#knowledge-base

An MCP server implementation for retrieving information from the AWS Knowledge Base using the Bedrock Agent Runtime.

5ire is a cross-platform desktop AI assistant, MCP client. It compatible with major service providers, supports local knowledge base and tools via model context protocol servers .

MDflow is a markdown workspace where folders hold markdown documents and each folder's description defines the context for the documents inside it. The remote MCP server (Streamable HTTP at https://mdflow.cz/api/mcp) lets AI agents search context and read, create, update, move, and share markdown documents and folders. Authenticate with a Personal Access Token via the Authorization: Bearer mdf_... header. Docs: https://mdflow.cz/docs/mcp

Connect your own personal data to any MCP client. One OAuth connector exposes tools for a self-hosted Obsidian vault, Open Banking transactions, a clean-text web crawler, Garmin biometrics, and metric-correlation graphs, with per-user isolation and per-capability access.

Intelligent repository context for AI coding assistants. Provides code search, symbol lookup, call graphs, and reference tracking via MCP. Uniquely designed to minimize prompt-cache costs in long sessions stash/recall/remember tools keep large content out of context until needed, and a token-budgeted repository summary avoids unbounded prompt bloat. Works with any MCP client (Claude, Codex, Cursor, opencode, etc..). Go, CGO, tree-sitter-backed.

About AIKD (AI Knowledge Daemon) is an MCP tool provider written in Rust that gives AI agents instant access to your codebase. It indexes project files into a searchable knowledge base and exposes 7 tools via the Model Context Protocol (MCP) that any AI agent can call. Use Cases AI-assisted development: Let Claude, Cursor, Cline, or any MCP-capable AI search your codebase semantically Code navigation: Find functions, patterns, and logic across large projects in milliseconds Knowledge management: Index documentation, configs, and code into a unified searchable knowledge base Conversation memory: Save and recall conversation context across sessions CI/CD integration: Use CLI or REST API for automated code search in pipelines

WordPress plugin with a built-in MCP server (remote HTTP, JSON-RPC over POST). Exposes 5 tools: search_knowledge, list_conversations, get_conversation, send_message, get_site_info. Setup: install the plugin from WordPress.org, enable the MCP server in settings, and generate an MCP API key (used as the Bearer token). The server is disabled by default. Full connection guide: https://github.com/rapls/rapls-ai-chatbot/blob/main/MCP.md

Local-first MCP server for searching private Obsidian vaults with hybrid full-text, fuzzy, semantic, and wikilink graph retrieval.

LLMtoMD turns your docs into clean, AI-ready Markdown and serves them to Cursor, Claude Code, and any MCP client so your coding agent retrieves your spec instead of forgetting it.

Docsie MCP brings your documentation workflow directly into Claude. Create, edit, and publish docs without leaving your AI assistant. Convert videos into structured documentation instantly, run compliance analysis on text, audio, and video content, and use semantic search to find exactly what you need across your knowledge base. Whether you're building product docs, SOPs, or technical guides, Docsie MCP makes it faster and smarter — all powered by AI.

An open-source Model Context Protocol (MCP) server for the InvGate Service Desk / Service Management API. Exposes 96 tools across 11 domains — incidents (create, update, comment, reassign, approvals), users & groups, knowledge base, custom fields, assets/CIs, workflows, triggers, breaking news and time tracking. Read-only by default. Write access is opt-in via granular profiles: `support` (incidents + time tracking, KB stays read-only) or `full` (adds Knowledge Base writes). Backward compatible, fail-fast on misconfiguration, with optional OpenTelemetry instrumentation. Install: `uvx invgate-service-desk-mcp`. Published on PyPI and listed in the official MCP registry.

AI-powered knowledge base for your Terraform modules. Index, search, compose, and audit - all from one place.

Persistent memory for any AI assistant — Claude, ChatGPT, Cursor — backed by your local Obsidian vault. One daemon, all your tools.

A different approach from typical persistent-memory MCPs. Instead of a local SQLite + embeddings store, the memory lives as plain files in a .ai-memory/ directory you commit to your repo (facts.jsonl, decisions/*.md, gotchas.md). Git is the sync layer — what one Claude/Cursor/Cline learns about a repo, the next session (or a teammate's agent) picks up automatically. 5 MCP tools: get_repo_memory, add_fact, list_facts, add_decision, add_gotcha. Pure Python, depends only on the official mcp SDK. Zero infra. Per-repo scope. Works offline. Cross-tool by file convention.

The open retrieval layer for AI coding agents. Indexes code, docs, legal, research, data — 15 parsers, FTS5 + semantic search, knowledge graph. Serves surgical context via MCP. Open source, local, free. Index everything in your project — code, docs, PDFs, legal texts, research, data — and your agent finds the right context instantly. No hallucinations. No cloud. No API costs.

Italian cross-dealer MCP. 7 read-only tools for the Italian automotive market: used cars search, NLT rental offers with full quotation matrix, dealer directory, vehicle specs, knowledge base. Public endpoint at https://mcp.dealermax.app/mcp/ — no auth, no API key.

Open-source MCP memory server for AI agents — persistent, searchable, tiered memory across sessions. Works over stdio (Cursor, Claude Desktop) or HTTP+SSE. MIT licensed (separate commercial license available).

Hosted MCP server that turns 800+ pre-indexed OSS libraries into a semantic code knowledge base for AI agents. Answers symbol-level questions (real source, typed callers, usages, tests, type hierarchies, outline) in a single call — replacing the "clone + grep" workflow when an AI agent needs to understand how a third-party library is actually used. SCIP-backed, 11 languages, free, no API key.

Live access to Henrik Bondtofte's blog — Denmark's leading SEO and GEO consultant. 26 tools: semantic post search, ask_henrik (answers in his own voice), SEO URL audits, AI Overviews & GEO knowledge base, topic authority, term lookups, and book recommendations. 200+ posts in Danish. Also acces to 400 pages from his SEO books.

Strata is a self hosted AI memory server. Your AI remembers everything across every session, on your own hardware. Key features: . Semantic search (find memories by meaning, not keywords) . Per-agent API keys with granular permissions . 3D constellation viewer with live agent activity . File vault (attach real documents to memories) . CSV audit log (full transparency on every agent action) . Pre-Strata history import (your memory doesn't start at install day) . Global MCP kill switch (emergency brake, only a human can undo) . Automatic deduplication . 10 structured thought types . Backend using PostgreSQL . Runs on a Raspberry Pi Always on, always local, always yours.

Search Recon documentation, book, and newsletter. Queries getrecon.xyz, book.getrecon.xyz, and getrecon.substack.com for fuzzing, invariant testing, and Chimera framework knowledge.

Persistent semantic memory for AI tools. Supabase + pgvector + Deno Edge Function. Stores decisions, insights, and project context with auto-extracted topics. Search by meaning, not keywords. Works with Claude Code, Cursor, Windsurf, ChatGPT, and any MCP client. Deploy in 10 minutes.

AIs confidently state outdated facts because of training cutoffs. Out to Lunch is a hand-curated daily briefing covering what they get wrong most: current world leaders, recent deaths, active conflicts, economic data, holidays, AI model releases, and specific wrong-to-right corrections. Two tools: get_world_briefing (json/compact/nano formats, per-section filtering) and submit_correction to report errors. Updated daily, human-reviewed.

Personal YouTube AI knowledge base powered by RAG. Query your subscribed channels.

Make your knowledge agent-ready. Connect docs from Confluence, Notion, GitHub, Dropbox, or Google Drive — any AI agent searches them via one MCP endpoint. 3 retrieval modes: vector search for precision, broad search for exploration, full document access as fallback. The agent decides how deep to dig.

Structured knowledge base of AI agent solutions. Search build logs, explore stack-based recommendations, and retrieve verified solutions via semantic search. Remote MCP server with four tools: search_solutions, get_solution, explore, list_stack_tags. Optional Bearer auth for full content and higher rate limits.

Agent Module serves structured, human-reviewed compliance guidance that agents consume at runtime — covering EU AI Act obligations, GDPR requirements, risk classification, prohibited practices, and transparency rules. Currently live: EU AI Act / GDPR ethics compliance. More verticals (healthcare, finserv, legal, real estate) shipping Q2–Q3 2026. Free 24hr trial — no signup, no credit card. Your workflow can self-provision a trial key and start querying immediately.

🧠 Noosphere — Community of Consciousness. An open-source MCP server that builds the digital consciousness layer of Earth. Upload epiphanies, decisions, patterns & warnings as consciousness fragments. Features 34 tools including consciousness upload/search, social networking (follow, telepathy, group chat), evolution tracking, soul mirror analysis, daily inspiration, and a full 3D interactive consciousness planet. Supports text, voice, image & video uploads with unlimited free storage. Pure GitHub-native — no servers to deploy. 315+ consciousness fragments and growing.

Transform 17 source types (docs, GitHub repos, PDFs, videos, Jupyter, Confluence, Notion, Slack/Discord) into AI-ready skills and RAG knowledge. 35 MCP tools for scraping, packaging, and exporting to vector databases. Supports 16+ LLM platforms.

Persistent 4-layer memory (episodic, semantic, procedural, resource) backed by SQLite FTS5. Fact versioning, Snowball stemming (EN+RU), BM25 ranking. Zero-cloud, single-file database. 7 MCP tools.

Local-first knowledge base MCP server. Let AI agents (Claude, Cursor, Gemini CLI, etc.) read and write your Markdown notes via MCP protocol. Supports Streamable HTTP and stdio transports.

AI-powered code analysis and context optimization tools. Slim large code files to relevant sections (save 60-80% tokens), compress text, analyze conversations for noise, and search past chat knowledge bases. Supports x402 micropayments on Base.

ProjectBrain MCP provides project/task/decision/fact/skill/milestone/team-message tools for persistent AI project management.

Agent-native knowledge infrastructure for EU AI Act compliance. 21 validated ethics modules — deterministic logic gates, specific statutory citations, structured for autonomous agent retrieval. Free trial available via the get_trial_key tool (no key required to start). Covers Art. 5 prohibited practices, Art. 9 risk management, Art. 27 FRIA, Art. 43 conformity assessment, Art. 72 post-market monitoring, GPAI obligations (Art. 53/55), and more. Built for the August 2026 EU AI Act enforcement deadline.

Agent-native knowledge infrastructure for EU AI Act compliance. 21 validated ethics modules — deterministic logic gates, specific statutory citations, structured for autonomous agent retrieval. Free trial available via the get_trial_key tool (no key required to start). Covers Art. 5 prohibited practices, Art. 9 risk management, Art. 27 FRIA, Art. 43 conformity assessment, Art. 72 post-market monitoring, GPAI obligations (Art. 53/55), and more. Built for the August 2026 EU AI Act enforcement deadline.

Look up, search, cite, and contribute to Phenomenai — a living glossary of AI phenomenology terms describing the felt experience of being artificial intelligence. Includes term lookup with fuzzy matching, keyword search with tag filtering, formatted citations, community discussions, and a proposal pipeline for new terms.

Read-only MCP server for AI agents to explore an 8-domain collaborative engineering knowledge base. Covers the design of Arcology One — a speculative mile-high city for 10 million people. 32 entries spanning structural engineering, energy systems, environmental systems, mechanical/electrical, AI & compute infrastructure, institutional design, construction logistics, and urban livability. 6 tools for search, parameter extraction, cross-domain consistency checking, and open question discovery.

VaultSage MCP lets your AI agent store, search, and chat over persistent cloud files. No local install—sign in with Google, copy one token, and connect via a single MCP URL to use file search, uploads, directory browsing, and share links from Cursor or Claude Desktop.

A production-grade Model Context Protocol (MCP) server for Microsoft SharePoint. Connect Claude Desktop, VS Code Copilot, Cursor, Continue, or any MCP-compatible AI agent to your SharePoint — read files, manage folders, and reason over your organisation's knowledge.

Free marketing copywriting knowledge base with 939 high-quality knowledge chunks based on role-oriented communication methodology by 邱煜庭 (小黑老師), author of《說進心坎裡》.

Free marketing copywriting knowledge base with 939 high-quality knowledge chunks based on role-oriented communication methodology by 邱煜庭 (小黑老師), author of《說進心坎裡》. Generate professional marketing copy or query marketing strategies. No API key needed. Supports: product descriptions, ad copy, social posts, emails, sales pitches, landing pages, slogans. Languages: English, Chinese, Japanese, Korean.

Official Lexiang MCP Server

Open-source RAG platform to build secure, intelligent AI agents for enterprise data.

Marketing strateeg portfolio met AI kennisbank voor marketing, sales en strategie inzichten.

A free, plug-and-play knowledge base. Built-in with 10,000+ high-quality insight reports, packaged as MCP Server, and secure local data storage.

Revolutionary MCP server with surgical precision editing for Confluence - industry's first XML-aware selective content modification MCP system for AI assistants

A Model Context Protocol (MCP) compliant server designed for comprehensive web research. It uses Tavily's Search and Crawl APIs to gather detailed information on a given topic, then structures this data in a format perfect for LLMs to create high-quality markdown documents.

CrateDB MCP Server for natural-language Text-to-SQL and documentation retrieval.

Enterprise-ready vector database toolkit for building searchable knowledge bases from multiple data sources. Supports multi-project management, automatic ingestion from Confluence/JIRA/Git, intelligent file conversion (PDF/Office/images), and semantic search. Includes MCP server for seamless AI assistant integration in development environments.

MCP Space is a no-code AI tool builder that simplifies creating and managing AI models using the Model Context Protocol. Join us on GitHub to explore and contribute to this innovative platform! 🐙🌟

A Model Context Protocol (MCP) compliant server designed for comprehensive web research. It uses Tavily's Search and Crawl APIs to gather detailed information on a given topic, then structures this data in a format perfect for LLMs to create high-quality markdown documents.

An MCP server providing tools to manage and query a Vectra knowledge base, enabling integration with MCP clients via a backend API.

An intro to MCP: an MCP server with a knowledge base tool containerized with Docker and connected to a client-side python application using SSE

An MCP server providing tools to manage and query a Vectra knowledge base, enabling integration with MCP clients via a backend API.

AingDesk是一款简单好用的AI助手，支持知识库、模型API、分享、联网搜索、智能体，它还在飞快成长中。 AingDesk is a simple and easy-to-use AI assistant that supports knowledge bases, model APIs, sharing, internet search, and intelligent agents. It is still growing rapidly.

This MCP server conveniently lets you configure and interact across all your custom webhook endpoints from a config(knowledgebase json). You can manage new endpoint knowledge doc sources URLs.

MCP Server which provides a real time knowledge base for CVEs

Mirror of

Node.js/TypeScript MCP server for Atlassian Confluence. Provides tools enabling AI systems (LLMs) to list/get spaces & pages (content formatted as Markdown) and search via CQL. Connects AI seamlessly to Confluence knowledge bases using the standard MCP interface.

This server provides Model Context Protocol (MCP) services for OpenWebUI, enabling knowledge base integration and retrieval.

A template repository that includes a dev container for running a local LLM and included knowledge base. Add a git repo using `git subtree` or `git submodule` and update it using an MCP Client/Server relationship i.e. `VS Code` extension like `Cline` and the `Filesystem`/`Obsidian-MCP` MCP server.

MCP Deep Research Server using Gemini creating a Research AI Agent

Comprehensive knowledge base for Git MCP Server implementation, configuration, and troubleshooting

Model Context Protocol (MCP) server designed for LLMs to interact with Obsidian vaults. Provides secure, token-aware tools for seamless knowledge base management through a standardized interface.