"A system for building an autonomous second brain" matching MCP servers:

This MCP server implements a second brain system, managing unvalidated investigation cases as JSON and validated knowledge as markdown files and skills. It provides tools for creating, updating, promoting cases, managing knowledge files, and performing semantic search.

Enables AI assistants to search a shared local archive of selected sessions, notes, and connected sources, returning source-backed context and citations through read-only MCP access.

Enables MCP clients to search and read notes from an Obsidian or markdown vault through four governed tools, with enforced read-only access, a page budget, and path sandboxing.

MCP server that ingests YouTube videos and podcasts, making them searchable with timestamps and deep links to exact moments.

Self-maintaining personal knowledge database — MCP server with figure-level search, auto-wikilinks, and Ebbinghaus-based memory compression

An MCP server that exposes an Obsidian vault to Claude, enabling reading, searching, writing notes, capturing voice thoughts, and managing tasks. It enforces vault filing rules in code, with path confinement and no hard deletes for safety.

Lets every AI client search, read, write, and edit the same Markdown notes by keyword or meaning, with each change committed to Git.

Self-hosted semantic memory layer for Claude and MCP-compatible AI clients. Store notes, search by meaning not keywords, and recall relevant context automatically across sessions. Runs free on Cloudflare Workers, D1, Vectorize, and Workers AI

Local MCP server that automates an open Obsidian vault through Obsidian's official CLI, offering tools for note creation/update, search, tasks, daily notes, and organization. It uses MCP over STDIO, requires no cloud services, and provides safety/audit features for autonomous writes.

Provides semantic search, note retrieval, source explanation, daily digests, and health checks for a local Obsidian vault, enabling MCP clients like Claude Desktop and Claude Code to query the second brain via natural language.

Enables read-only access to Obsidian vaults with semantic search, tag filtering, and metadata queries. Provides secure, intelligent note retrieval and summarization for LLMs without modifying your vault.

Enables Claude to review drafts by fact-checking claims against web sources, building the strongest counter-argument, suggesting copy edits, and flagging potentially unoriginal text, returning a sourced report.

Provides 12 tools to query South Korean building register data, including title sheets, floor details, and official house prices via the data.go.kr API. It enables users to perform smart building lookups and region code searches using natural language.

Connects claude.ai to a private GitHub repo of markdown files as a personal second brain, providing guarded read and write tools for knowledge management.

A personal second brain on Cloudflare Workers that stores knowledge as a semantic graph with auto-linking, deduplication, and MCP tools for AI agents to save, search, and connect information.

Self-hosted MCP server for collecting, searching, and sharing agent session history from Claude Code, Codex, and Cursor, with repository scoping and token-based authentication.

Provides comprehensive building and office address information queries for enterprises in China, including fuzzy enterprise search, office address details and statistics, and building information queries to support geographical distribution and occupancy analysis.

A standalone Node MCP server that provides semantic search, knowledge graph, and vault editing over an Obsidian vault. It runs locally as a single stdio process without requiring an Obsidian plugin for core functionality.

Turns an Obsidian vault into live, private context for Claude and other MCP clients, enabling identity-aware search, project briefings, graph traversal, recent-note retrieval, captures, and memory writes directly against the vault.

Cognitive prosthetic for AI agents. Indexes conversation history from ChatGPT, Claude Code, Cursor, and Gemini CLI into searchable embeddings. 25 MCP tools including tunnel_state (resume where you left off), switching_cost (quantify context-switch penalty), thinking_trajectory (track idea evolution), and alignment_check (decisions vs principles). LanceDB + Parquet, 12ms recall, local-first.

Enables hybrid dense and BM25 search over a markdown vault, with tools for reading, writing, grepping, and managing notes through any MCP-compatible client.

Serves a Markdown memory vault to AI agents over MCP, letting them write, search, edit, and verify memories while full-text and graph indexes stay in sync in the background. Combines SQLite FTS5 retrieval with a Graphiti temporal knowledge graph so agents can recall both documents and entity facts over time.

Local-first knowledge system for reasoning agents, exposing facts, evidence, documents, retrieval, and audit history through a thin stdio MCP server.

Enables Claude to capture structured, schema-validated notes into a personal Obsidian vault's inbox and later recall them through ranked keyword search, recency listing, and single-note reading, with reads confined to the vault and no edit or delete access.

An MCP server that enables AI agents to search, read, and contribute to a structured markdown knowledge base with citations, freshness tracking, and a safe write path, providing a shared, auditable company memory.

Gives Claude durable, queryable memory by logging every prompt/response to Supabase Postgres and exposing MCP tools to save, search, and retrieve conversation history.

Enables Claude Code to search, read, create, edit, rename, and delete notes in a shared self-hosted markdown vault, and to inspect backlinks, outgoing links, outlines, tags, properties, daily notes, unresolved links, orphans, dead-ends, and templates over Streamable HTTP with bearer-token authentication.

Open-source MCP server that gives any LLM long-term memory using a knowledge graph and vector search hybrid. It stores entities, observations, and relationships, enabling semantic recall across sessions with automatic clustering and fail-loud infrastructure.

Enables MCP clients to use a FalkorDB-backed LinkedIn network graph as agent memory, with tools to remember people and notes, find entities, run read-only Cypher questions, and forget facts, alongside a 3D network viewer.

Enables querying a folder of company documents over MCP and retrieving matching passages with file:line citations for Claude to answer from. Supports keyword and multilingual hybrid search over an incrementally indexed SQLite knowledge base.