SponsorSubmit a toolSubscribe

Does MCP Run Python (Pydantic) work with Claude Desktop?

Yes. MCP Run Python (Pydantic) passed every step of our test in Claude Desktop on Oct 18, 2026: it installed, connected, its tools were visible, and an agent used it to finish a real task.

Result

ResultPassed
Date testedOct 18, 2026
Plan tested onNot recorded for this run
App versionClaude Desktop 2.37337.1 (Linux beta)
Server packagepackage version not recorded
Connect timeconnected in 11s

Steps

  1. install OK
  2. connect OK
  3. tools visible OK
  4. agent task: run cell OK

Test note: server wrapped in harness/scripts/mcp_tee.py to record JSON-RPC; prompts typed via xdotool; tool Allow pop-ups approved by the operator for test servers only; model = app default

From our own harness run, not the maker’s claims. How we test.

Versions tested

Claude Desktop 2.37337.1 (Linux beta) · package version not recorded · connected in 11s · tested Oct 18, 2026

Server package and resolved dependency versions: not recorded for these runs (our harness records them from Oct 19, 2026 on).

What happened in this run

Install config we used

{
 "command": "uvx",
 "args": [
  "mcp-run-python",
  "stdio"
 ]
}

Connection check

initialize seen in tee log after app restart

Tools check

tools/list answered (tee log)

Agent task: run cell

  • 1 calls reached the server
  • Agent’s answer (excerpt): The output is 42. The mcp-run-python server runs each snippet in a fresh sandboxed interpreter rather than a persistent notebook kernel, so variables won't carr…

Raw details from our harness log for this run. Secrets redacted.

Set it up in Claude Desktop

Copy-paste config for every app is on the MCP Run Python (Pydantic) page. Not connecting? Claude Desktop MCP troubleshooting.

Other apps we tested it in: Claude Code (passed) · Cursor (passed) · ChatGPT (Codex) (passed).

All MCP servers tested in Claude Desktop

Sponsors
+Sponsor this space