mcpField
F
FactQL

FactQL

Remote
factql.aiData & Analytics0Updated 1d ago

About FactQL

FactQL is an MCP server for developers building AI applications and internal tools around real data. It verifies answers and returns the executed query, result rows, and lineage, declining when it cannot verify a result.

Key features

  1. 01Verified answers from connected data
  2. 02Executed SQL included with answers
  3. 03Returned rows and data lineage
  4. 04Clarification and decline results
  5. 05SELECT-only queries with timeouts

Use cases

  1. 01Answering questions over business databases
  2. 02Querying uploaded CSV and XLSX files
  3. 03Providing cited answers from PDFs
  4. 04Adding data-backed answers to MCP clients

MCP support

FactQL exposes `whoami` and `ask` tools to MCP clients, including Claude Desktop, Claude Code, and Cursor. It can run as a hosted remote server or locally with an API key.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://api.factql.ai/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Packages
pypifactql-mcp0.1.2

Tools

Details

From the project README

factql-mcp

FactQL is the harness around the model.

Ask a question about your data. FactQL runs the query, checks the result before you see an answer, and declines instead of guessing when it can't verify.

Every answer ships with the query that ran, the rows it returned and the lineage behind it. One API call. Works with Postgres, MySQL, DuckDB, uploaded CSV and XLSX files, and PDFs with cited answers.

Built for developers putting AI near real data: AI apps, agents and internal tools that can't afford a confident wrong number.

This package is FactQL's MCP server: it brings those answers into Claude Desktop, Claude Code, Cursor, or any MCP client. Learn more at factql.ai.

Hosted server (no install)

FactQL also runs this server for you at:

https://api.factql.ai/mcp

Add it as a remote (Streamable HTTP) MCP server in Claude (Settings → Connectors → Add custom connector; works on web, desktop and mobile), Claude Code (claude mcp add --transport http factql https://api.factql.ai/mcp), Cursor, VS Code, or any app that supports remote MCP. The app opens a FactQL sign-in page; click Allow and its questions run as you. Disconnect under Settings → Connected apps on factql.ai. Apps that can't sign in can send an API key as Authorization: Bearer fl_live_... instead.

Setup for each app: docs.factql.ai/guides/mcp.

The rest of this README is for running the server yourself.

Get a key

Sign up free at factql.ai/signup, connect your data, and create an API key. An ask-only key is enough for this server.

Install

uvx factql-mcp

or pip install factql-mcp.

Configure

VariableRequiredDefault
FACTQL_API_KEYyes— your FactQL API key (an ask-only key is enough)
FACTQL_BASE_URLnohttps://api.factql.ai
FACTQL_WORKSPACE_IDnodefault workspace, for tenants that use workspaces
FACTQL_END_USER_IDnomcp:<os user>
Claude Desktop / Cursor (mcpServers)
{
  "mcpServers": {
    "factql": {
      "command": "uvx",
      "args": ["factql-mcp"],
      "env": { "FACTQL_API_KEY": "fl_live_..." }
    }
  }
}
Claude Code
claude mcp add factql -e FACTQL_API_KEY=fl_live_... -- uvx factql-mcp

Tools

  • whoami() — the tenant, plan, and workspaces this key can query.
  • ask(question, workspace_id?, locale?) — the answer, the SQL that ran, and up to 50 rows. A needs_clarification result means the question was too vague; ask the user and call again with the detail. A declined result means FactQL couldn't verify an answer and gave none rather than guess; the reason says why. locale is en-GB or en-US.

Each ask is stateless: the MCP client carries the conversation, so a follow-up should restate what it refers to.

Safety

FactQL only runs SELECT queries, under a statement timeout, and only against the tables your admin has enabled. The key's permissions decide what it can see; this server adds nothing on top.

Development

uv run --with pytest pytest -q

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.