query_docs
Query the document Q&A system with a prompt
LABSCO SUMMARY
The flow does the work; this is the doorway.
Everything that determines answer quality — which documents are loaded, how they are chunked, which model reads them — is configured in Langflow, not here. That is the appeal: you can rebuild the retrieval pipeline visually and the MCP side does not change. It also means the server is only as useful as the flow behind it, and API_ENDPOINT is the one setting that decides which flow that is.
What it is
A thin MCP server that forwards a question to a Langflow flow and returns the answer. The retrieval, the documents and the model all live in your Langflow instance; this makes that flow reachable from any MCP client as a single tool.
What you get
- A question sent to your Langflow Document Q&A flow, with the flow's response returned to the model —
query_docs - The flow chosen by configuration rather than by argument:
API_ENDPOINTnames which flow answers, so pointing at a different set of documents is a config change, not a code change
Requirements
A running Langflow instance with a flow built from its Document Q&A template — chat input, file upload and an LLM component — and that flow's API endpoint URL, which Langflow shows behind the API button as a cURL command. Put that URL in API_ENDPOINT; it defaults to a local Langflow address with a placeholder flow id, so it must be set to reach your own flow. The npm package name is doc-qa-server (0.1.0) and it is marked private, so nothing is on the npm registry: the client block runs it straight from the GitHub repository with npx -y github:GongRzhe/Langflow-DOC-QA-SERVER. The README's own routes are a clone built with npm install and npm run build, or the Smithery installer.
Setup effort
One command — npx -y github:GongRzhe/Langflow-DOC-QA-SERVER
USE CASES
01
Asking your own documents a question from a chat client
Point the server at a Langflow flow loaded with your files and query it in conversation, without opening Langflow.
02
Reusing a retrieval pipeline you already built
Expose an existing Document Q&A flow to any MCP client instead of rebuilding the same retrieval logic inside a new server.
03
Switching which corpus answers
Change API_ENDPOINT to a different flow id to move between document sets, keeping the same tool and the same client configuration shape.
1 tool
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
BEFORE YOU INSTALL
What to know first
Tools you get
1 tool when we connected.
Requires
- npx on PATH
- API_ENDPOINT set to your Langflow flow's API URL
CONTEXT COST
Light Standing cost
Rated by the size of the one tool definition that rides along on every turn
INSTALLATION
Connect your client
Add the block to your client, or run the command directly.
Server setup
Configuration file
JSON
{
"mcpServers": {
"Langflow-DOC-QA-SERVER": {
"command": "npx",
"args": [
"-y",
"github:GongRzhe/Langflow-DOC-QA-SERVER"
],
"env": {
"API_ENDPOINT": "http://127.0.0.1:7860/api/v1/run/<YOUR_FLOW_ID>?stream=false"
}
}
}
}Set API_ENDPOINT to your own flow's API endpoint — the URL in the cURL command behind the API button of your Document Q&A flow in Langflow.
npx
TERMINAL
npx -y github:GongRzhe/Langflow-DOC-QA-SERVER
