mcp-server

FastGPT: Easy QA Systems

Get easy question-answering systems with FastGPT, a knowledge-based platform for founders
intermediate30 minutes💵 Free
29,371 stars7,264 forksTypeScriptGuide quality 8/10Updated 8/17/2026100% free · open source
What it is

Use FastGPT to create question-answering systems without much setup.

Real use case example

"A founder wants to create an onboarding flow for new website users. They use FastGPT to build an automated question-answering system that responds to FAQs. After 30 minutes of setup, their users can quickly find answers to basic questions, freeing up the founder to work on more advanced features."

Best insideClaude DesktopCursor
When to use it
  • You need to build a chatbot that can answer a wide range of user questions
  • You want to automate customer support with a question-answering system
  • You need to integrate a knowledge-based platform into your existing application
Ready-to-paste prompt
Use the command `fastgpt ask -q 'What is the capital of France?'` to test the question-answering system
Heads up: Make sure you have the required Node.js version (14 or higher) and Python version (3.8 or higher) installed, as FastGPT relies on these to function properly
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/fastgpt && curl -fsSL https://workflowstacks.com/api/skills/fastgpt/claude-skill -o ~/.claude/skills/fastgpt/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How FastGPT: Easy QA Systems works
Codeflow
Free to inspect

FastGPT: Easy QA Systems is a very large TypeScript project (~410k lines across 3144 code files, plus 824 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, Other license, has a test suite.

Size
Very large codebase
~410k lines · 3144 code files · days to read — use, don't read
Setup
Developer setup
A real software project. Use it via its install path; don't expect to read it all.
Runs on
Node.js
No API keys detected
TypeScript 89%MDX 9%Rust 1%JavaScript 1%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    AGENTS.md
    The instructions the AI actually follows
  3. 3
    bin/fastgpt-v1.0.0-helm.tgz
    Where the program starts running
  4. 4
    package.json
    Dependencies and the commands it exposes
What's in each folder
packages/Sub-packages / plugins2603 files
bin/Command-line entry points1 files
projects/Folder1935 files
document/Folder1077 files
sdk/SDKs / client libraries131 files
deploy/Deployment / infrastructure26 files
scripts/Helper scripts8 files
.agents/Tool / agent settings104 files
READMEHas testsDocumentedCI checksOther licenseUpdated this month
Quick Actions
Details
Creator
labring
Language
TypeScript
Category
mcp-server
Published
2/23/2023

Are you the creator of this tool? Claim your listing → and earn 85% of every sale.