"Creating a Custom Local Knowledge Base" matching MCP servers:

A local MCP server that gives LLMs long-term memory by indexing code, infrastructure, logs, and docs into a queryable graph. It enables semantic and structural search, evidence-backed reasoning, and tracked plans that persist across sessions and teams.

Local-first Microsoft Outlook MCP server: a single Go binary that manages calendar events and mail through the Microsoft Graph API over stdio, with tokens stored in the OS keychain and no Entra ID app registration required. Exposes four aggregate tools (calendar, mail, account, system) dispatched by an operation verb, with multi-account support and read-only and mail-gating modes.

Connects AI tools to GitHub and local git repositories, enabling natural language management of issues, PRs, code analysis, and workflows.

Enables LLM agents to maintain structured long-term memory and knowledge using SQLite, with graph storage and relational query tools for persistent context.

Coordination for parallel coding agents: TTL file claims stored in the git common dir (visible across all worktrees), enforcement hooks that block colliding edits, agent presence, handoff notes, and a git-committed lessons knowledge base with BM25 search. Single static Go binary — no server, no database.

MCP server for Directum RX (ECM/BPM): assignments, tasks, documents and their text, knowledge base, agile boards, project plans, any entity via OData, and search over the system help of your own RX version. Read-only by default; write tools are behind a flag and ask for confirmation.

Enables AI coding assistants to search and retrieve information from a locally ingested knowledge base using hybrid search, grounded in user-curated documentation.

KSM MCP is a Model Context Protocol (MCP) server that acts as a secure intermediary between AI language models (like Claude) and Keeper Secrets Manager (KSM). It allows AI agents to manage your KSM secrets-such as listing, creating, retrieving, and deleting records and folders-while protecting your

Enables querying and, when explicitly enabled, creating Pix charges through a local stdio server with SQLite-backed idempotency and audit.

A modern community hub with forum and knowledge base. Native MCP built-in, ready for the next era of internet culture.

Serves a folder as an MCP knowledge server: it indexes text, code, PDFs, office documents and audio or video, then answers search and ask calls with citations that name the file, the line range, the page or the time range. Runs fully local with Ollama by default; Mistral, OpenAI, Gemini and Anthropic are optional providers.

This project is intended as a both MCP server connecting to Kubernetes and a library to build more servers for any custom resources in Kubernetes.

A frontier knowledge base that’s minimal extensible and agent-native. Built to keep your team’s shared context current and inspectable.

Enables AI agents to orchestrate 100+ security tools over MCP for authorized penetration testing, including recon, scanning, exploitation, attack-chain planning, and knowledge-base retrieval.

A self-hosted personal context server that unifies knowledge base, retrieval, credential management, and agent memory via MCP, with a built-in notes app for human oversight.

Enables MCP-capable AI clients to read and write a self-hosted todo list, quick memos, and a plain-Markdown knowledge base through 16 tools covering search, tasks, notes, and identity checks. Tool visibility is scoped per API key with directory-level permissions, and every call is audit-logged.

An MCP server that lets AI agents read and write a self-hosted TriliumNext knowledge base over its ETAPI, enabling note capture, structured table maintenance, and search.

High-performance code graph and code intelligence engine. Index code base into knowledge graph, supports 257 languages and native multi repositories environment

A local-first MCP server that indexes Markdown/Obsidian folders and lets AI clients retrieve cited local context through MCP.

Provides persistent memory for AI tools by building a local knowledge graph from conversations, enabling cross-session recall and context awareness without cloud dependencies.