Run PythonSAFE
MCP server to run Python code in a sandbox.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
MCP Run Python
MCP server to run Python code in a sandbox.
We've decided to retire and archive this project - there's just no safe way to run Python within pyodide safely with reasonable latency.
Instead, we're working hard on Monty which should solve the usecase we initially intended for mcp-run-python, with better security, lower latency, easier install, and better ways to communicate with the OS.
If you want to use this projects code, or otherwise use pyodide to run LLM generated code, feel free to do so.
However be extremely careful about how you sandbox the service and what code you allow to run.
In particular Python code running in pyodide can run arbitrary javascript meaning it can do whatever the javascript runtime running pydodie can do, including:
- tainting that runtime to control or alter how code runs on later onvocations
- reading and/or writing to any files that runtime has access to
- OOMing the machine by consuming all memory - deno has no good way limit memory usage
These issu
907ee5263c8aOBSERVED · 2026-10-06Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add mcp-run-python -- uvx mcp-run-python
{
"mcpServers": {
"mcp-run-python": {
"command": "uvx",
"args": [
"mcp-run-python"
]
}
}
}Exposed tools (1)
0 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
run_python_code | write |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (1)
.pre-commit-config.yaml
Gates applied: no_behavioural_pass.
907ee5263c8afull audit observations/trust-audit/mcp-server/pydantic__run-python.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-06 | 907ee5263c8a | SAFE | B | 89 | first audit |
Questions
What is the Run Python MCP server?
MCP server to run Python code in a sandbox.
What tools does Run Python expose?
1 in total: 0 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Run Python safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Run Python need?
No credential environment variables were found in its source, so it appears to need none.
How does Run Python run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on PyPI as mcp-run-python.
How current is this page?
The grade is for one exact copy of the source (907ee5263c8a), read on 2026-10-06. The repository is watched and re-audited when it changes.