Data Processing MCP Server
1. Click on "Install Server".
2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
3. In the chat, type `@` followed by the MCP server name and your instructions, e.g., "`@Data Processing MCP Server` Summarise this CSV: name,scoreAlice,88 Bob,72"
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](https://glama.ai/blog/2025-07-08-how-to-install-and-use-mcp-servers).Data Processing MCP Server
A FastMCP 3.0 server exposing data-processing tools, resources, and prompts over HTTP.
Quick Start
1. Install dependencies
pip install -r requirements.txt2. Run the server
# Simple one-liner (stdio→http)
python server.py
# Or via the FastMCP CLI
fastmcp run server.py:mcp --transport http --port 8000The server starts at http://localhost:8000/mcp
Tools
CSV
Tool | Description |
| Parse CSV text → list of dicts |
| Descriptive statistics for every numeric column |
| Return rows where |
| Convert CSV → JSON array string |
JSON
Tool | Description |
| Flatten nested JSON with dot-notation keys |
| Convert a JSON array of objects → CSV |
| List every unique key path in a JSON document |
Text
Tool | Description |
| Top-N word counts in plain text |
| Characters, words, sentences, paragraphs |
| Find & replace with an optional case-insensitive mode |
Numeric
Tool | Description |
| Min, max, mean, median, stdev, variance for a list of numbers |
Resources
URI | Description |
| Server metadata and capability map |
| Ready-to-use sample CSV string |
| Ready-to-use sample nested JSON |
Prompts
Name | Description |
| Full end-to-end analysis workflow for any dataset |
| Data cleaning + format conversion workflow |
Endpoints
Path | Method | Description |
| POST/GET | MCP protocol (StreamableHTTP) |
| GET | Health check (always unauthenticated) |
Production (Uvicorn + multiple workers)
# stateless_http=True is required for multi-worker setups
FASTMCP_STATELESS_HTTP=true uvicorn server:mcp.http_app() \
--host 0.0.0.0 --port 8000 --workers 4Or create app.py:
from server import mcp
app = mcp.http_app(stateless_http=True) # for multi-worker deploymentsThen:
uvicorn app:app --host 0.0.0.0 --port 8000 --workers 4Connect from a client
import asyncio
from fastmcp import Client
client = Client("http://localhost:8000/mcp")
async def main():
async with client:
result = await client.call_tool("summarise_csv", {
"csv_text": "name,score\nAlice,88\nBob,72\nCarol,95"
})
print(result)
asyncio.run(main())Install into Claude Desktop
fastmcp install server.py:mcp --name "Data Processing Server"This server cannot be installed
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/FelipeVandevelde/mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server