fetchLABSCO SUMMARY
Search finds the passage, then you read the whole file.
The two-step split is the useful pattern here: excerpts are cheap to search and often not enough, so get_content exists to pull the full file once you know which one matters. Documentation deliberately chopped into small files is what makes that work.
What it is
A small MCP server exposing three tools over SSE transport. It fetches remote pages, and it holds the MCP Python SDK documentation split into small files with a semantic index over them, so an agent can find the right passage and then read the whole file.
What you get
- fetch — give it an absolute URL, get the page text back
- search_docs — semantic search across the bundled SDK documentation, returning the top matches;
queryis required andkdefaults to 3 - get_content — the full local file behind any match
search_docsreturned, by path relative to the docs directory - A CLI that manages the server itself:
start,stop,checkfor a health check, andrestart, which stops the old server, starts a new one in the background, waits until it responds, and logs to server.log
Requirements
Python 3.10 or higher, with dependencies from requirements.txt in a virtual environment. Start it with python -m mcp_simple_tool start; it listens on port 7000 unless you pass --port. Clients connect over SSE — for Cursor that is a .cursor/mcp.json entry pointing at http://localhost:7000/sse. The semantic index builds automatically on first use of search_docs, or you can build it ahead of time with python scripts/build_doc_index.py.
Setup effort
Follow the published steps — python3 -m venv venv
USE CASES
01
Answering a question about the MCP Python SDK
Search the bundled docs semantically, then open the file the best match came from.
02
Reading a page an agent cannot otherwise reach
Fetch it by absolute URL and get the text back.
3 tools
Listed in project docs. Your client may show a different list.
search_docsget_contentBEFORE YOU INSTALL
What to know first
Tools you get
3 tools named in the project's documentation.
Requires
- Python 3.10 or higher (tested on Python 3.13)
- Run the server in a terminal
- SSE transport
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
git clone https://github.com/slawekradzyminski/mcp
cd mcpCreate a virtual environment
TERMINAL
python3 -m venv venvActivate the virtual environment
TERMINAL
source venv/bin/activateInstall the package and dependencies
TERMINAL
pip install -r requirements.txtStart the server (it listens on port 7000; add --port to change it)
TERMINAL
python -m mcp_simple_tool startMCP Clients
Cursor
CURSOR · JSON
{
"mcpServers": {
"website-fetcher-sse": {
"url": "http://localhost:7000/sse"
}
}
}
