- Knowledge @fulminate-io/knowledge-mcpPersistent memory graph for coding agents: hypotheses, evidence, and decisions survive sessions.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.1 GitHub stars.
- Aidimag @aidimag/aidimagPersistent, verified memory for AI coding agents: recall, capture, guardrails, review queue.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Codex Delegate @andreilungeanu/codex-delegate-mcpBridge AI coding hosts to the OpenAI Codex CLI for delegated implementation.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- ThinkReview @thinkode/thinkreviewLive PR/MR code reviews via review_url_code. OAuth or portal Bearer auth.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.1 GitHub stars.
- Meeba Brain @meemoprasad/meeba-brainRepository knowledge graph MCP server for codebase understanding and debugging.3% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- MCP VS Code @mario-andreschak/mcp-vscodeA self-hosted VS Code workbench embedded as an interactive MCP App.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- koment @koment-dev/komentRead and write checked code rationale stored outside source comments.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.1 GitHub stars.
- Ctx @vanshulgoyal101/ctxTurn a GitHub repo or docs site into agent-ready context: pack it or search it, over MCP.3% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- devmcp @rudranaresh0201/devmcpGit/CI MCP server with the full protocol surface (tools, resources, prompts, roots, sampling).5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- lockvet @matteo-sung/lockvetExplain any lockfile or workflow-pin change: bumps, vulns, ages, deprecations — 61 formats3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.1 GitHub stars.
- koment @janpuc/komentRead and write checked code rationale stored outside source comments.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.1 GitHub stars.
- mendapi @mendapi/mendapiDetect API breaking changes, scan your codebase for impact, and draft the fix. Runs locally.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- CodeFundi @felixwaweru/code-fundi-mcpCodeFundi MCP server for codebase mapping and blast-radius analysis.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Br8n @anthonysuherli/br8nCapture dev context on interrupt; replay it as a 30-second resume card. Git stash for your head.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Invigil @invigil/invigilLinters check your code. Invigil checks whether your repo is legible — to newcomers and AI agents.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Rhizome MCP @odrin/rhizome-mcpLocal-first MCP server for task tracking and coordination of autonomous AI coding agents.2% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Project Context @sandovalrr/project-contextSafely manage repository-scoped issues across Linear, GitHub Issues, and Jira Cloud.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Interviewer @girik-chadha/interviewer-mcpFull technical interview prep: company briefing, concepts, code deep-dive, mock interviews.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Evidrift @bm1016bm-svg/evidriftCatch TypeScript API and OpenAPI contract drift in AI-generated code, then revalidate it in CI.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- robo-cortex @robotel-limited/robo-cortexGit-aware memory store for AI coding agents; memories are anchored to git blob hashes.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- gittr-mcp @arbadacarbayk/gittr-mcpGit on Nostr via gittr.space: repos, push, issues, PRs, stars, bounties. Nostr identity (NIP-34).5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.1 GitHub stars.
- T Rush @devds1989/t-rush-mcpMCP server for t-rush. Exposes TODO/FIXME scanning and streak tracking to AI agents.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- agentsync (remote) @jarmstrong158/agentsync-remoteCloudflare Worker remote transport for agentsync. MCP 2026-07-28, dual-era, stateless.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.1 GitHub stars.
- Agentic SDLC MCP @sakuracianna/agentic-sdlc-mcpAgentic SDLC governance and security controls for AI coding agents working with GitHub.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
