mcp-exec
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp-execRun Python code that prints the first 10 Fibonacci numbers."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mcp-exec
English | Русский
Public OSS MCP server (Go, MIT) exposing a single powerful tool — exec — that runs
caller-supplied Python code in a network-isolated, locked-down sandbox and returns
stdout / stderr / exit_code. It is the "code-execution mode" building block: instead of
flooding an agent's context with hundreds of tool schemas, the agent writes code that orchestrates
the work.
Works over three transports — stdio / HTTP / SSE — with an identical tool set everywhere
(official modelcontextprotocol/go-sdk).
The exec tool
Input: { code: string (required), timeout_s?: int, stdin?: string }
Output: { stdout, stderr, exit_code, duration_ms, truncated, timed_out }
A non-zero
exit_codeortimed_out=trueis a normal result, not a tool error. Only invalid input (emptycode, oversizedstdin) is a tool-call error.Sandbox v1: Python 3 with stdlib + PyYAML, Jinja2, Pillow, numpy, pandas, matplotlib.
Related MCP server: Sandbox MCP
Security model (invariants)
Per execution: no network, non-root, cap-drop=ALL, no-new-privileges, read-only rootfs,
no CAP_SYS_ADMIN, ephemeral tmpdir (cleaned up), wall-clock timeout (kills the whole
process-group), memory/PID/CPU limits, capped output (1 MiB → truncated). Runs are serialized
within an instance; scale out with replicas. Caller data (code/stdin/output) is never persisted
and never logged in full — only metadata.
execis the most powerful surface there is. When embedding it in an agent, gate it behind that agent's tool-policy (trusted roles only).
Network note: --network none only applies to stdio. In HTTP/SSE the container needs
networking to serve its port, so sandboxed code would inherit egress — deny it at the orchestrator.
In k8s, a NetworkPolicy that allows ingress to the port and denies all egress:
apiVersion: networking.k8s.io/v1
kind: NetworkPolicy
metadata: { name: mcp-exec-lockdown }
spec:
podSelector: { matchLabels: { app: mcp-exec } }
policyTypes: [Ingress, Egress]
ingress: [{ ports: [{ port: 8080 }] }]
egress: [] # deny all egress → sandbox has no networkRun
go build -o mcp-exec ./cmd/mcp-exec
MCP_EXEC_TRANSPORT=stdio ./mcp-execDocker (recommended production posture):
docker run --rm -i --network none --read-only --cap-drop ALL \
--security-opt no-new-privileges --user 65532:65532 \
--tmpfs /tmp:rw,noexec,nosuid,size=64m \
--memory 256m --pids-limit 128 --cpus 1 \
idconstruct/mcp-exec--tmpfs /tmp is required: the rootfs is read-only, and each run needs a writable
ephemeral workspace (cleaned up after).
Optional auth (HTTP/SSE)
Set MCP_EXEC_AUTH_TOKEN to require every HTTP/SSE request to carry a matching X-MCP-AUTH header
(constant-time compare; 401 otherwise). Empty token disables it. Not applicable to stdio.
Configuration
Env var | Purpose | Default |
|
|
|
| listen address for http/sse |
|
| default wall-clock timeout |
|
| timeout ceiling |
|
| combined stdout+stderr cap |
|
| stdin size cap |
|
| interpreter path |
|
| if set, http/sse require | `` |
Not in v1
bash / multi-language, network from the sandbox, proxying other MCP servers into the sandbox.
License
MIT.
This server cannot be deployed
Maintenance
Related MCP Connectors
MCP server for Superserve sandboxes: create, exec, and manage Firecracker microVMs
MCP server for mandates, delegation, policy-gated execution, credential grants, and audit.
MCP server for the FFmpeg Micro video transcoding API — create, monitor, download transcodes.
Host your MCP tool over streamable HTTP in one command.
Related MCP Servers
- AlicenseBqualityDmaintenanceA secure MCP server for executing whitelisted shell commands with resource and timeout controls, designed for integration with Claude and other MCP-compatible LLMs.203897MIT
- AlicenseNot gradedqualityDmaintenanceProduction-ready MCP server for secure Python code execution with artifact capture, virtual environment support, and LM Studio integration.11Apache 2.0
- AlicenseNot gradedqualityCmaintenanceAn MCP server for securely executing Python code, supporting STDIO, Streamable HTTP, and SSE transports, with easy deployment on Heroku.8Creative Commons Zero v1.0 Universal
- AlicenseAqualityCmaintenanceMCP server that gives AI assistants a secure gVisor-isolated sandbox to run Python or JavaScript code, returning stdout, stderr, and exit codes without local access.120MIT