- CogniRepo @ashlesh-t/cognirepoFAISS, call graph, AST, BM25 — 34 MCP tools for AI agents. 50-80% token reduction. Offline.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.14 GitHub stars.
- Hated WoW MCP @rdygaming/hated-wow-mcpMCP server for WoW addons: Lua API, Blizzard UI source, CVars, art lookup, linting, scaffolding.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.13 GitHub stars.
- ABAP Adt @williansaez/abap-adt-mcpABAP development from Claude and other MCP hosts: source, transports, tests, ATC, debugger4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.13 GitHub stars.
- Local Rag @damoqiongqiu/mcp-local-ragSemantic code & doc search with keyword boost. AST code nav, auto HF mirror, local, privacy-first.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.13 GitHub stars.
- Kotlin & Java Library Sources @aoreshkov/kotlin-lib-mcpKotlin/Java library sources, public API and KDoc from the real Maven sources jar, for AI agents3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.13 GitHub stars.
- Locus @sylphxai/locusLocus — the exact code chunk for the job: local BM25 search for agents.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.12 GitHub stars.
- mdflow — Context OS for AI Coding Agents @yubinbin32-ops/mdflowContext OS for AI coding agents: task-scoped AST context, verified mutation, and rollback.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.12 GitHub stars.
- Memex @stifler7/memexTemporal engineering context for agents via MCP.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.12 GitHub stars.
- Codeweaver @knitli/codeweaverSemantic code search built for AI agents. Hybrid, AST-aware, context for 166 languages.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.12 GitHub stars.
- Miru @takara/miruHybrid semantic and keyword code search for coding agents.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.11 GitHub stars.
- AIContextBuilder @gregordadera/aicb-roslyn-mcpSymbol-aware C# and .NET code context for AI coding assistants.Not assessed yet.Runs on your machine, installed from NuGet.11 GitHub stars.
- AIContextBuilder @gregordadera/aicbSymbol-aware C# and .NET code context for AI coding assistants.Not assessed yet.Runs on your machine, installed from NuGet.11 GitHub stars.
- coldstart @akashgoenka/coldstartCodebase memory for AI agents: an AST index plus agent-written notes that self-stale.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.11 GitHub stars.
- Paparats – Local Semantic Code Search MCP @ibazylchuk/paparats-mcpLocal-first semantic code search across all your repos. Private context for AI coding assistants.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.11 GitHub stars.
- Klarion @0x1adi/klarionSecret scanning for AI agents: rules and entropy find candidates, a model decides which are real.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.10 GitHub stars.
- Prism @shailesh200/prismLocal-first repo intelligence for agents: DNA, health, blast radius, and Dispatch jobs.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.10 GitHub stars.
- Fw Context @turbyho/fw-context-mcpBuild-aware code intelligence for embedded C/C++ firmware — libclang, FTS5, call graphs, 33 tools4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.10 GitHub stars.
- Turbo Quant Memory @lexus2016/turbo-quant-memoryLocal-first memory and knowledge graph for coding agents. Compact retrieval, no network.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.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.
- Rune @thecolourfoundation/runeEvidence-backed codebase understanding with file:line citations, for AI clients over MCP.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.9 GitHub stars.
- XAF Logic Explainer @peopleworks/xaf-logic-explainerQuery your DevExpress XAF app: entities, controllers, actions, rules, Model Editor.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from NuGet.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.
- 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.
