Code Executor Mcp
Let your coding agent run Python or shell snippets in a sandbox and return stdout, errors, and exit codes without leaving the chat.
Overview
code-executor-mcp is a Build-phase MCP server that executes agent-submitted code via stdio and returns run output for fast validation during implementation.
What is this MCP server?
- PyPI package code-executor-mcp v1.0.4 with stdio MCP transport
- Runs agent-supplied code and returns structured execution results
- Supports quick validation loops for generated backends and CLI utilities
- GitHub-hosted under CSOAI-ORG / MEOK AI Labs for version pinning
- Fits agent-first workflows where copy-paste manual runs slow you down
- Server schema version 1.0.4
- Single PyPI package with stdio transport
- Repository: github.com/CSOAI-ORG/code-executor-mcp
What problem does it solve?
You waste context and time bouncing between the agent chat and a terminal every time you need to prove a generated script actually runs.
Who is it for?
Indie builders using agent-heavy stacks who want immediate run feedback on Python or shell snippets while prototyping APIs, CLIs, and automation.
Skip if: Teams that need hardened multi-tenant sandboxes, full CI matrices, or production job orchestration without additional guardrails beyond this MCP.
What do I get? / Deliverables
Your agent can run snippets on demand so you confirm behavior, fix failures, and iterate in one workflow instead of manual copy-paste runs.
- Registered stdio MCP server the agent can call for code runs
- Structured stdout, stderr, and exit status returned into the agent thread
- Faster validate-fix cycles on small scripts before git commit
Recommended MCP Servers
Journey fit
Execution belongs in Build because solo builders need to verify generated scripts, APIs, and data transforms while iterating—not only after release. Agent-tooling is the canonical shelf for MCP bridges that extend what Claude Code, Cursor, or Codex can do during implementation.
How it compares
MCP execution bridge, not a hosted notebook platform or a full CI/CD runner.
Common Questions / FAQ
Who is code-executor-mcp for?
Solo and indie developers who use Claude Code, Cursor, or similar agents and want run-output tools wired through MCP instead of manual terminal steps.
When should I use code-executor-mcp?
Use it during Build when you are validating agent-generated code, debugging small scripts, or closing the loop before you commit larger changes.
How do I add code-executor-mcp to my agent?
Install the PyPI package code-executor-mcp (v1.0.4), add a stdio MCP server entry pointing at that package, restart your agent, and confirm the execution tool appears in the tool list.