About Exec Sandbox
Exec Sandbox is an open-source MCP server for agents that need to run caller-provided Python in a restricted environment. Its single `exec` tool returns output and exit status, with execution limits and network isolation for stdio deployments.
Key features
- 01Single Python `exec` tool
- 02Network-isolated stdio sandbox
- 03Timeout and resource limits
- 04Capped stdout and stderr
- 05stdio, HTTP, and SSE transports
Use cases
- 01Run Python calculations for an agent
- 02Transform data without adding tool schemas
- 03Execute untrusted code in a restricted environment
MCP support
Exposes one `exec` tool to MCP clients over stdio, HTTP, or SSE. The tool accepts Python code and returns stdout, stderr, exit code, duration, truncation, and timeout status.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
docker run -i --rm -e MCP_EXEC_TRANSPORT -e MCP_EXEC_DEFAULT_TIMEOUT_S -e MCP_EXEC_MAX_TIMEOUT_S -e MCP_EXEC_MAX_OUTPUT_BYTES -e MCP_EXEC_MAX_STDIN_BYTES -e MCP_EXEC_AUTH_TOKEN docker.io/idconstruct/mcp-exec:v0.5.4MCP_EXEC_TRANSPORTMCP transport. Must be 'stdio' for direct docker/stdio use.MCP_EXEC_DEFAULT_TIMEOUT_SDefault wall-clock timeout per exec, seconds.MCP_EXEC_MAX_TIMEOUT_SMaximum wall-clock timeout a caller may request, seconds.MCP_EXEC_MAX_OUTPUT_BYTESCap on combined stdout/stderr before truncation.MCP_EXEC_MAX_STDIN_BYTESCap on stdin passed to the sandboxed code.MCP_EXEC_AUTH_TOKENSecretOptional X-MCP-AUTH token (http/sse transports only).Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEmcp-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.
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 network
Run
go build -o mcp-exec ./cmd/mcp-exec
MCP_EXEC_TRANSPORT=stdio ./mcp-exec
Docker (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 |
|---|---|---|
MCP_EXEC_TRANSPORT | stdio | http | sse | stdio |
MCP_EXEC_ADDR | listen address for http/sse | :8080 |
MCP_EXEC_DEFAULT_TIMEOUT_S | default wall-clock timeout | 30 |
MCP_EXEC_MAX_TIMEOUT_S | timeout ceiling | 300 |
MCP_EXEC_MAX_OUTPUT_BYTES | combined stdout+stderr cap | 1048576 |
MCP_EXEC_MAX_STDIN_BYTES | stdin size cap | 1048576 |
MCP_EXEC_PYTHON | interpreter path | python3 |
MCP_EXEC_AUTH_TOKEN | if set, http/sse require X-MCP-AUTH header (constant-time); empty = off | `` |
Not in v1
bash / multi-language, network from the sandbox, proxying other MCP servers into the sandbox.
License
MIT.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.