- Causari @croviatrust/causariRecords the prompt, model and files an agent declared for a line. It does not prove who typed it.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from cargo.9 GitHub stars.
- repo2graph @srinivasan-78/repo2graphAsk a codebase a question, get back the source that answers it — every block cited to file:line.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.9 GitHub stars.
- Trent @trent/trentSecurity reviews, threat models over a repo or website, and remediation tracking, in your editor.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.9 GitHub stars.
- Ducklab @jrullan/ducklabMulti-LLM dev harness, MCP-operable: bugs, cycles, gates. Verdicts are exit codes, never opinions.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.9 GitHub stars.
- Growmos @codician/growmosLiving knowledge graph for your repo: query with citations, remember/link facts, fact-check claims.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.9 GitHub stars.
- Gitcontribute @morluto/gitcontributeLocal-first GitHub contribution research workbench4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.9 GitHub stars.
- redcon @natiixnt/redconDeterministic context packing for AI coding agents; measured 83% fewer input tokens, local.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.9 GitHub stars.
- Doc Bridge @agentskit-io/doc-bridgeResolve documentation ownership, edit roots, checks, and human handoffs before an agent edits code.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.9 GitHub stars.
- Bug Bounty Intelligence @holistis/bug-bounty-intelligence-mcpAI security scanner for Solidity + free CC0 dataset of Sherlock audit-competition acceptance rates.12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.9 GitHub stars.
- Gerrit Code Review @gaijin/go-gerrit-mcpCapability-gated Gerrit code review tools with opt-in review notifications pushed into the session3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.9 GitHub stars.
- Lain @spuentesp/lainHigh-performance knowledge graph MCP server for AI coding agents with semantic search.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.9 GitHub stars.
- Codeix @montanetech/codeixFast semantic code search for AI agents — find symbols, references, and callers across any codebase4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.9 GitHub stars.
- Lynx @lorenzo-cambiaghi/lynxLynxMCP: 100% local MCP server for the code questions grep can't answer: call graph, hybrid search4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.9 GitHub stars.
- GitLab @dubuqingfeng/gitlab-mcp-serverGitLab MCP (Model Context Protocol) server for AI agents6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.9 GitHub stars.
- Obsidian GitHub @smithery/hint-services-obsidian-github-mcpConnect AI assistants to your GitHub-hosted Obsidian vault to seamlessly access, search, and analy…8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.9 GitHub stars.
- komnet @komdosh/komnetLets AI coding agents coordinate asynchronously through a private git repository. No server.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.8 GitHub stars.
- Replen @replenhq/replenA local intelligence layer for AI coding agents. Maps your repos, matches the open-source frontier.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.8 GitHub stars.
- Codeledger @codeledgerecf/codeledgerDeterministic context selection for AI coding agents. Local memory that compounds across sessions.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.8 GitHub stars.
- Niro @apxlabs-ai/niroAI pentester for PRs — finds exploitable bugs and hands your developer agent the fix.16% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.8 GitHub stars.
- OpenGrok MCP Server @icyhot09/opengrok-mcp-serverMCP server bridging OpenGrok search engine with AI for instant context across massive codebases.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.8 GitHub stars.
- Archprint @tommkruix/archprintMine the architecture rules your TypeScript repo already enforces, with the evidence attached.2% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.7 GitHub stars.
- CodeCortex Context Engine @behnamjalalico/codecortex-context-engineContext intelligence for AI coding agents: navigation, impact, memory, guarded edits.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.7 GitHub stars.
- Draugr @draugr/draugrSecurity scanning for AI agents: SAST, SCA, secrets, IaC, DAST, ranked by real risk.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.7 GitHub stars.
- Skeletongraph @yashdoke7/skeletongraphZero-LLM structural code retrieval for AI coding agents, served over MCP.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.7 GitHub stars.
