- TokenSaver @byggarepop/tokensaverStructural warm start for AI coding agents in .NET: cheap Roslyn signature maps of C#/.NET files.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from NuGet.4 GitHub stars.
- Smart Context @arrayo/smart-context-mcpReduces AI agent token usage by 90% via context compression and task checkpoint persistence.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.4 GitHub stars.
- CogZ @balaianu/cogzLocal-first engineering cognition for AI coding agents — persistent memory over your codebase.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.3 GitHub stars.
- Astria @nodesify/astriaTurn any codebase into a queryable knowledge graph — offline-first, zero API keys.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- repomap @sylphxai/repomapA map of your codebase for AI agents: code graph, search, call paths and change impact. No API key.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- Gitleaks Cloud - GitHub API Key Hunter & Secret Scanner @anshumanatrey/gitleaks-github-secret-scannerGitleaks Cloud - GitHub API Key Hunter & Secret Scanner26% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.3 GitHub stars.
- Celmis @constantinemakoid/celmisSelf-hosted code intelligence: cross-repo Q&A, dependency audits and PR review, over MCP5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.3 GitHub stars.
- High Performance MCP Server @aniayana/high-performance-mcp-serverHigh-performance, modular MCP v2 server with safe profiles, worker pool, caching, and stdio.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- Sinter @shellfu/sinterPersistent, evidence-backed code graph for coding agents.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.3 GitHub stars.
- codeindex @munhq/codeindexStructural code intelligence over MCP: symbols, callers, imports and blast radius, 40+ languages.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- quillrag @ayush-yadav11/quillragSingle-binary local RAG MCP server in Rust. MiniLM compiled in, hybrid search, zero deps.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.3 GitHub stars.
- Spiderbrain @spiderbrain/spiderbrainDeterministic context layer for your codebase: change impact, blast radius, answers with receipts.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.3 GitHub stars.
- ovecc @ovecc-labs/oveccArchitecture guardrails for AI-written code: dependency graph, impact, dead code, CI gate2% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- TestAtlas @karzone/testatlas-mcpSemantic map of a .NET test-automation solution for AI agents — search, impact, endpoints2% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from NuGet.3 GitHub stars.
- Maguyva @maguyva/maguyvaCode intelligence for coding agents: semantic, AST, graph, and full-text search. 279+ languages.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.3 GitHub stars.
- Ariadne @whyy9527/ariadneDeterministic local cross-service API-chain discovery for AI coding agents.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.3 GitHub stars.
- LSP @theupsider/lsp-mcpUniversal LSP MCP server6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- fittok @likhithreddy/fittokRetrieve only the relevant code for a codebase question, within a token budget.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.3 GitHub stars.
- Sourcebook @maroondlabs/sourcebookLive codebase intelligence for AI agents: conventions, blast radius, import graphs, git insights.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.3 GitHub stars.
- Droste @lorismascio17/droste-memoryLocal code-memory graph for AI coding agents.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.3 GitHub stars.
- Vector DB MCP @kroq86/vector-db-mcpAssembly-accelerated DuckDB MCP server for code search, indexing, and symbol lookup.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.3 GitHub stars.
- efficient GitLab @detailobsessed/efficient-gitlabToken-efficient GitLab MCP: 167 tools via 3 meta-tools, field projection, keyset pagination3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- Daimonos @beardfaceguy/daimonosAgent-optimized MCP server with structured JSON tools. 20-45% token savings.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.3 GitHub stars.
- Nanostores MCP @valyay/nanostores-mcpDebug and analyze Nanostores apps with AI: scan stores, monitor runtime events, and search docs.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
