Code RunnerBLOCK
Code Runner MCP Server
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://www.npmjs.com/package/mcp-server-code-runner) [](https://smithery.ai/server/@formulahendry/mcp-server-code-runner) [](https://hub.docker.com/r/formulahendry/mcp-server-code-runner)
MCP Server for running code snippet and show the result.
It supports running multiple programming languages: JavaScript, PHP, Python, Perl, Perl 6, Ruby, Go, Lua, Groovy, PowerShell, BAT/CMD, BASH/SH, F# Script, C# Script, VBScript, TypeScript, CoffeeScript, Scala, Swift, Julia, Crystal, OCaml Script, R, AppleScript, Elixir, Clojure, Racket, Scheme, AutoHotkey, AutoIt, Kotlin Script, Dart, Haskell, Ni, Lisp, Kit, V, SCSS, Sass. Full list could be seen here in constants.ts.
Setup
npx for VS Code
Install the Code Runner MCP server in VS Code using below buttons:
-VS_Code-0098FF) [-VSCodeInsiders-24bfa5)](https://insiders.vscode.dev/redirect?url=vscode-insiders%3Amcp%2Finstall%3F%257B%2522name%2522%253A%2522mcp-server-code-runner%2522%252C%2522command%2522%253A%2522npx%2522%252C%2522args%2522%253A%255B%2522-y%2522%252C%2522mcp-
9357f0494619OBSERVED · 2026-10-06Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add mcp-server-code-runner -- npx -y [email protected]
claude mcp add mcp-server-code-runner -- docker run -i --rm formulahendry/mcp-server-code-runner:0.1.8
Exposed tools (1)
0 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
run-code | write | Run code snippet and return the result. |
Trust audit
BLOCKgrade D · trust 69/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- declared (1 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (2)
exec(command, (error: any, stdout: string, stderr: string) => {@modelcontextprotocol/sdk, commander, express, zod, @types/express, @types/node, shx, typescript
Gates applied: no_behavioural_pass.
9357f0494619full audit observations/trust-audit/mcp-server/formulahendry__code-runner.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-06 | 9357f0494619 | BLOCK | D | 69 | first audit |
Questions
What is the Code Runner MCP server?
Code Runner MCP Server
What tools does Code Runner expose?
1 in total: 0 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Code Runner safe to connect to an agent?
No — not without reading the findings first. The audit graded it D (69/100) and found 1 critical or high issue in the source. Each one is listed on this page with the file and line it is on.
What credentials does Code Runner need?
No credential environment variables were found in its source, so it appears to need none.
How does Code Runner run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as mcp-server-code-runner at 0.1.8.
How current is this page?
The grade is for one exact copy of the source (9357f0494619), read on 2026-10-06. The repository is watched and re-audited when it changes.