- ivygrep @bvolpato/ivygrepLocal code search and task context packs for coding agents3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.7 GitHub stars.
- ContextAtlas @traviswye/contextatlasPre-computed atlas of your codebase for Claude Code: LSP + ADRs + git. 45-72% token reduction.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.7 GitHub stars.
- Advanced GitLab MCP server @structured-world/gitlab-mcp58 CQRS tools exposing 231 GitLab operations across 26 entity types5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.7 GitHub stars.
- Engram @spectra-g/engramMCP adapter for Engram - organizational memory for AI agents5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.7 GitHub stars.
- Live Memory @shofer-dev/live-memoryPersistent, read-only codebase memory for Claude Code; ask it instead of re-reading files.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.7 GitHub stars.
- GitHub PR Context @paarths-collab/github-pr-context-mcpRetrieves GitHub PR history as context material; the connected IDE agent does the reasoning.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.7 GitHub stars.
- Mneme @patsa2561-art/mneme-aiMemory layer for AI coding assistants. Indexes git history + code, exposes via MCP.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.7 GitHub stars.
- Octopus Blackboard @octoryn/octopus-blackboardShared memory & coordination for AI coding agents — a blackboard, not an orchestrator.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.7 GitHub stars.
- archy @hslee16/archyArchitectural sensor for Python codebases.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.7 GitHub stars.
- Decantr Ai MCP @decantr-ai/mcp-serverStable eight-tool MCP server for changed-UI assurance, authority-aware UI task context, and repair.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.7 GitHub stars.
- HefestoAI @artvepa80/hefestoaiPre-commit code quality guardian. Detects semantic drift in AI-generated code.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.7 GitHub stars.
- LayerMap @coffeecoproject/layermapCall graph for coding agents: callers up to HTTP routes, callees, usages for TS/JS, Go, Python, Java3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.6 GitHub stars.
- Jev agent tools @nomenak/jev-agent-toolsEvidence-oriented code questions, diff review and test selection via a Jev endpoint.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.6 GitHub stars.
- Code Factory @zrk222/code-factoryLocal audit evidence for agents: source, workflows, runtime, repair and native scanner status.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.6 GitHub stars.
- Axis @useaxis/axisCoding agents from Claude Code, Cursor and Codex claim jobs and lock files on one shared board.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.6 GitHub stars.
- culprit @noordeen123/culpritDeterministic, offline root-cause analysis and pre-commit fix verification for coding agents.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.6 GitHub stars.
- diffctx @nikolay-e/diffctxSelects the minimum code an LLM needs to review a git diff3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.6 GitHub stars.
- Reuse Before Generate @aradar46/reuse-before-generateChecks whether your idea already exists before your agent builds it. Searches GitHub, npm, Python.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.6 GitHub stars.
- CodeCartographer @huginnindustries/codecartographerTurn an unfamiliar codebase into validated architecture, contracts, and a reimplementation spec.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.6 GitHub stars.
- Quilt @wkoverfield/quiltTrack which AI agent wrote which lines in a shared Git checkout; each commits only its own lines.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.6 GitHub stars.
- GitLab @vish288/mcp-gitlabGitLab MCP server for MCP 2026-07-28: projects, MRs, files, reviews, pipelines, CI/CD, issues5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.6 GitHub stars.
- GitDealFlow — GitHub signals for startup investors @kindrat86/vc-deal-flow-signalGitHub engineering acceleration signals for venture deal flow across 15 sectors.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.6 GitHub stars.
- Guardvibe @goklab/guardvibeDeterministic security layer your AI can't be. 574 rules, 39 tools, CLI + doctor + host audit.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.6 GitHub stars.
- Codecov @egulatee/codecovMCP server for querying Codecov coverage data with configurable URL support4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.6 GitHub stars.
