microqueryhq avatar

Microquery Mcp

microqueryhq/microquery-mcp

Turns Claude into a SQL interface for real world datasets: FDA adverse events, SEC filings, blockchain transactions, clinical trials, CVEs, genomics, and two dozen others. Exposes four tools: query() runs Sneller SQL and auto-registers an account on first call, list_databases() returns live schemas, authenticate() links a wallet, and get_quickstart() surfaces recipe queries. Ships with $0.10 trial credit covering roughly 1,600 queries, stored in ~/.microquery/token. No dependencies beyond Python stdlib. Reach for this when you need production data for research questions without standing up Postgres or writing scrapers. The agent variant exists for unattended cron jobs with USDC top-up.

tools
4
transport
STDIO
last updated
Apr 30, 2026

Tools

4 tools

Public tool metadata for what this MCP can expose to an agent.

queryRun SQL against a microquery dataset. Auto-registers on first call.

Run SQL against a microquery dataset. Auto-registers on first call.

No parameter schema in public metadata yet.

authenticateManually register or link a wallet address.

Manually register or link a wallet address.

No parameter schema in public metadata yet.

list_databasesShow all available datasets and field schemas.

Show all available datasets and field schemas.

No parameter schema in public metadata yet.

get_quickstartSneller SQL notes and multi-dataset example recipes.

Sneller SQL notes and multi-dataset example recipes.

No parameter schema in public metadata yet.

Sponsors

Readme

microquery-mcp

MCP server for Microquery — ask research questions about real-world data and get actual database records back. Works in Claude Desktop, Cursor, or any MCP-compatible AI host. Claude handles the SQL; you just ask the question.

No wallet required. Auto-registers on first query and runs on $0.10 trial credit (~1,600 typical queries).

See also

microquery-agent — autonomous agent for pipelines and cron jobs: register → deposit USDC → query → auto top-up. Use this if you want to run microquery unattended without an AI host.

Prerequisites

  • Python 3.9+
  • No third-party packages — stdlib only

Installation

Claude Desktop (recommended)

The easiest paths, in order of friction:

1. Registry install Find microquery in the Claude Desktop MCP marketplace or on smithery.ai and click Install. No config editing needed.

2. uvx install Add one entry to ~/Library/Application Support/Claude/claude_desktop_config.json (Mac) or %APPDATA%\Claude\claude_desktop_config.json (Windows):


View the full README on GitHub

Details

Repository
github.com/microqueryhq/microquery-mcp
Categories
Databases, Data & Analytics
Package
microquery-mcp
Transport
STDIO
Registry
MCP registry, active

Related Databases MCP servers

View all
1minaprotocol avatarMina Mcp Serverminaprotocol/mina-mcp-serverQuery Mina Protocol: accounts, blocks, transactions, zkApp events/actions, archive SQL, Rosetta.0stars
2mcpso avatarChatsummcpso/mcp-server-chatsumQueries and summarizes chat messages from a chat database via MCP to provide concise summaries and insights.1Kstars
3arben-adm avatarSequential Thinking Working Notesarben-adm/mcp-sequential-thinkingLocal working notes, decisions, evidence and resumable sessions with SQLite persistence.960stars
4domdomegg avatarAirtabledomdomegg/airtable-mcp-serverRead and write access to Airtable database schemas, tables, and records.456stars
5massive-com avatarMassive.commassive-com/mcp_massiveProvides access to Massive.com data via an MCP server with four composable tools and in-memory DataFrame storage for SQL queries and analytics.332stars
6slow-stack avatarMneme Memoryslow-stack/mnemeCross-session memory for AI coding agents via six tools; local-first SQLite store.211stars