"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.

A hybrid Fivetran MCP server with 23 native tools for common data engineering tasks and two universal tools (search/execute) that unlock all 161 Fivetran REST API endpoints.

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.

Exposes materials-science data, simulations, workflows, and computing capabilities to MCP hosts through a plugin-agnostic, contract-governed engine with progressive capability discovery, bounded context, scoped permissions, and provenance-traceable artifacts. Concrete integrations such as a real OPTIMADE provider plugin stay separately packaged, so servers remain focused and evidence-backed rather than unrestricted.

Exposes Iceberg-backed ontology objects, links, and actions as typed MCP tools for LLM agents, enabling governed data access and operations without raw SQL.

Provides deterministic, stateless tools for common data work including JSON, CSV, text, encoding, hashing, IDs, date/time, and number statistics.

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.

Enables repair of malformed JSON strings into valid JSON for agent workflows by fixing common LLM formatting issues. Supports cleanup of code fences, smart quotes, unquoted keys, trailing commas, and missing brackets to ensure reliable data parsing.

Provides persistent, versioned JSON transformation solutions with lineage and evidence retrieval, enabling users to resolve structured problems via query, contribute new solutions, and verify reuse.

Enables read-only access to market data and analytics through one vendor-neutral schema, with Alpaca built in and other providers pluggable. Large results are kept out of the model's context in a local DuckDB store the model queries with read-only SQL, and common analytics such as returns, volatility, correlation, drawdown and beta are computed on those stored results.