V8 JavaScript RuntimeBLOCK
MCP server that exposes a V8 JavaScript runtime as a tool for AI agents like Claude and Cursor. Supports persistent heap snapshots via S3 or local filesystem, and is ready for integration with modern AI development environments.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://r33drichards.github.io/mcp-js/) [](https://github.com/r33drichards/mcp-js/releases) [](./LICENSE)
[](https://railway.com/deploy/mcp-js?referralCode=cj5P6Z&utmmedium=integration&utmsource=template&utm_campaign=generic)
mcp-v8 is a Model Context Protocol server, written in Rust, that lets an AI agent run JavaScript and TypeScript in a sandboxed V8 isolate. Instead of wiring up dozens of narrow tools, you give the agent one tool — run_js — and it writes code: looping, branching, transforming data, and calling other tools, often with far fewer tokens than equivalent tool-call chains.
In its default stateful mode the V8 heap is saved as a content-addressed snapshot, so an agent can build up state across many turns. Host capabilities (network, filesystem, subprocess, WebAssembly, module imports, and calls to other MCP servers) are all off by default and unlocked only by explicit OPA/Rego policies.
Why mcp-v8
- One tool, unbounded capability. The agent runs a program, not a fixed menu of tools.
- Durable state. Heap snapshots persist variables and objects across calls.
- Secure by default.
fetch, filesystem, subprocess, and external imports are denied until you grant them via policy. - Kernel-enforced confinement. Opt-in `--sandbox-manifest` confines the whole process with a nono capability manifest (Landlock on Linux, Seatbelt on macOS) as defense in depth beneath the policy layer.
- Production-ready. stdio / Streamable HTTP / SSE transports, a
ff428604f98aOBSERVED · 2026-10-08Connect
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. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add mcp-js:0.20.0 -- docker run -i --rm docker.io/wholelottahoopla/mcp-js:0.20.0:None
Trust audit
BLOCKgrade F · trust 41/100 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 | WARN |
| 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
- declared (6 observation(s))
- Network
- declared (6 observation(s))
- Shell
- declared (3 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- found
Findings (25)
exec(input, baseURL) {seed_binary
seed_sqlite
seed_raw
seed_raw
valid_add_module
console.log(`--- Session A: read secret via heap ${heapA.slice(0, 12)}... ---`);const resultA2 = await runCode(clientA, `console.log("secret=" + globalThis.secret);`);TARGET_URLS="http://127.0.0.1:3001"
TARGET_URLS="http://127.0.0.1:3001,http://127.0.0.1:3002,http://127.0.0.1:3003"
ROLE=$(curl -sf --max-time 5 http://127.0.0.1:4001/raft/status 2>/dev/null \
"input": "redis://foo:bar@somehost:6379/0?baz=bam&qux=baz",
"href": "redis://foo:bar@somehost:6379/0?baz=bam&qux=baz",
"input": "redis://foo:bar@somehost:6379/0?baz=bam&qux=baz",
"href": "redis://foo:bar@somehost:6379/0?baz=bam&qux=baz",
let secret = "client-secret-must-not-be-logged";
let secret = "client-secret-must-not-be-logged";
let secret = "object-client-secret-must-not-be-logged";
.envrc
.lychee.toml
.cargo-ok
.cargo_vcs_info.json
let out = eval(
let out = eval(
let out = eval(
Gates applied: no_behavioural_pass.
ff428604f98afull audit observations/trust-audit/mcp-server/r33drichards__v8-javascript-runtime.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 |
|---|---|---|---|---|---|
| 2026-10-08 | ff428604f98a | BLOCK | F | 41 | first audit |
Questions
What is the V8 JavaScript Runtime MCP server?
MCP server that exposes a V8 JavaScript runtime as a tool for AI agents like Claude and Cursor. Supports persistent heap snapshots via S3 or local filesystem, and is ready for integration with modern AI development environments.
Is V8 JavaScript Runtime safe to connect to an agent?
No — not without reading the findings first. The audit graded it F (41/100) 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 V8 JavaScript Runtime need?
It reads GITHUB_PERSONAL_ACCESS_TOKEN from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does V8 JavaScript Runtime run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as @mcp-js/widdershins-tooling.
How current is this page?
The grade is for one exact copy of the source (ff428604f98a), read on 2026-10-08. The repository is watched and re-audited when it changes.