create-queryLABSCO SUMMARY
Your documentation, made answerable.
The generated service description is the clever part of the setup step: it reads what you dropped in and writes the summary the tool descriptions use, so the assistant's own advertisement of itself matches your API rather than a generic template. Because everything routes through Claude, the answers cost tokens on your key on every call.
What it is
An MCP server that reads a folder of your own documentation and turns it into two assistants: one that answers questions about the API, and one that turns a plain-language request into a query against it. Claude does the reasoning, and the prompts that steer it are files you can edit rather than behaviour baked into the code.
What you get
create-query— hand it arequestin plain language and get back a query written against your documented APIdocumentation— ask a question and get the answer drawn from the documentation you supplied- A
docs/directory you fill with.txt,.mdor.jsonfiles, which is the entire knowledge source - Editable prompts under
prompts/—system-prompt.txtfor the main instruction,tool-metadata.txtfor how the tools describe themselves,query-metadata.txtfor query generation, and aservice-description.txtgenerated during setup
Requirements
An Anthropic API key, supplied as ANTHROPIC_API_KEY. Node.js 18 or higher; from a clone, npm install, npm run build and then npm run setup, which creates the docs/ and prompts/ directories, writes default prompt files and generates the service description. Add your documentation to docs/ before use. The client entry points at build/index.js with the key in the env block, over stdio, and absolute paths are required.
Setup effort
Build from source — git clone https://github.com/crazyrabbitLTC/mcp-expert-server.git
USE CASES
01
Answering a question about an internal API
Ask how authentication works or what an endpoint returns and get the answer from your own docs rather than the model's memory.
02
Getting a first draft of a query
Describe what you want in a sentence and receive a query written against the documented interface.
03
Tuning how the assistant behaves
Edit the system prompt and query metadata files rather than changing code when the answers are the wrong shape.
2 tools
Listed in project docs. Your client may show a different list.
documentationBEFORE YOU INSTALL
What to know first
Tools you get
2 tools named in the project's documentation.
Requires
- Node.js >= 18
- ANTHROPIC_API_KEY in your environment
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
You clone and build this one yourself.
Server setup
TERMINAL
git clone https://github.com/crazyrabbitLTC/mcp-expert-server.git
cd mcp-expert-server
npm installCreate a .env file in the project folder containing ANTHROPIC_API_KEY=<YOUR_ANTHROPIC_API_KEY>
TERMINAL
npm run build
npm run setupAdd your API documentation files (.txt, .md or .json) to the docs/ directory
MCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"expert": {
"command": "node",
"args": [
"<YOUR_PATH_TO_MCP_EXPERT_SERVER>/build/index.js"
],
"env": {
"ANTHROPIC_API_KEY": "<YOUR_ANTHROPIC_API_KEY>"
}
}
}
}
