convez.ai
MCP ServerIntegração & APIsAvançado
r33drichards

mcp-v8 — Runtime JavaScript para Agentes IA

r33drichards/mcp-js

Execute JS/TS em sandbox com estado durável para agentes IA

Ver no GitHub
BomPluginScore · de 0 a 100

Servidor MCP em Rust que expõe um runtime V8 isolado, permitindo que agentes de IA (como Claude) executem JavaScript e TypeScript com estado persistente via snapshots. Suporta políticas de segurança via OPA/Rego e oferece transporte stdio, HTTP/SSE e clustering com Raft.

Instalação

$npx convez-ai r33drichards/mcp-js

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
65
Forks
13
Acompanhando
2
Saúde
42%
Último commit
há 1 dia
Versão
v0.22.0
Issues abertas
43
Contribuidores
5

Casos de uso

  • Agentes IA processando dados complexos com lógica condicional e loops
  • Transformação e análise de dados em runtime isolado
  • Construção de estado persistente entre múltiplas interações com IA
  • Execução segura de código dinâmico com políticas granulares
  • Integração com Claude Desktop/Cursor como ferramenta única unificada

Veredito

Ferramenta madura e bem arquitetada para casos de uso exigentes. Reduz significativamente complexidade de tool-chaining ao oferecer programa completo em vez de menu fixo, com segurança robusta como padrão. Recomendado para builders que precisam de execução dinâmica controlada em ambientes de produção.

README

A tradução para o português deste README ainda está na fila.

mcp-v8 — a JavaScript/TypeScript runtime for AI agents

Docs Release License: AGPL v3

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.
  • Production-ready. stdio / Streamable HTTP / SSE transports, a REST sidecar, async execution with pagination, JWKS auth, and Raft-replicated clustering.

Documentation

Full documentation lives at https://r33drichards.github.io/mcp-js/ (built from site-docs/) — tutorials, how-to guides, concept explanations, and complete reference for the CLI flags, HTTP API, and MCP tools.

Quick start

Install

# Server
curl -fsSL https://raw.githubusercontent.com/r33drichards/mcp-js/main/install.sh | sudo bash

# Optional CLI client
curl -fsSL https://raw.githubusercontent.com/r33drichards/mcp-js/main/install-cli.sh | sudo bash

Installs to /usr/local/bin. Supported platforms: Linux x86_64/arm64 and macOS Apple Silicon. You can also nix run github:r33drichards/mcp-js, use Docker (see the docker-compose.*.yml stacks), or build from source.

Connect an MCP client

# Claude Code (stdio)
claude mcp add mcp-v8 -- mcp-v8 --directory-path /tmp/mcp-v8-heaps   # stateful
claude mcp add mcp-v8 -- mcp-v8 --stateless                          # stateless

For Claude Desktop / Cursor, add to the client's mcpServers config:

{ "mcpServers": { "js": { "command": "mcp-v8", "args": ["--stateless"] } } }

Then ask the agent: "Run this JavaScript: console.log([1,2,3].map(x => x*2))".

Run over HTTP

mcp-v8 --stateless --http-port 8080
# MCP endpoint: POST http://localhost:8080/mcp
# REST sidecar: POST http://localhost:8080/api/exec

See the Quick Start tutorials and the transports guide for more.

Features

  • JavaScript & TypeScript in an isolated V8 engine (via deno_core); TypeScript types are stripped with SWC (type removal, not type checking).
  • Async/await & timers — Promises and the event loop, plus setTimeout/clearTimeout.
  • Console capture — console.log/info/warn/error/debug/trace, streamed to storage and readable with line- or byte-based pagination.
  • Async execution model — run_js returns an execution ID; poll status and stream output; cancel running work.
  • Content-addressed heap snapshots — persist/restore V8 state across calls (local FS, S3, or S3 + write-through cache), or run stateless.
  • WebAssembly — the standard WebAssembly API, plus pre-loaded modules (--wasm-module) exposed as globals and advertised to clients as runjs__wasm__<name> stub tools.
  • ES module imports — optional npm:, jsr:, and URL imports fetched at runtime (policy-gated).
  • Policy-gated capabilities — fetch, filesystem (fs), and subprocess access, each checked against a Rego policy per operation; plus header/OAuth injection for fetch.
  • Compose other MCP servers — connect upstream MCP servers and call them from JS via mcp.callTool() / mcp.listTools().
  • Customizable surface — override the server instructions and the run_js description (--instructions, --run-js-description).
  • Auth & clustering — JWKS-based JWT verification, and optional Raft clustering with replicated session metadata and horizontal scaling.
  • Multiple transports — stdio, Streamable HTTP (MCP 2025-03-26+), and SSE, with a REST sidecar and OpenAPI spec.

What the agent's code can do

These globals are available inside run_js (capability globals require a policy):

GlobalPurposeGated by
console, setTimeoutOutput & timers—
fetch(url, opts?)HTTP requests (Fetch API)fetch policy
fs.*File I/O (readFile, writeFile, …)filesystem policy
child_process / Deno.CommandRun subprocessessubprocess policy
import (npm: / jsr: / URL)External ES modules--allow-external-modules + modules policy
WebAssembly, __wasm_<name>Run/instantiate WASM—
mcp.callTool/listTools/serversCall upstream MCP serversmcp_tools policy

See Concepts → Security policies for the policy model.

MCP tools

ToolModeDescription
run_jsbothStateful: queue execution → {execution_id}. Stateless: run and return {output, error?}.
get_executionstatefulPoll status/result of an execution.
get_execution_outputstatefulRead paginated console output (line or byte).
cancel_executionstatefulTerminate a running execution.
list_executionsstatefulList executions and their status.
list_sessions, list_session_snapshotsstatefulBrowse named sessions and history.
get_heap_tags, set_heap_tags, delete_heap_tags, query_heaps_by_tagsstatefulTag and search heap snapshots.

Full parameters: MCP tools reference.

Configuration

mcp-v8 is configured entirely through CLI flags — storage backend, transport, execution limits, policies, fetch-header injection, WASM modules, clustering, JWKS auth, and the prompt/tool-description overrides. The complete, always-current list is the generated CLI flags reference.

mcp-v8 --help            # all flags
mcp-v8 --print-openapi   # print the REST OpenAPI spec

CLI client (mcp-v8-cli)

A fully-typed client for the REST API, generated from the OpenAPI spec via progenitor:

mcp-v8 --stateless --http-port 3000 &
mcp-v8-cli exec "console.log('hello'); 1 + 1"
mcp-v8-cli executions get <execution_id>
mcp-v8-cli executions output <execution_id>
export MCP_V8_URL=https://my-server.example.com   # point at a remote server

Rust client (mcp-v8-client)

[dependencies]
mcp-v8-client = { git = "https://github.com/r33drichards/mcp-js" }
use mcp_v8_client::Client;
let client = Client::new("http://localhost:3000");
let body = mcp_v8_client::types::ExecRequest {
    code: "1 + 1".to_string(),
    heap: None, session: None,
    heap_memory_max_mb: None, execution_timeout_secs: None, tags: None,
};
let resp = client.exec_handler(&body).await?;
println!("execution_id: {}", resp.into_inner().execution_id);

Build from source

The repo is a Nix flake (it wires up the prefetched V8 archive so the build stays offline-friendly):

nix build github:r33drichards/mcp-js   # → ./result/bin/server
# or for development:
nix develop      # then: cargo build -p server

A plain cargo build --release inside server/ also works if your toolchain can build deno_core/V8.

Limitations

  • setInterval is not available — use a loop with awaited setTimeout.
  • No DOM or browser APIs — there is no window/document.
  • TypeScript is type-stripped, not type-checked — invalid types are removed, not reported. JSX/TSX is not supported (it parses to a clear error).

License

GNU AGPL-3.0.

MCP-V8 Load Test Benchmark Report v0.1.0

Comparison of single-node vs 3-node cluster at various request rates.

Results

ran on railway gha runners on pr

TopologyTarget RateActual Iter/sHTTP Req/sExec Avg (ms)Exec p95 (ms)Exec p99 (ms)Success %DroppedMax VUs
cluster-stateful100/s99.599.544.9196.88416.99100%3141
cluster-stateful200/s199.6199.623.2279.32131.13100%1333
cluster-stateless1000/s999.9999.93.827.7213.09100%0100
cluster-stateless100/s1001003.675.658.03100%010
cluster-stateless200/s2002003.565.98.61100%020
cluster-stateless500/s5005003.425.859.2100%050
single-stateful100/s99.199.1215.12362.5376.6100%3242
single-stateful200/s97.897.81948.822212.552960.96100%5939200
single-stateless1000/s977.1977.160.98482.98602.38100%843561
single-stateless100/s1001003.715.738.73100%010
single-stateless200/s2002003.615.437.74100%020
single-stateless500/s5005004.678.4927.98100%050

P95 Latency

TopologyRateP95 (ms)
cluster-stateful100/s196.88█████████████████████
cluster-stateful200/s79.32█████████████████
cluster-stateless100/s5.65███████
cluster-stateless200/s5.9███████
cluster-stateless500/s5.85███████
cluster-stateless1000/s7.72████████
single-stateful100/s362.5███████████████████████
single-stateful200/s2212.55██████████████████████████████
single-stateless100/s5.73███████
single-stateless200/s5.43██████
single-stateless500/s8.49████████
single-stateless1000/s482.98████████████████████████

Notes

  • Target Rate: The configured constant-arrival-rate (requests/second k6 attempts)
  • Actual Iter/s: Achieved iterations per second (each iteration = 1 POST /api/exec)
  • HTTP Req/s: Total HTTP requests per second (1 per iteration)
  • Dropped: Iterations k6 couldn't schedule because VUs were exhausted (indicates server saturation)
  • Topology: single = 1 MCP-V8 node; cluster = 3 MCP-V8 nodes with Raft
Ver o original no GitHub

Bom para

Relacionados