{
  "markdown": "# microquery-mcp\n\n<!-- mcp-name: io.github.microqueryhq/microquery-mcp -->\n\nMCP server for [Microquery](https://microquery.dev) — ask research questions\nabout real-world data and get actual database records back. Works in Claude\nDesktop, Cursor, or any MCP-compatible AI host. Claude handles the SQL; you just\nask the question.\n\nNo wallet required. Auto-registers on first query and runs on $0.10 trial credit\n(~1,600 typical queries).\n\n## See also\n\n[microquery-agent](https://github.com/microqueryhq/microquery-agent) —\nautonomous agent for pipelines and cron jobs: register → deposit USDC → query →\nauto top-up. Use this if you want to run microquery unattended without an AI\nhost.\n\n## Prerequisites\n\n- Python 3.9+\n- No third-party packages — stdlib only\n\n## Installation\n\n### Claude Desktop (recommended)\n\nThe easiest paths, in order of friction:\n\n**1. Registry install** Find microquery in the Claude Desktop MCP marketplace or\non [smithery.ai](https://smithery.ai) and click Install. No config editing\nneeded.\n\n**2. `uvx` install** Add one entry to\n`~/Library/Application Support/Claude/claude_desktop_config.json` (Mac) or\n`%APPDATA%\\Claude\\claude_desktop_config.json` (Windows):\n\n```json\n{\n  \"mcpServers\": {\n    \"microquery\": {\n      \"command\": \"uvx\",\n      \"args\": [\"microquery-mcp\"]\n    }\n  }\n}\n```\n\n`uvx` requires `uv` to be installed separately\n([astral.sh/uv](https://astral.sh/uv)). Once installed, Claude Desktop will pick\nit up automatically.\n\n**3. Manual install** *(developers)* Download `microquery_mcp.py` from this repo\nand point your host at it:\n\n```json\n{\n  \"mcpServers\": {\n    \"microquery\": {\n      \"command\": \"python3\",\n      \"args\": [\"/path/to/microquery_mcp.py\"]\n    }\n  }\n}\n```\n\nRestart Claude Desktop after editing. The server appears in **Settings →\nDeveloper** with a green dot when connected.\n\n### Other MCP hosts (Cursor, etc.)\n\nUse the same `command` / `args` pattern above. Consult your host's MCP\ndocumentation for the exact config format.\n\n## Tools\n\n| Tool                               | Description                                                         |\n| ---------------------------------- | ------------------------------------------------------------------- |\n| `query(database, sql)`             | Run SQL against a microquery dataset. Auto-registers on first call. |\n| `authenticate(name, wallet_addr?)` | Manually register or link a wallet address.                         |\n| `list_databases()`                 | Show all available datasets and field schemas.                      |\n| `get_quickstart()`                 | Sneller SQL notes and multi-dataset example recipes.                |\n\n## How it works\n\n1. On the first `query()` call the server registers an account using your OS\n   username (`getpass.getuser()`) via `POST /v1/register` and stores the API key\n   in `~/.microquery/token`.\n1. Subsequent calls use the stored key — no configuration needed.\n1. The new account starts with 100,000 µUSDC ($0.10) trial credit, covering\n   roughly 1,600 typical queries.\n1. When trial credit runs low the server automatically tops up the account (up\n   to 10 times, $2 each). Once the free allowance is exhausted a checkout URL is\n   returned — visit it to add USDC and continue querying.\n\n## Available datasets\n\nFDA adverse events · SEC EDGAR · clinical trials · ClinVar · arXiv · PubMed ·\nEthereum · Bitcoin · Base · DeFi TVL · FEC contributions · FRED economic series\n· NVD/CVE · OSV advisories · sanctions · FHFA house prices · GWAS · ClinPGx ·\nmalware samples · open food facts · world bank commodities · and more — call\n`list_databases()` for the full live schema.\n\n## Example\n\n```\nUser:    What were the top adverse events reported for metformin last year?\n         And how does that compare to 2022 and 2023?\nClaude:  [queries fda.faers for each year, builds trend table]\n         GI events (diarrhoea, nausea, vomiting) were flat 2022→2024,\n         then spiked sharply in 2025 — consistent with the longevity/\n         obesity wave hitting FAERS with a lag. Lactic acidosis stayed\n         nearly flat across all four years despite overall volume growth.\n\nUser:    Can you cross-reference that with genomic profiles?\nClaude:  [queries clinpgx, clinvar, gwas — no SQL needed from user]\n         SLC22A1 rs628031 has a direct ClinPGx annotation for GI toxicity —\n         the strongest known genomic explanation for why diarrhoea and nausea\n         dominate the FAERS signal for metformin.\n```\n",
  "bytes": 4453,
  "sha": "9cb7b900145030a6007b4b2a1f988dc42018031fa6f2c29529054fe6e3f1f38f",
  "repo_slug": "microqueryhq/microquery-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_microqueryhq_microquery_mcp_c7d5c913/readme"
}