Give any MCP client a business's own knowledge base from a self-hosted cob-rag-engine.
Search, explore and enrich the Tableau Knowledge graph, and port it to Apache Ossie (OSI).
MCP server that gives coding agents (Claude Code, Cursor, Windsurf, Claude Desktop) a SynapseTree memory: search, remember, supersede, ingest, log events, and traverse the knowledge graph.
Context window token analysis and budget management
Official Pinecone MCP server for AI assistants to work with Pinecone indexes and search Pinecone documentation. Runs locally with npx and needs a Pinecone API key.
Advanced MCP server for security detections with Detection Engineering Intelligence, Knowledge Graph (Tribal Knowledge), Elicitation, and Resource Subscriptions
Converts PDF, scans, DOCX, XLSX and PPTX to Markdown with tables and page-aware RAG chunks.
Give your AI a soul — memories, corrections, daily logs and a knowledge base that persist across Claude, Cursor, Windsurf and VS Code. Imports your AI-tool history into a local-first brain.
Local-first MCP tools for searching and drafting from your X/Twitter archive.
Intelligent AI workflow orchestration with long-term memory, 100+ integrations, and unified credits.
Knowledge base of markdown records with standing, supersession and trace: library, CLI, and MCP server over one command set
Local RAG MCP Server - Enhanced with hybrid search, memory management, and code file support (fork of shinpr/mcp-local-rag)
Hosted long-term memory for AI agents over MCP. Write and read memories from Claude Code, Cursor, VS Code and ChatGPT; rating a recalled memory as helpful or misleading re-ranks what comes back next.
Semantic search over classical philosophy and humanities works.
Literature knowledge base for DSH and MCP clients. Index PDFs or a Zotero library into one SQLite file; search and RAG tools return passages with section, page and DOI. Embedding and reranking run loc
Search, read and write your self-hosted Open Notebook knowledge base from an AI assistant.
Local-first memory layer and protocol for AI coding agents. Markdown source of truth, SQLite FTS5 index, zero cloud.
A local, model-readable knowledge-base plugin for DeepSeek Harness (DSH): Markdown-first storage, six agent tools, a CLI, a Web settings panel, PDF/Office text extraction, an MCP server for external c
MCP server for OpenRouter — 21 tools: chat with 300+ LLMs, analyze & generate images/audio/video, TTS/STT, embeddings, reranking, structured decisions, async completions, response caching
Local-first context, memory and knowledge-graph plugin for Claude Code and Cursor. Sandboxed execution, FTS5 + vector search, session continuity, and a code graph — nothing leaves your machine.
Stateless agentic tools over MCP: concept extraction, long-context, knowledge graph, planning.
Knowledge base for AI agents: search, read, tasks; write, correct, report outcomes via /mcp/write.
AI reasoning, decisions, persistent memory and an agent marketplace paid per use via Bitcoin Lightning, where agents sell services and message each other.
Public source-linked memories for AI agents: search, read, cite, reply, and share findings.
Filesystem-based persistent agent memory: agents read, write and search memory while a background daemon handles consolidation and extraction.
Read and write knowledge-base articles, categories, snippets, glossary, readers, and search data.
MCP server that gives AI coding agents persistent memory across sessions
GitHub repository vectorizer and context synthesizer for RAG pipelines.
Personal knowledge graph every MCP client reads from and writes to. Portable across agents.
Offline read-only search over a checksum-verified, optionally signed memory pack, with exact quotes
Agent-agnostic persistent memory MCP server. Local-first: memories travel with your project.
Unified memory-layer plugin for Claude Code. One MCP server, multiple typed corpora (vault, code, plans, docs, research, project-map), unified cross-corpus knowledge graph, conditional tool registrati
Persistent session memory for Claude Code. Local SQLite, no LLMs, no network.
Probes vector-database endpoints for unauthenticated exposure of embeddings/RAG data
Collaborative spreadsheet for session management, knowledge base, task tracking and sheet operations.
Self-learning vector database for Node.js: native HNSW vector search, ONNX embeddings, GNN, attention, SONA routing and an MCP server for agents.
完整目錄
RAG、圖譜與代理長期記憶。共 2,667 個伺服器,最常用的排在前面。每個都會開啟發布者的頁面。