Fabi Analyst Agent Mcp

创建者

Fabi.ai9 months ago

Fabi is a sophisticated analyst agent that independently handles data analysis tasks. Simply delegate tasks in natural language - Fabi will autonomously: - Discover and inspect schemas using RAG - Find relevant tables/columns with semantic understanding - Generate and validate SQL/Python code - Execute queries with error handling - Format and preview results

# Vibe analytics

# Analyst Agent

概览内容工具评论

内容

AI-native BI platform","creator":{"@type":"Organization","name":"Mintlify","url":"https://mintlify.com"}})||!a.startsWith("lang:"))\u0026\u0026(localStorage.removeItem(a),l--)}document.documentElement.setAttribute(d,k?"visible":"hidden")}catch(a){console.error(a),document.documentElement.setAttribute(d,"hidden")}})(\n {},\n "en",\n [],\n "data-banner-state",\n "bannerDismissed",\n)","id":"_mintlify-banner-script"}])

::before,*::after{-webkit-transition:none!important;-moz-transition:none!important;-o-transition:none!important;-ms-transition:none!important;transition:none!important}")),document.head.appendChild(a),function(){window.getComputedStyle(document.body),setTimeout(()=\u003e{document.head.removeChild(a)},1)}}();("requestAnimationFrame"in globalThis?requestAnimationFrame:setTimeout)(()=\u003e{let a;a=!1,a=window.scrollY\u003e50,document.getElementById(c)?.setAttribute("data-is-opaque",${!!a}),d()})})("mint")","id":"_mintlify-navbar-transition-script"}]))};\n (function(a){let b=[],c=0,d="undefined"==typeof ResizeObserver?null:new ResizeObserver(f);function e(){let c=Array.from(document.querySelectorAll("[id='navbar'], [data-top-chrome]"));(c.length!==b.length||c.some((a,c)=\u003ea!==b[c]))\u0026\u0026d\u0026\u0026(d.disconnect(),c.forEach(a=\u003ed.observe(a))),b=c,a()}function f(){c||(c=requestAnimationFrame(()=\u003e{c=0,e()}))}new MutationObserver(f).observe(document.documentElement,{childList:!0,subtree:!0}),window.addEventListener("resize",f),"loading"===document.readyState\u0026\u0026document.addEventListener("DOMContentLoaded",e),e()})(measure);\n (function(a){let b=window.location.hash.slice(1);if(!b)return;function c(){return"smooth"===getComputedStyle(document.documentElement).scrollBehavior}function d(c){let d=document.getElementById(b);return!!d\u0026\u0026(a(),d.scrollIntoView(c?{behavior:c}:void 0),!0)}if("complete"===document.readyState)return void d();let e=new MutationObserver(()=\u003e{!c()\u0026\u0026d("instant")\u0026\u0026f()});function f(){e.disconnect(),window.removeEventListener("load",g)}function g(){let a=c();f(),a\u0026\u0026requestAnimationFrame(()=\u003e{d(),function(){let a=["wheel","touchstart","keydown","pointerdown"],c=0,e=window.scrollY,f=setInterval(()=\u003e{c+=1;let a=document.getElementById(b);if(!a||c\u003e=6)return g();let f=Math.abs(window.scrollY-e)\u003e1;if(e=window.scrollY,f)return;let h=parseFloat(getComputedStyle(a).scrollMarginTop)||0;Math.abs(a.getBoundingClientRect().top-h)\u003e4\u0026\u0026d()},350);function g(){clearInterval(f),a.forEach(a=\u003ewindow.removeEventListener(a,g))}a.forEach(a=\u003ewindow.addEventListener(a,g,{passive:!0}))}()})}window.addEventListener("load",g),e.observe(document.documentElement,{childList:!0,subtree:!0}),!c()\u0026\u0026d("instant")\u0026\u0026f()})(measure);\n})();","id":"_mintlify-scroll-margin-script"}])

Getting started

Data analysis & reporting

Workflow automation

Collaboration & organization

Integrations & connectors

Advanced features & dev tools

Admin & configuration

var path = (window.location.pathname || '/').split('#')[0].split('?')[0];
if (path.endsWith('/index')) path = path.slice(0, -6);
else if (path === 'index') path = '';

var candidates = [];
if (path) candidates.push(path);
if (path.startsWith('/')) candidates.push(path.slice(1));
else candidates.push('/' + path);

var item = null;
for (var i = 0; i < candidates.length && !item; i++) {
  var matches = document.querySelectorAll('[id="' + candidates[i].replace(/"/g, '\\"') + '"]');
  for (var j = 0; j < matches.length; j++) {
    if (matches[j].closest('#sidebar, #sidebar-content')) {
      item = matches[j];
      break;
    }
  }
}
if (!item) return;

var parent = item.parentElement;
while (parent) {
  var style = getComputedStyle(parent);
  if (style.overflowY === 'auto' || style.overflowY === 'scroll') break;
  parent = parent.parentElement;
}
if (!parent) return;

var parentRect = parent.getBoundingClientRect();
var itemRect = item.getBoundingClientRect();
if (itemRect.top >= parentRect.top && itemRect.bottom <= parentRect.bottom) return;

var itemTopRelative = itemRect.top - parentRect.top + parent.scrollTop;
parent.scrollTop = itemTopRelative - parentRect.height / 2 + itemRect.height / 2;

} catch (e) {} })();

/* Dark mode: dot pattern with vignette */ [data-theme="dark"] body, [data-theme="dark"] html, [data-theme="dark"] #root, [data-theme="dark"] .main-content, [data-theme="dark"] main { background-color: #0f0f0f !important; background-image: radial-gradient(ellipse at center, transparent 0%, transparent 30%, rgba(15,15,15,0.5) 70%, rgba(15,15,15,1) 100%), radial-gradient(circle, #2a2a2a 0.5px, transparent 2px) !important; background-size: 100% 100%, 18px 18px !important; background-attachment: fixed !important; } </style><div class="flex flex-row-reverse gap-12 box-border w-full pt-40 lg:pt-10"><div class="hidden xl:flex self-start sticky xl:flex-col max-w-[28rem] z-21 h-[calc(100vh-8rem)] top-[6.5rem]" id="content-side-layout"><div class="z-10 hidden xl:flex box-border max-h-full pl-10 w-[19rem]" id="table-of-contents-layout"><div role="presentation" style="position:relative;--scroll-area-corner-height:0px;--scroll-area-corner-width:0px" data-component-part="scroll-area" id="table-of-contents" class="min-w-0 text-gray-600 text-sm leading-6 w-[16.5rem] -mt-10"><div role="presentation" data-id="base-ui-_R_bd7av5tccsnisnpfiulb_-viewport" tabindex="-1" class="size-full rounded-[inherit] [--scroll-area-fade-size:32px] pt-10 pb-4 base-ui-disable-scrollbar" style="overflow:scroll" data-component-part="scroll-area-viewport"><div role="presentation" style="min-width:fit-content" data-component-part="scroll-area-content" class="min-w-0! w-full space-y-2"><nav aria-labelledby="_R_3d7av5tccsnisnpfiulb_"><h2 id="_R_3d7av5tccsnisnpfiulb_" class="m-0 font-normal"><button type="button" class="text-gray-700 dark:text-gray-300 font-medium flex items-center space-x-2 hover:text-gray-900 dark:hover:text-gray-100 transition-colors cursor-pointer"><svg xmlns="http://www.w3.org/2000/svg" width="18" height="18" viewBox="0 0 18 18" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true" class="size-3 shrink-0"><path d="M2.75 14.25H15.25" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path><path d="M2.75 3.75H15.25" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path><path d="M2.75 9H8.25" stroke="currentColor" width="1.5" linecap="round" linejoin="round"></path></svg><span>On this page</span></button></h2><div><ul id="table-of-contents-content" class="toc"><li class="toc-item relative" data-depth="0"><a href="#overview" class="break-words py-1 block dark:text-gray-400 [li:not([data-active])>&:hover]:text-gray-900 dark:[li:not([data-active])>&:hover]:text-gray-300 [[data-active]>&]:text-primary dark:[[data-active]>&]:text-primary-light [[data-active]>&]:[text-shadow:-0.15px_0_0_currentColor,0.15px_0_0_currentColor]">Overview</a></li><li class="toc-item relative" data-depth="0"><a href="#authentication" class="break-words py-1 block dark:text-gray-400 [li:not([data-active])>&:hover]:text-gray-900 dark:[li:not([data-active])>&:hover]:text-gray-300 [[data-active]>&]:text-primary dark:[[data-active]>&]:text-primary-light [[data-active]>&]:[text-shadow:-0.15px_0_0_currentColor,0.15px_0_0_currentColor]">Authentication</a></li><li class="toc-item relative" data-depth="0"><a href="#token-authentication" class="break-words py-1 block dark:text-gray-400 [li:not([data-active])>&:hover]:text-gray-900 dark:[li:not([data-active])>&:hover]:text-gray-300 [[data-active]>&]:text-primary dark:[[data-active]>&]:text-primary-light [[data-active]>&]:[text-shadow:-0.15px_0_0_currentColor,0.15px_0_0_currentColor]">Token authentication</a></li><li class="toc-item relative" data-depth="0"><a href="#oauth-authentication" class="break-words py-1 block dark:text-gray-400 [li:not([data-active])>&:hover]:text-gray-900 dark:[li:not([data-active])>&:hover]:text-gray-300 [[data-active]>&]:text-primary dark:[[data-active]>&]:text-primary-light [[data-active]>&]:[text-shadow:-0.15px_0_0_currentColor,0.15px_0_0_currentColor]">OAuth authentication</a></li><li class="toc-item relative" data-depth="0"><a href="#configuration" class="break-words py-1 block dark:text-gray-400 [li:not([data-active])>&:hover]:text-gray-900 dark:[li:not([data-active])>&:hover]:text-gray-300 [[data-active]>&]:text-primary dark:[[data-active]>&]:text-primary-light [[data-active]>&]:[text-shadow:-0.15px_0_0_currentColor,0.15px_0_0_currentColor]">Configuration</a></li><li class="toc-item relative" data-depth="0"><a href="#available-tools" class="break-words py-1 block dark:text-gray-400 [li:not([data-active])>&:hover]:text-gray-900 dark:[li:not([data-active])>&:hover]:text-gray-300 [[data-active]>&]:text-primary dark:[[data-active]>&]:text-primary-light [[data-active]>&]:[text-shadow:-0.15px_0_0_currentColor,0.15px_0_0_currentColor]">Available tools</a></li><li class="toc-item relative" data-depth="0"><a href="#create-a-thread" class="break-words py-1 block dark:text-gray-400 [li:not([data-active])>&:hover]:text-gray-900 dark:[li:not([data-active])>&:hover]:text-gray-300 [[data-active]>&]:text-primary dark:[[data-active]>&]:text-primary-light [[data-active]>&]:[text-shadow:-0.15px_0_0_currentColor,0.15px_0_0_currentColor]">Create a thread</a></li><li class="toc-item relative" data-depth="0"><a href="#submit-chat" class="break-words py-1 block dark:text-gray-400 [li:not([data-active])>&:hover]:text-gray-900 dark:[li:not([data-active])>&:hover]:text-gray-300 [[data-active]>&]:text-primary dark:[[data-active]>&]:text-primary-light [[data-active]>&]:[text-shadow:-0.15px_0_0_currentColor,0.15px_0_0_currentColor]">Submit chat</a></li><li class="toc-item relative" data-depth="0"><a href="#get-chat-result" class="break-words py-1 block dark:text-gray-400 [li:not([data-active])>&:hover]:text-gray-900 dark:[li:not([data-active])>&:hover]:text-gray-300 [[data-active]>&]:text-primary dark:[[data-active]>&]:text-primary-light [[data-active]>&]:[text-shadow:-0.15px_0_0_currentColor,0.15px_0_0_currentColor]">Get chat result</a></li><li class="toc-item relative" data-depth="0"><a href="#save-to-smartbook" class="break-words py-1 block dark:text-gray-400 [li:not([data-active])>&:hover]:text-gray-900 dark:[li:not([data-active])>&:hover]:text-gray-300 [[data-active]>&]:text-primary dark:[[data-active]>&]:text-primary-light [[data-active]>&]:[text-shadow:-0.15px_0_0_currentColor,0.15px_0_0_currentColor]">Save to Smartbook</a></li><li class="toc-item relative" data-depth="0"><a href="#usage-examples" class="break-words py-1 block dark:text-gray-400 [li:not([data-active])>&:hover]:text-gray-900 dark:[li:not([data-active])>&:hover]:text-gray-300 [[data-active]>&]:text-primary dark:[[data-active]>&]:text-primary-light [[data-active]>&]:[text-shadow:-0.15px_0_0_currentColor,0.15px_0_0_currentColor]">Usage examples</a></li><li class="toc-item relative" data-depth="0"><a href="#basic-workflow" class="break-words py-1 block dark:text-gray-400 [li:not([data-active])>&:hover]:text-gray-900 dark:[li:not([data-active])>&:hover]:text-gray-300 [[data-active]>&]:text-primary dark:[[data-active]>&]:text-primary-light [[data-active]>&]:[text-shadow:-0.15px_0_0_currentColor,0.15px_0_0_currentColor]">Basic workflow</a></li><li class="toc-item relative" data-depth="0"><a href="#example-analyzing-sales-data" class="break-words py-1 block dark:text-gray-400 [li:not([data-active])>&:hover]:text-gray-900 dark:[li:not([data-active])>&:hover]:text-gray-300 [[data-active]>&]:text-primary dark:[[data-active]>&]:text-primary-light [[data-active]>&]:[text-shadow:-0.15px_0_0_currentColor,0.15px_0_0_currentColor]">Example: Analyzing sales data</a></li><li class="toc-item relative" data-depth="0"><a href="#troubleshooting" class="break-words py-1 block dark:text-gray-400 [li:not([data-active])>&:hover]:text-gray-900 dark:[li:not([data-active])>&:hover]:text-gray-300 [[data-active]>&]:text-primary dark:[[data-active]>&]:text-primary-light [[data-active]>&]:[text-shadow:-0.15px_0_0_currentColor,0.15px_0_0_currentColor]">Troubleshooting</a></li><li class="toc-item relative" data-depth="0"><a href="#best-practices" class="break-words py-1 block dark:text-gray-400 [li:not([data-active])>&:hover]:text-gray-900 dark:[li:not([data-active])>&:hover]:text-gray-300 [[data-active]>&]:text-primary dark:[[data-active]>&]:text-primary-light [[data-active]>&]:[text-shadow:-0.15px_0_0_currentColor,0.15px_0_0_currentColor]">Best practices</a></li><li class="toc-item relative" data-depth="0"><a href="#token-security" class="break-words py-1 block dark:text-gray-400 [li:not([data-active])>&:hover]:text-gray-900 dark:[li:not([data-active])>&:hover]:text-gray-300 [[data-active]>&]:text-primary dark:[[data-active]>&]:text-primary-light [[data-active]>&]:[text-shadow:-0.15px_0_0_currentColor,0.15px_0_0_currentColor]">Token security</a></li><li class="toc-item relative" data-depth="0"><a href="#error-handling" class="break-words py-1 block dark:text-gray-400 [li:not([data-active])>&:hover]:text-gray-900 dark:[li:not([data-active])>&:hover]:text-gray-300 [[data-active]>&]:text-primary dark:[[data-active]>&]:text-primary-light [[data-active]>&]:[text-shadow:-0.15px_0_0_currentColor,0.15px_0_0_currentColor]">Error handling</a></li><li class="toc-item relative" data-depth="0"><a href="#performance" class="break-words py-1 block dark:text-gray-400 [li:not([data-active])>&:hover]:text-gray-900 dark:[li:not([data-active])>&:hover]:text-gray-300 [[data-active]>&]:text-primary dark:[[data-active]>&]:text-primary-light [[data-active]>&]:[text-shadow:-0.15px_0_0_currentColor,0.15px_0_0_currentColor]">Performance</a></li></ul></div></nav></div></div></div></div></div><div class="relative grow box-border flex-col w-full mx-auto px-1 lg:pl-[5.7rem] lg:-ml-12 xl:w-[calc(100%-28rem)]" id="content-area"><header id="header" class="relative leading-none @container/page-header"><div class="mt-0.5 space-y-2.5"><div class="eyebrow h-5 text-primary dark:text-primary-light text-sm font-semibold">Advanced features & dev tools</div><div class="flex flex-col sm:flex-row items-start sm:items-center relative gap-2 min-w-0"><h1 id="page-title" class="text-3xl sm:text-4xl text-gray-900 tracking-tight dark:text-gray-200 [overflow-wrap:anywhere] font-semibold">MCP Server</h1></div></div><div class="mt-2 text-lg prose prose-gray dark:prose-invert [&>*]:[overflow-wrap:anywhere]"><p>Connect to Fabi through the Model Context Protocol (MCP) server

Overview

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.

Authentication

The Fabi MCP server supports two authentication methods:

Token authentication

Token authentication is the recommended method for programmatic access. You can generate MCP tokens from your Fabi.ai settings:

Navigate to https://app.fabi.ai/settings/mcp
Generate a new MCP token
Copy the token securely - it will only be shown once

OAuth authentication

OAuth authentication is also supported for user-based integrations. Follow the OAuth flow to authenticate your application and use the following URL: https://app.fabi.ai/mcp

Configuration

To connect to the Fabi MCP server, add the following configuration to your MCP client settings:

{
  "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.

Available tools

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

Create a thread

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. Parameters:

title (optional): Title for the analysis session

Returns: Thread UUID for subsequent operations

Submit chat

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. Parameters:

thread_uuid: UUID of the thread from create_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

Get chat result

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

request_uuid: UUID of the chat request (returned by submit_chat)

Returns: Processing status or completed results with data preview

Save to Smartbook

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. Parameters:

thread_uuid: UUID of the thread to save

Returns: Confirmation of saved Smartbook cells

Usage examples

Basic workflow

Create a thread to start a new analysis session
Submit chat requests with natural language queries
Get chat results to retrieve analysis outputs
Save to Smartbook (optional) to persist results for sharing

Example: Analyzing sales data

// 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
});

Troubleshooting

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

Best practices

Token security

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

Error handling

Implement retry logic for get_chat_result when status is “processing”
Handle timeout scenarios gracefully
Validate thread UUIDs before making subsequent calls

Performance

Use context_cell_uuids and context_dataframes to build on previous analyses
Only call save_to_smartbook when you need to persist results
Batch related queries in the same thread for better context

服务器配置

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

Visual Studio Code - Open Source ("Code - OSS")Visual Studio Code

EdgeOne Pages MCPAn MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.

MCP AdvisorMCP Advisor & Installation - Use the right MCP server for your needs

ChatWiseThe second fastest AI chatbot™

MiniMax MCPOfficial MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.

Serper MCP ServerA Serper MCP Server

Playwright McpPlaywright MCP server

Y GuiA web-based graphical interface for AI chat interactions with support for multiple AI models and MCP (Model Context Protocol) servers.

Tavily Mcp

AiimagemultistyleA Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.

Howtocook Mcp基于Anduin2017 / HowToCook （程序员在家做饭指南）的mcp server，帮你推荐菜谱、规划膳食，解决“今天吃什么“的世纪难题； Based on Anduin2017/HowToCook (Programmer's Guide to Cooking at Home), MCP Server helps you recommend recipes, plan meals, and solve the century old problem of "what to eat today"

Jina AI MCP ToolsA Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.