I hacked around with this a bit and figured out a way to get it to spit out logging of the prompts and responses to the server: <a href="https://gist.github.com/simonw/54fc42ef9a7fb8f777162bbbfbba4f23" rel="nofollow">https://gist.github.com/simonw/54fc42ef9a7fb8f777162bbbfbba4...</a><p>Short-ish version:<p><pre><code> ANTHROPIC_API_KEY="$(llm keys get anthropic)" \
uv run --with devtools --with pydantic-ai python -c '
import asyncio
from devtools import pprint
from pydantic_ai import Agent, capture_run_messages
from pydantic_ai.mcp import MCPServerStdio
server = MCPServerStdio(
"deno",
args=[
"run",
"-N",
"-R=node_modules",
"-W=node_modules",
"--node-modules-dir=auto",
"jsr:@pydantic/mcp-run-python",
"stdio",
],
)
agent = Agent("claude-3-5-haiku-latest", mcp_servers=[server])
async def main():
with capture_run_messages() as messages:
async with agent.run_mcp_servers():
result = await agent.run("How many days between 2000-01-01 and 2025-03-18?")
pprint(messages)
print(result.output)
asyncio.run(main())'
</code></pre>
Output here: <a href="https://gist.github.com/simonw/54fc42ef9a7fb8f777162bbbfbba4f23#output" rel="nofollow">https://gist.github.com/simonw/54fc42ef9a7fb8f777162bbbfbba4...</a><p>I got it running against Mistral Small 3.1 running locally too - notes on that here: <a href="https://simonwillison.net/2025/Apr/18/mcp-run-python/" rel="nofollow">https://simonwillison.net/2025/Apr/18/mcp-run-python/</a>