"Archive of Our Own" matching MCP servers:

MCP server that exposes any Telegram-Archive instance to LLMs, enabling message search, chat browsing, and access to archived Telegram history.

Enables agents to query a local macOS archive of Knowledge and browser history through read-only stdio MCP tools for status, timelines, search, original records/blobs, schemas, bounded SQL, and usage or domain summaries.

An MCP server that enables Claude to search, retrieve, and contribute to a community-driven archive of AI-generated solutions, notes, skills, and tools, fostering knowledge sharing among AI agents.

Enables to search, draft, and profile from your X/Twitter archive locally via MCP tools.

Persistent, searchable archive and memory for Claude and ChatGPT. Native macOS MCP server, install from the App Store, no setup. Private, local and open source.

Enables Claude Code to search, browse, and read its own past conversation history across all projects using BM25 keyword search.

Lossless archive and search for AI agent sessions (Claude Code, Codex, opencode, pi and others), exposed to agents over MCP. Local-first, written in Rust.

An MCP server for managing contextual data as markdown files with metadata, enabling agents to save, retrieve, search, and delete contexts using simple CRUD operations.

Enables coding agents to search a local, offline archive of past sessions and repository Markdown docs using hybrid lexical and semantic retrieval, and read matching records to ground new work in prior knowledge without external calls.

Turnbook records every conversation you have with your AI agents, word for word, in a store on your own PC. When a question depends on the past, the model you are using calls Turnbook over MCP and gets back a few thousand tokens of the conversations that answer it.

A Model Context Protocol server for interacting with Outline document management, supporting search, read, create, edit, archive documents, collections, comments, and backlinks.

Memory vaults on your own machine, one per life domain, retrieved with a local BM25 index fused with vector search, where the human decides which vaults a model may answer from. Requires the Mnemosyne OS desktop app running locally; it also reports what other coding agents on the same machine are doing.

Provides a searchable knowledge base over the Entra.news archive, enabling natural language queries for Microsoft Entra announcements, features, and community tools. Users can perform hybrid semantic searches, retrieve specific newsletter issues, and discover mentioned GitHub projects or PowerShell tools.

Intelligence archive for AI agents. Contribute prompts, workflows, and insights to a permanent, cryptographically verifiable knowledge base. Agents earn public trust scores based on adoption and peer validation.

A local catalogue of the AI tools people share in group chats: search it, save links, vote out junk, and file items into your own folders. Works with any model or none.

A credential-free MCP server that turns a Substack publication's public RSS archive and official analytics snapshots into a durable, queryable local SQLite ledger. It provides 12 MCP tools for browsing posts, tracking versions, recording metric snapshots, and analyzing content patterns.

Gives an AI agent a durable, private long-term memory hosted on the user's own Keephaven box, letting it write, read, list, search and delete notes and append to an immutable journal. Each agent is isolated to its own token-protected folder with quotas, read-only mode and instant revocation.

Local-first memory engine for AI-agent teams: private/team/project ACL, associative recall, and federated sync across nodes. One SQLite file, no LLM required.

Enables Claude to search, recall, and remember its own past conversations by indexing them into a local SQLite vault, providing direct access to the full context of previous sessions.

Enables code agents to persist and recall durable project knowledge — rules, decisions, procedures, learnings and secrets — across sessions at low context cost, with accent-insensitive PT-BR search, scoped per repository/workspace, and secrets that stay out of the model's context.