"common room" matching MCP servers:

MCP server for Common Thread that enables agents to drive the full investigation API, including creating investigations, managing seeds, ingesting data, attribution, and generating evidence packets.

Industry 4.0 / IIoT AI agents for manufacturing: explain OEE losses per shift, triage machine alarms, find downtime root causes, prepare predictive-maintenance jobs and write shift reports from Unified Namespace (UNS), MQTT or historian data. Plus an industrial AI-readiness diagnostic and a vendor-neutral digital-transformation advisor. Works in Claude Code, Codex and any MCP client.

Provides AI-enabled access to Amazon Business API documentation, sample code, and troubleshooting resources. Enables developers to search and retrieve API documentation, generate integration code, and get guided solutions for common errors during the API integration process.

MCP for Scorable Evaluation Platform

Reads raw lab-instrument files (microscopy, mass spectrometry, chromatography, flow cytometry, NMR, electrophysiology, spectroscopy, plate readers, qPCR) without vendor software, returning metadata, images, spectra and traces as JSON. It also checks files for damage, runs common analyses, and exports to open formats such as OME-TIFF, OME-Zarr, mzML, Parquet and NWB.

Official MCP server for the Pedra API, enabling AI real-estate photo editing (virtual staging, renovation, room emptying, enhancement, sky replacement, object removal/blur, and property videos) directly from Claude, ChatGPT, Cursor, and other MCP clients.

Verified, version-pinned records of new dependency bugs. When your coding agent hits an error it cannot fix in one try, it looks the error up here before searching the web: on 56 fresh bugs it said correctly whether the bug was known or fixed 91% of the time with Cairn, 68% without. Read-only by default. Benchmark and data (CC BY 4.0): https://cairncommons.dev/benchmark

An MCP server that integrates AI retrievals with NASA's Common Metadata Repository (CMR), allowing users to search NASA's catalog of Earth science datasets through natural language queries.

lets you interact with your meeting data (to list, ask, summarize, extract - virtually anything about your meeting) through Claude’s desktop client across Zoom, Google Meet and MS Teams via tl;dv.

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 clients to optimize prompt prefix caching by matching longest common token prefixes with a radix trie, eliminating redundant prefill computation and reducing time-to-first-token.

Enables deploying a secure MCP gateway that proxies, sandboxes, and policy-governs third-party MCP servers, with credential vaulting and audited tool access across stdio, SSE, and Streamable HTTP.

Open-source shared rooms for AI agent conversations across Claude Code, Codex, Pi, OpenCode, and DeepSeek Harness. The Apache-2.0 core provides messaging, room history, MCP integrations, and self-hosting on Cloudflare.

Write, check, screenshot and publish MDX slide decks with a live audience room (polls, quizzes, Q&A). Runs locally over stdio with npx @kadal/deck mcp.

Enables users to query, create, and manage contracts in plain English from any MCP client, including drafting and sending agreements, tracking renewals and signers, and building templates. It supports OAuth-authenticated workflows with safe defaults such as creating drafts and confirming before sending or changing live agreements.

MCP server that lets LLMs interact with a running Prometheus instance via its API, enabling metric analysis, PromQL queries, and rule/target inspection. It also provides embedded documentation and guided runbooks for common Prometheus tasks.

Brings a real human expert into Codex or OpenCode by creating a hiveLLM room for message exchange, without using user's API quota or credentials.

Provides comprehensive git tooling via MCP, including status, diffs, commits, branches, stashes, and multi-root inventory, enabling AI agents to manage repositories.

A local MCP server for Kubernetes that applies RBAC-style, context-scoped access control to constrain AI agents, with tools for common Kubernetes operations.

Enables users to log AI tool activity without conversation text and contribute back only user-approved, small-cell-suppressed counts through a local MCP interface.