Provides tools for performing numerical and array operations on uploaded datasets using NumPy, supporting mathematical, statistical, and linear algebra computations.
Provides tools for manipulating and analyzing uploaded tabular datasets using Pandas DataFrames, including filtering, grouping, aggregating, and transforming data.
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., "@Pandas Excel Analytics MCP Upload sales.csv and tell me which region has the highest profit"
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 deterministic Model Context Protocol (MCP) server exposing Pandas, NumPy, Excel/openpyxl, and automated EDA operations over uploaded tabular datasets.
This server does not contain an LLM, embeddings, RAG, or Langflow/OpenRouter credentials. It is purely the data-execution layer, meant to be called by an MCP client (e.g. Langflow's MCP Tool node) driven by an LLM.
Built on the current stable MCP Python SDK (mcp v2.x), where the server
class is mcp.server.mcpserver.MCPServer — the successor to the
pre-2.0 mcp.server.fastmcp.FastMCP name used in older tutorials. The public
API (.tool(), .streamable_http_app()) is unchanged.
Related MCP server: CSV MCP Assistant
python3 -m venv .venv && source .venv/bin/activate
pip install -r requirements.txtuvicorn server:app --reload --host 127.0.0.1 --port 8000MCP endpoint: http://127.0.0.1:8000/mcp
Health check: http://127.0.0.1:8000/health
npx @modelcontextprotocol/inspectorThen connect to http://127.0.0.1:8000/mcp using the "Streamable HTTP"
transport in the Inspector UI, and browse/call the 27 registered tools.
pytest tests/ -vVariable | Purpose | Required |
| Port to bind (set automatically by Render) | No (default 8000) |
| Bearer token for authenticated requests | Recommended in production |
| Force auth even without inspecting | No |
| Comma-separated hostnames this server is reachable at, e.g. | Yes, in production |
| Upload size limit (default 50) | No |
| Dataset shape limits | No |
| Excel workbook sheet limit | No |
| Max rows returned per tool call | No |
OPENROUTER_API_KEY and any LLM credentials are intentionally not
consumed by this server — keep them in Langflow.
Push this repository to GitHub.
In Render, "New +" → "Blueprint", point it at the repo (uses render.yaml).
Render will set MCP_API_TOKEN automatically (via generateValue: true);
copy it from the Render dashboard's Environment tab for your MCP client.
Set MCP_ALLOWED_HOSTS to your actual *.onrender.com hostname (the
Blueprint pre-fills a guess — update it once Render assigns the final
service name).
Deploy. Render runs pip install -r requirements.txt then
uvicorn server:app --host 0.0.0.0 --port $PORT.
Verify: curl https://YOUR-SERVICE.onrender.com/health → {"status":"ok"}.
Production MCP URL:
https://YOUR-SERVICE.onrender.com/mcpNo eval/exec/shell execution/arbitrary imports anywhere in the codebase.
Every dataset is addressed by an opaque dataset_id — callers never supply
filesystem paths.
Filenames are sanitised and path-joined under a fixed storage root
(utils/security.py::safe_join) — path traversal is structurally impossible.
TransportSecuritySettings host allowlist is always configured; the
SDK's default localhost-only protection is never disabled.
Bearer-token auth is opt-in via MCP_API_TOKEN; when unset the server
runs unauthenticated (fine for local dev, not for a public Render URL).
In Langflow, add an MCP Tools / MCP Client component.
Point it at https://YOUR-SERVICE.onrender.com/mcp using the Streamable
HTTP transport, and add header Authorization: Bearer <MCP_API_TOKEN>.
Set the component to "Tool Mode" so all 27 tools populate as a Toolset.
Wire that Toolset into your Base LLM Agent (OpenRouter) node.
Test with a prompt like: "Upload sales.csv and tell me which region has the highest profit."
Langflow + OpenRouter + embeddings/RAG are deliberately out of scope for this backend and should be added only after the above is verified working.
This server cannot be deployed
Governed data discovery, exact queries, decisions, simulations, and runtime utilities over MCP.
Query, join, profile, clean and convert CSV/JSON/Parquet with server-side DuckDB over MCP.
Hosted MCP server for AI-driven data ops. Create apps, manage schemas, and CRUD structured data.
Unified gateway exposing 150+ tools across all NexGenData MCP servers via one endpoint.
