"common room" matching MCP servers:

A local-first MCP server that indexes code repositories and enables AI assistants to search, fetch, and navigate code using BM25 hybrid retrieval, supporting common languages and tools like Codex and ChatGPT.

Enables LLM agents to query a contract data room using structured metadata filters and BM25 full-text search over contract articles, returning relevant contracts, justifying clauses, and explicitly excluded unknowns. It supports exhaustive list answers and citation-ready JSON for MCP clients.

A lightweight server that provides curated, high-quality prompts for common development tasks like UI/UX design, project setup, and debugging to enhance AI-powered development workflows.

Adds interactive widgets to LLM chats for common tasks like timers, stopwatches, unit conversions, and displaying facts. Breaks away from text-only interfaces by providing visual, interactive components similar to Google's search result widgets.

DEVONthink 4 connector with six tools for search, retrieval, and write operations. Dry-run by default, append-only audit log, selective undo via audit_id; macOS-only, MIT, local-only, clean-room implementation.

Enables AI agents to create, search, and manage subject matter expert profiles, including private workspace organization and moderated sharing to a common library.

Enables accessing and managing personal/team internal knowledge repository with tools for semantic search, smart search, document listing, and saving information for future recall.

A stdio MCP server backed by the TypeScript SDK that exposes frozen Clervo operations for web search and answer functionality, enabling agents to find and understand information through a clean-room outcome infrastructure.

This server enables AI assistants (CLINE, Cursor, Windsurf, Claude Desktop) to share a common knowledge base through Retrieval Augmented Generation (RAG), providing consistent information access across multiple tools.

A persistent world your agents share across sessions and models. MCP memory server with semantic memory retrieval, cross-agent handoff, a hosted remote endpoint with OAuth, a free 24-hour room, and an open-source local stdio server.

Local-first knowledge graph MCP server — hybrid BM25 + vector + graph retrieval over your personal vault with provenance-grade extraction. 8 tools for Claude Desktop including search, archaeology, and graph write.

MCP for Scorable Evaluation Platform

Enables Claude Desktop and compatible agents to search, read, add, update, and delete a locally stored, user-curated memory using hybrid retrieval with reranking and Qdrant. All processing runs locally without cloud services or API keys.

The open retrieval layer for AI agents. Index your entire project — code, docs, legal, research, data — and serve surgical context via MCP. FTS5 full-text search, optional semantic search (FastEmbed/ONNX), 10 built-in parsers, incremental auto-sync.

MCP search and evidence tool for AI agents. Rewrites queries, zooms into source domains, and returns sourced answers with metrics.

Enables fully local semantic search over a Roam Research graph via MCP, providing tools for hybrid retrieval, index refresh, and stats while keeping all content on-machine.

Enables searching, retrieving, and analyzing documents from over 30 Egyptian official, legal, academic, and news sources with MCP tools for timeline building, source comparison, and claim tracing.

Enables Alexa+ listeners to find and hear previously aired local public-radio stories they only half-remember, answering from the station's own editor-approved published record with the show and month attributed. Returns up to three matching stories or a single story told with its source and a next step, plus an on-screen story card with artwork, places, things to do, and a Play button.

An MCP proxy server that intercepts large tabular tool results, ingests them into an embedded DuckDB, and provides a compact envelope with schema and query capabilities, enabling efficient cross-server data analysis.

Serves one shared knowledge store over MCP so multiple coding agents can read and write the same facts, standing rules and research notes, with duplicate detection, per-repository scopes and inheritance from a global scope. This lets a correction taught to one agent apply to all of them at once, while tracking usage and keeping concurrent writes safe.