Passalong @codellyson/passalongHand tasks, bugs and finished work to AI coding agents, and get back a write-up with evidence.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Versionly @versionly/mcpMonitor third-party API changes in GitHub repos, map breaks to files, open reviewable auto-fix PRs.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Graphify @graphify-labs/graphifySearch indexed code, trace dependencies, assess change impact, and recall repository memory.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- cubic @cubic/cubicTriage cubic AI code review findings, start PR reviews, and read wikis, scans, and team learnings.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Seshat @papyruslabs/seshat-mcpStructural code intelligence for AI agents: real call graphs, blast radius, and change history.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Lawang Onboard @gablooge/lawang-onboardPermission-aware onboarding MCP server: answers about a codebase, filtered by the caller's role.Not assessed yet.A remote server; it needs your API key.
- Guard @codapult/guardLocal-first architecture guardrails and project context for JS/TS AI coding agents.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- chargehand @egoushka/chargehandRuns coding-agent workers on a codebase question; every claim in the answer carries evidence.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from NuGet.
- GitLab @mmedum/gitlab-mcpGitLab over MCP from your own account: issues, merge requests, reviews, the repository and CI.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- whichlib @josifb/whichlibDependency picker for coding agents: recommends, compares and scores GitHub repos with a verdict.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Forgejo / Codeberg / Gitea @brechanbech/forgejo-mcp-rsModel Context Protocol server for Forgejo, Codeberg and Gitea, in Rust3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from cargo.
- Git history @tonyweckstrom1987/git-historyGive AI agents Git history tools: commit search, file history, blame, contributors, ref diffs.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
