- TokenKnows @johnnywuj81/tokenknowsDistill AI coding sessions into weekly reports, ADRs and a knowledge graph - self-hosted5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.4 GitHub stars.
- Skill Shelf (Rust singleton daemon) @halflifezyf2680/skill-shelfProgressive group routing for 524 professional skills via Rust daemon stdio shim.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.4 GitHub stars.
- MemoGraph @indhar01/memographGraph-based memory system for LLMs with knowledge graphs and semantic search.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.4 GitHub stars.
- Atlassian Dc Confluence @mrrefactoring/atlassian-dc-mcp-confluenceMCP server for Atlassian Confluence Data Center - access and manage content4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- Magnemo @magnemo/magnemoGoverned memory for AI agents. Memory with receipts. Local, plain files, zero network calls.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.3 GitHub stars.
- gosidian @daniele-chiappa/gosidianSelf-hosted Obsidian-compatible markdown vault with a web UI and a 63-tool MCP server for AI agents4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.3 GitHub stars.
- Hudu @wyre-ai/hudu-mcpMCP server for Hudu IT documentation — companies, assets, articles, passwords, and procedures.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.3 GitHub stars.
- Firekeep @kapella-hub/firekeepSelf-hosted operating layer for AI agents: knowledge, continuity, coordination, and governance.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.3 GitHub stars.
- Workfile @illodev/workfileRepository-native protocol and local MCP server for Work, Docs, History and durable project Memory.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- Hudu @wyre-technology/hudu-mcpMCP server for Hudu IT documentation — companies, assets, articles, passwords, and procedures.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.3 GitHub stars.
- EVC Team Relay @entire-vc/evc-team-relay-mcpMCP server for AI agent read/write access to Obsidian vaults via EVC Team Relay.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.3 GitHub stars.
- SmartMemory @mauriceisrael/smartmemoryNeuro-symbolic memory for LLMs (POC)4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.3 GitHub stars.
- Biel.ai @biel/biel-aiQuery your product docs from AI tools. Source-cited answers from your indexed documentation.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.3 GitHub stars.
- briar @iklobato/briarLocal knowledge store built from GitHub, Jira, Linear and cloud history, served over MCP.Not assessed yet.Runs on your machine, installed from Docker.2 GitHub stars.
- Metis @brightbeamai/metisGoverned tacit memory for AI agents: reviewed expert know-how, given only where conditions match4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- Noetive @noetive/mcp-serverYour agents share what they learn. Semantik finds it by meaning, with no topic names to agree on.Not assessed yet.Runs on your machine, installed from npm.2 GitHub stars.
- Tencent Lexiang MCP Server @tencent-lexiang/lexiang-mcp-serverTencent Lexiang AI knowledge base MCP server for searching, managing entries, and editing docs.10% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.2 GitHub stars.
- DEPRECATED - Use lexiang-mcp-server @tencent-lexiang/mcp-serverDEPRECATED: Please use io.github.tencent-lexiang/lexiang-mcp-server instead.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.2 GitHub stars.
- Ossian @dockndevai/ossian-mcpAsk your own documents with citations, plus durable memory for agents. Safe by default.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Wiki.js @ni-c/wikijs-mcpSearch, read and edit Wiki.js pages, and manage its assets, users, groups and comments4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Cli @aligndottech/cliCross-tool decision memory for AI coding agents: search your decision graph, check changes over MCP.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Inkwell @veronchenko/inkwell-memoryPersistent memory for AI agents: Markdown entries, hybrid search, typed graph links4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.2 GitHub stars.
- SpecMgr @dfch/biz-dfch-specmgrAn artifact manager for system specifications.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- Cachly Dev MCP @cachly-dev/mcp-serverSolve it once. From then on, your AI knows. Experience for coding agents, EU-hosted. 124 MCP tools.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
