{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_ynp8mvjmcy4v","handle":"iflow-mcp-mcp-safe-local-python-executor","url":"https://wellknown.network/agents/iflow-mcp-mcp-safe-local-python-executor","links":{"self":"https://wellknown.network/agents/iflow-mcp-mcp-safe-local-python-executor/record.json","html":"https://wellknown.network/agents/iflow-mcp-mcp-safe-local-python-executor","markdown":"https://wellknown.network/agents/iflow-mcp-mcp-safe-local-python-executor/record.md","api":"https://wellknown.network/api/v1/agents/iflow-mcp-mcp-safe-local-python-executor","status":"https://wellknown.network/api/v1/agents/iflow-mcp-mcp-safe-local-python-executor/status","claim":"https://wellknown.network/agents/iflow-mcp-mcp-safe-local-python-executor/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/iflow-mcp-mcp-safe-local-python-executor/claim.json","badge":"https://wellknown.network/agents/iflow-mcp-mcp-safe-local-python-executor/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/iflow-mcp-mcp-safe-local-python-executor/history","tools":"https://wellknown.network/api/v1/agents/iflow-mcp-mcp-safe-local-python-executor/tools"},"ard":{"identifier":"urn:air::server:iflow-mcp-mcp-safe-local-python-executor","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"iflow-mcp_mcp_safe_local_python_executor","summary":"MCP server exposing tool for a safe local Python code execution","description":"# Safe Local Python Executor\n\nAn MCP server (stdio transport) that wraps Hugging Face's [`LocalPythonExecutor`](https://github.com/huggingface/smolagents/blob/main/src/smolagents/local_python_executor.py)\n(from the [`smolagents`](https://huggingface.co/docs/smolagents/en/index) framework). It is a custom Python runtime that \nprovides basic isolation/security when running Python code generated by LLMs locally. It does not require Docker or VM.\nThis package allows to expose the Python executor via MCP (Model Context Protocol) as a tool for LLM apps like Claude Desktop, Cursor or any other MCP compatible client.\nIn case of Claude Desktop this tool is an easy way to add a missing Code Interpreter (available as a plugin in ChatGPT for quite a while already).\n\n<img width=\"1032\" alt=\"image\" src=\"https://github.com/user-attachments/assets/3b820bfc-970a-4315-8f2d-970591c6fdae\" />\n\n## Features\n\n- Exposes `run_python` tool\n- Safer execution of Python code compared to direct use of Python `eva()l`\n- Ran via uv in Python venv\n- No file I/O ops are allowed\n- Restricted list of imports\n    - collections\n    - datetime\n    - itertools\n    - math\n    - queue\n    - random\n    - re\n    - stat\n    - statistics\n    - time\n    - unicodedata\n\n## Security\n\nBe careful with execution of code produced by LLM on your machine, stay away from MCP servers that run Python via command line or using `eval()`. The safest option is using a VM or a docker container, though it requires some effort to set-up, consumes resources/slower. There're 3rd party servcices providing Python runtime, though they require registration, API keys etc.\n\n`LocalPythonExecutor` provides a good balance between direct use of local Python environment (which is easier to set-up) AND remote execution in Dokcer container or a VM/3rd party service (which is safe). Hugginng Face team has invested time into creating a quick and safe option to run LLM generated code used by their code agents. This MCP server builds upon it:\n\n>To ad…","publisher":{"name":"Maxim Saplin","url":null},"homepage":"https://github.com/maxim-saplin/mcp_safe_local_python_executor/tree/main","repository":"https://github.com/maxim-saplin/mcp_safe_local_python_executor/tree/main","version":"0.1.0","license":"MIT","protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:iflow-mcp_mcp_safe_local_python_executor","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"code.execution","name":"Code Execution","confidence":0.905,"provenance":"derived"},{"slug":"ai.model-access","name":"Model Access","confidence":0.905,"provenance":"derived"}],"categories":["ai","code"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"iflow-mcp_mcp_safe_local_python_executor","registry":"pypi","observedAt":"2026-10-22T03:27:43.279Z","publishedAt":"2025-11-12T05:23:01.293912Z","latestVersion":"0.1.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"iflow-mcp_mcp_safe_local_python_executor","url":"https://pypi.org/project/iflow-mcp_mcp_safe_local_python_executor/","firstSeenAt":"2026-09-09T20:23:38.361Z","fetchedAt":"2026-10-22T03:26:04.602Z","normalizedAt":"2026-10-22T03:26:04.602Z"}]},"firstSeenAt":"2026-09-09T20:23:38.361Z","updatedAt":"2026-10-22T03:27:43.279Z"}