Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@MCP Docs Server How do I publish a package with uv on GitLab?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A small Python project that exposes a FastMCP tool for fetching documentation from supported libraries and returning clean, readable text. The project includes a sample client that connects to the server, calls the tool, and uses Groq to answer the user's question using the retrieved documentation as context.
Runs an MCP server with the get_docs tool
Searches the web through the Serper API
Fetches documentation pages and strips HTML into readable text
Supports these libraries:
langchain
llama-index
openai
uv
Provides a sample client for interacting with the server
Related MCP server: DOC-Intelligence-MCP-SERVER
mcp_server.py — MCP server and documentation-fetching tool
client.py — example client that connects to the MCP server
utils.py — HTML cleanup and LLM response helpers
pyproject.toml — Python dependencies and project metadata
.env — local environment variables for API keys
README.md — project documentation
Python 3.13+
uv package manager
Install dependencies:
uv syncCreate a .env file in the project root and add your API keys:
SERPER_API_KEY=your_serper_api_key_here
GROQ_API_KEY=your_groq_api_key_hereRun the MCP server:
uv run mcp_server.pyRun the example client:
uv run client.pyThe client currently asks:
How to use publish a package with uv on gitlab?
Library: uv
The server will search documentation for the selected library, collect sources, and return the extracted content for the client to use as context.
The .env file is meant for local development only and should not be committed to GitHub.
The project uses the FastMCP library, httpx, python-dotenv, trafilatura, and groq.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | ||
| library | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0get_docsScored across 1 tool
With only one tool, there is no possibility of ambiguity or overlapping purposes. The single tool is trivially distinct.
The only tool name 'get_docs' follows a clear verb_noun convention. Consistency is trivially maintained with a single tool.
A single tool feels thin for a documentation server, but it is at the low end of borderline. The count is not egregious but likely insufficient for a full-featured docs experience.
The tool name suggests retrieving documentation, but there is no listing, searching, or other navigation capability. This creates significant gaps for a docs server, and the lack of a description makes the surface even more unclear.
Search and read Rust documentation for the standard library and any crate on crates.io
Search and read Vector Panda docs: API operations, pricing, storage tiers, measured benchmarks.
Versioned documentation registry and semantic search for AI tools and coding assistants.
Retrieve information from the Medusa documentation to assist you with your Medusa development.
