Fabi Analyst Agent MCP

Fabi MCP is an autonomous agent that handles end-to-end data analysis tasks from natural language requests, automatically discovering data schemas, generating sql or python code, executing queries, and presenting insights.

Connect to Fabi through the Model Context Protocol (MCP) server

Fabi.ai provides an MCP (Model Context Protocol) server that allows you to integrate Fabi's AI data analysis capabilities directly into your development workflow or your client/interface of choice. The MCP server enables AI assistants and development tools to interact with Fabi.ai, creating threads, submitting chat requests, and saving Smartbooks programmatically.

The Fabi MCP server is the single fastest way for you to implement an AI assistant to chat directly with your data.

The Fabi MCP server supports two authentication methods:

Token authentication is the recommended method for programmatic access. You can generate MCP tokens from your Fabi.ai settings:
- Navigate tohttps://app.fabi.ai/settings/mcp
- Generate a new MCP token
- Copy the token securely - it will only be shown once

{ "mcpServers": { "fabi": { "command": "npx", "args": [ "mcp-remote", "https://app.fabi.ai/mcp", "--header", "Authorization: Bearer <your-fabi-mcp-token>" ] } } }

Replace<your-fabi-mcp-token>with the token you generated from the settings page.

The Fabi MCP server provides the following tools for interacting with Fabi.ai:

Creates a new data analysis session (backed by a Smartbook) for SQL/Python queries. Used to start analyzing database tables, running queries, or exploring data. The thread will persist your analysis history and generated code.

- title(optional): Title for the analysis session

Returns:Thread UUID for subsequent operations

Delegate a data analysis task to the Fabi autonomous agent. Takes a description of what you want in natural language - Fabi will independently handle all complexity: discovering data sources, using RAG to find relevant table/column schemas and semantics, generating SQL/Python code, validating queries with dry runs, executing them, and formatting results.

- thread_uuid: UUID of the thread fromcreate_thread
- message: Natural language data analysis request (e.g., 'show top 10 customers by revenue')
- context_cell_uuids(optional): Previous cell UUIDs to reference in this analysis
- context_dataframes(optional): Variable names of dataframes to use as context

Returns:Request UUID and initial status

Poll for the result of a long-running chat analysis request. Used by the agent whensubmit_chatreturns early due to timeout (after 45 seconds). The chat continues processing in the background - call this periodically to check if results are ready.

- request_uuid: UUID of the chat request (returned bysubmit_chat)

Returns:Processing status or completed results with data preview

Save AI-generated cells from chat history to the Smartbook for dashboard publishing or collaboration. Used by the agent to persist, publish, or share the analysis as a dashboard. This accepts pending chat results and converts them into executable Smartbook cells. Regular analyses are already viewable in chat history and don't need saving.

- thread_uuid: UUID of the thread to save

Returns:Confirmation of saved Smartbook cells
- Create a threadto start a new analysis session
- Submit chat requestswith natural language queries
- Get chat resultsto retrieve analysis outputs
- Save to Smartbook(optional) to persist results for sharing

// 1. Create a new thread const thread = await mcp.callTool('fabi', 'create_thread', { title: 'Sales Analysis Q4 2024' }); // 2. Submit an analysis request const request = await mcp.callTool('fabi', 'submit_chat', { thread_uuid: thread.uuid, message: 'Show top 10 customers by revenue in Q4 2024' }); // 3. Get the results const results = await mcp.callTool('fabi', 'get_chat_result', { request_uuid: request.uuid }); // 4. Save to Smartbook for sharing await mcp.callTool('fabi', 'save_to_smartbook', { thread_uuid: thread.uuid });

- First try using the AI Analyst Agent in the Fabi UI to ensure it works as expected. If it does then
- If using token-based authentication, make sure you're using a valid token
- If using a local agent, restart the agent after configuring the tools

- Store MCP tokens securely and never commit them to version control
- Use environment variables or secure secret management
- Rotate tokens regularly for enhanced security
- Each token should only be used by one application or user

- Implement retry logic forget_chat_resultwhen status is "processing"
- Handle timeout scenarios gracefully
- Validate thread UUIDs before making subsequent calls

- Usecontext_cell_uuidsandcontext_dataframesto build on previous analyses
- Only callsave_to_smartbookwhen you need to persist results
- Batch related queries in the same thread for better context

Postgres skills and documentation to help AI coding tools generate better PostgreSQL code.

Build custom MCP tools on any datasource and ship them to any agent builder from one control plane—using only SQL and a secure link.

The Xata MCP server lets AI assistants and agents interact with your Xata organizations, projects, and Postgres database branches.

Hosted MCP server for live sports data — scores, analytics, schedules, standings, multi-book odds, team form, head-to-head, model predictions, and pre-generated matchup analysis across 1,000+ leagues in 150+ countries. Free tier, no card.

A secure MCP server that connects AI agents to CloudBeaver web client, allowing them to explore database schemas, read metadata, and execute SQL queries.

Real-time company and people intelligence for AI agents

An enterprise-ready system to archive AI conversations from ChatGPT and Claude into a Supabase database.

MCP server for Apache AGE graph databases on PostgreSQL. 21 MCP tools — the most comprehensive Apache AGE MCP server (graph CRUD, Cypher queries, batch transactions, semantic search, Graph RAG, vis.js visualization, export/import) - F#/.NET — the only non-Python Apache AGE MCP server, installs as a single dotnet tool - Production-grade — BenchmarkDotNet-verified performance (cached queries in 62 ns, Cypher in 1 ms) - Open source — MIT license, published on NuGet - Documentation — full docs site at neftedollar.com/age-mcp

Local semantic search over documents (txt, md, pdf, docx, pptx, csv). Fully offline, multilingual, hybrid vector + keyword search via LanceDB. No API keys, no cloud.

A local MCP server that gives Claude Code, Cursor and Codex read access to your DynamoDB schema and items, with every write staged for human review.