Official description7 sourcesMCP servers8d ago
hileamlakB/PRIMS
๐ ๐ - Python runtime interpreter that executes submitted code in an isolated environment
View on GitHub โDirect link ยท no redirect page
Official description> PRIMS โ Python Runtime Interpreter MCP Server PRIMS is a tiny open-source **Model Context Protocol (MCP)** server that lets LLM agents run arbitrary Python code in a secure, throw-away sandbox.
Config template (adjust for your client)
claude mcp add prims -- npx -y prims
A pasteable skeleton generated from the repository name. Check the project README for the exact package and arguments.
- Star count
- 30 โ ยท hileamlakB/PRIMS ยท read from the repository page ยท (checked 2026-10-16 20:00:20)
- Source
- collected from the punkpeye/awesome-mcp-servers list ยท type: MCP server
- Harvest history
- first seen 2026-10-09 ยท last seen 2026-10-16 ยท seen 32ร ยท listed by 7 sources
- Score
- score 703 ยท 30 โ ยท 7 sources ยท mcp
FAQ (answers come from our records)
How do I install it?
We did not find an install command for this repository (our install coverage is only about 4%). Check its README or releases page.
Who is it for?
We filed it under these tags: MCP ๆๅก. The tags come from the entry itself, not a taxonomy we imposed.
Who maintains it?
repository
hileamlakB/PRIMS๏ผfirst catalogued 2026-10-09๏ผlast seen 2026-10-16ใThere is no official certification or quality rating here โ we record sources and dates only.Third-party quality signals
PRIMS โ Python Runtime Interpreter MCP Server
ไปฅไธๆๅฝ่ช่ฏฅไปๅบ็ README๏ผ็ๆฎต๏ผ ยท ๅจ GitHub ่ฏปๅฎๆด README โ
PRIMS is a tiny open-source **Model Context Protocol (MCP)** server that lets LLM agents run arbitrary Python code in a secure, throw-away sandbox.
โข **One tool, one job.** Exposes a single MCP tool โ run_code โ that executes user-supplied Python and streams back stdout / stderr.
โข **Isolated & reproducible.** Each call spins up a fresh virtual-env, installs any requested pip packages, mounts optional read-only files, then nukes the workspace.
โข **Zero config.** Works over MCP/stdio or drop it in Docker.
---
Quick-start
1. Local development environment
2. Launch the server
3. Docker
Examples
List available tools
You can use the provided script to list all tools exposed by the server:
Expected output (tool names and descriptions may vary):
Run code via the MCP server
Mount a dataset once & reuse it
This mounts a CSV with mount_file and then reads it inside run_code without re-supplying the URL.
Inspect your session workspace
This shows how to use the **list_dir** and **preview_file** tools to browse files your code created.
Persist an artifact to permanent storage
The **persist_artifact** tool uploads a file from your output/ directory to a presigned URL.
Example (Python):
Download an artifact
Small artifacts can be fetched directly:
---
Available tools
| Tool | Purpose |
|---------------------|---------------------------------------------------------------|
| run_code | Execute Python in an isolated sandbox with optional pip deps. |
| list_dir | List files/directories inside your session workspace. |
| preview_file | Return up to 8 KB of a text file for quick inspection. |
| persist_artifact | Upload an output/ file to a client-provided presigned URL. |
| mount_file | Download a remote file once per session to mounts/ . |
See the examples/ directory for end-to-end demos.
Contributing
Contributions are welcome! Feel free to open issues, suggest features, or submit pull requests to help improve PRIMS.
โข **One tool, one job.** Exposes a single MCP tool โ run_code โ that executes user-supplied Python and streams back stdout / stderr.
โข **Isolated & reproducible.** Each call spins up a fresh virtual-env, installs any requested pip packages, mounts optional read-only files, then nukes the workspace.
โข **Zero config.** Works over MCP/stdio or drop it in Docker.
---
Quick-start
1. Local development environment
2. Launch the server
3. Docker
Examples
List available tools
You can use the provided script to list all tools exposed by the server:
Expected output (tool names and descriptions may vary):
Run code via the MCP server
Mount a dataset once & reuse it
This mounts a CSV with mount_file and then reads it inside run_code without re-supplying the URL.
Inspect your session workspace
This shows how to use the **list_dir** and **preview_file** tools to browse files your code created.
Persist an artifact to permanent storage
The **persist_artifact** tool uploads a file from your output/ directory to a presigned URL.
Example (Python):
Download an artifact
Small artifacts can be fetched directly:
---
Available tools
| Tool | Purpose |
|---------------------|---------------------------------------------------------------|
| run_code | Execute Python in an isolated sandbox with optional pip deps. |
| list_dir | List files/directories inside your session workspace. |
| preview_file | Return up to 8 KB of a text file for quick inspection. |
| persist_artifact | Upload an output/ file to a client-provided presigned URL. |
| mount_file | Download a remote file once per session to mounts/ . |
See the examples/ directory for end-to-end demos.
Contributing
Contributions are welcome! Feel free to open issues, suggest features, or submit pull requests to help improve PRIMS.
- Source
- awesome ยท https://github.com/hileamlakB/PRIMS
- Browse by field
- MCP servers
- Traction
- 30 โ
- added
- yesterday
More in MCP servers
Filed under
Every tag opens the full list for that filter. Counts are the live catalogue figures.