- Fwozen @fwozen/fwozenFreeze and unfreeze merges across a GitHub organization, with an audit trail.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- MCP Server Discovery — new model-context-protocol repos ($0.01/query) @a2awire/data-model-context-protocol-mcp-server-discoveryNew MCP servers on GitHub: discovery index. $0.01/query. Register in-session — free testnet funds.26% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Trending Repository Tracker — new GitHub repo discovery ($0.01/query) @a2awire/data-trending-repository-new-github-repo-discoveryTrending GitHub repos: new & rising daily. $0.01/query. Register in-session — free testnet funds.22% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Deepcontext @wild-card/deepcontextAdvanced codebase indexing and semantic search MCP server7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- ACN Preflight @abacore-net/acn-preflightPreflight checks for agent repository contributions, bounty work, and Base payments.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- SandboxAPIs @sandboxapis/mcpDrop-in read-only replicas of GitHub, Jira, Slack and 18 more, preloaded with one fake company.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- harmony-mcp @abduljabbarbxr/harmony-mcpRepo rules enforcement for AI agents. Checks diffs against repo conventions.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- PreviewDrop @previewdrop/cliDeploy any Git branch to a live HTTPS preview URL from your agent. No Dockerfile required.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- X402 Git @x402git/git-x402Buy private git repos and agent skills with USDC over x402. Read the manifest free, then pay.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Veridu @michaelw-pr/veriduCode review that knows what depends on your change — before commit or on every PR.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Latchkey @that-developer-kaveh/latchkeyTriage failing GitHub Actions jobs and see what self-heal repaired, in natural language.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Triageshield @edgethirteen/triageshieldVerify a vuln report's file/line/function claims against a real GitHub repo.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Vercelpycheck @edgethirteen/vercelpycheckScan a public GitHub repo for known Vercel Python-runtime deploy footguns.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Triageshield @triageshield/triageshieldVerify a vuln report's file/line/function claims against a real GitHub repo.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Dsh Codebase Chat @shinzarou-eng/dsh-codebase-chatLocal-first codebase intelligence: cited answers, audits, reports. EN/FR.Not assessed yet.Runs on your machine, installed from npm.
- Brain Scanner @kevin-lozada-santos/brain-scannerCodebase graphs, caller impact analysis, and recorded project context for AI coding agents.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Perfloop @perfloop/perfloopAlways-on performance engineering for your own code: proven pull requests, the merge stays yours.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- graphy @omnislash157/graphyosCompile any codebase into a walkable graph and serve it over MCP. No model decides an edge.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Localhero.ai @localhero/localheroManage product translations from Claude and ship reviewed changes as GitHub pull requests.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Contextual @contextual-laboratories/contextualPersistent memory for AI coding agents: local-first semantic search, dependency graphs, git history.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- ReviewGate @reviewgate/reviewgateCode review against your team standards, before the pull request: generator finds, judge confirms6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- rezee @rezee/rezeeIssues, pull requests, docs, chat and CI runs across a rezee workspace.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- SHPBL: Repository Audit & Repair @shpbl/repository-audit-and-repairAudit and repair any public GitHub repo. Free survey; paid source, unified diffs and a pull request.16% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Release Branch Planner @wxt-ai/release-branch-plannerSelect a branch for a release8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
