Frontier Now
Search

← Back toMCP

Code Execution

Published entries filed under “Code Execution” in MCP, newest first by publication date on this site.

21 entries

  1. alfonsograziano/node-code-sandbox-mcp

    Run JavaScript snippets in isolated Docker sandboxes with on-the-fly npm dependency installation and clean teardown.

    Code Execution

  2. alvii147/piston-mcp

    Execute code through the Piston remote code execution engine.

    Code Execution

  3. asif-nvc/e2b-sandbox-mcp

    E2B cloud sandboxes: create isolated Linux VMs, clone repos, run commands, manage files and perform git operations without touching the local machine.

    Code Execution

  4. ckanthony/openapi-mcp

    Access any API through its existing OpenAPI documentation.

    Code Execution

  5. dagger/container-use

    Containerized environments for coding agents: each agent works in its own fresh container and git branch, with execution history and terminal access.

    Code Execution

  6. fstandhartinger/sandbox-as-a-service-mcp

    Dedicated Linux VM sandboxes for untrusted, model-generated code: run commands, move files, expose a preview URL and destroy the VM.

    Code Execution

  7. gwbischof/outsource-mcp

    Delegate tasks to other AI providers' models, e.g. ask OpenAI to generate an image.

    Code Execution

  8. HanSur94/matlab-mcp-server-python

    MATLAB integration: execute code, run async jobs with progress reporting, get interactive Plotly plots and expose custom .m functions as tools.

    Code Execution

  9. hileamlakB/PRIMS

    Python runtime interpreter that executes submitted code in an isolated environment.

    Code Execution

  10. ksterx/srunx

    Submit SLURM jobs, run YAML workflows, monitor GPU resources, manage SSH profiles and sync files with local or SSH-remote HPC clusters.

    Code Execution

  11. mavdol/capsule/mcp-server

    Run untrusted Python/JavaScript code in WebAssembly sandboxes.

    Code Execution

  12. musharna/jobd

    Self-hostable GPU-aware job broker: dispatch long-running or GPU jobs that outlive the session, route them by VRAM tier and monitor them across sessions.

    Code Execution

  13. ouvreboite/openapi-to-mcp

    Access any API via its OpenAPI specification, with full JSON Schema support for parameters and request bodies.

    Code Execution

  14. r33drichards/mcp-js

    JavaScript sandbox that uses V8 isolation to run AI-generated code locally, with heap snapshotting for persistent sessions.

    Code Execution

  15. Reachpad/reachpad-mcp

    Persistent cloud dev environments for coding agents: create, run commands, checkpoint and fork, with files, services and terminal state kept between calls.

    Code Execution

  16. rikarazome/prolog-reasoner

    SWI-Prolog execution for LLMs with CLP(FD), negation as failure and recursion.

    Code Execution

  17. SebastianGilPinzon/colab-mcp

    Control Google Colab notebooks and assign GPUs (T4/L4/A100).

    Code Execution

  18. Sowiedu/Edict

    Agent-oriented programming language: agents emit a JSON AST that the compiler validates, type- and effect-checks, verifies with Z3/SMT and compiles to WASM.

    Code Execution

  19. telleroutlook/agentkit-js/mcp-server

    Code-mode MCP server: collapses user-defined tools into code execution plus docs search, sandboxed in node:vm, WASM or remote microVMs.

    Code Execution

  20. The-40-Thieves/codecalc

    Code and logic calculator with an offline core: run code, exact symbolic math, SMT/logic and complexity analysis, with optional gVisor/AppContainer sandboxing.

    Code Execution

  21. yepcode/mcp-server-js

    Run LLM-generated code in a YepCode sandbox and create custom MCP tools in JavaScript or Python with npm and PyPI packages.

    Code Execution