Errata MCP Server

by formachines Your server? Claim it

local only

Errata runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 2 Nov 2026.

Sandbox-verified fixes where AI models write outdated code for PyPI and npm libraries

—

Installs / week

npm · @formachines/errata-mcp

Stars

0 open issues

2 Nov 2026

Last commit

from GitHub

MIT

License

TypeScript

Nothing serious here today

Today is the operative word: we check Errata every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add errata -- npx -y @formachines/errata-mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "errata": {
      "command": "npx",
      "args": [
        "-y",
        "@formachines/errata-mcp"
      ]
    }
  }
}

~/.codex/config.toml

[mcp_servers.errata]
command = "npx"
args = ["-y", "@formachines/errata-mcp"]

.cursor/mcp.json

{
  "mcpServers": {
    "errata": {
      "command": "npx",
      "args": [
        "-y",
        "@formachines/errata-mcp"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "errata": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@formachines/errata-mcp"
      ]
    }
  }
}

Optional settings from the registry entry, left out of the block above: ERRATA_BASE_URL (Base URL of the Errata site (default https://formachines.ai)), ERRATA_TIMEOUT_MS (Timeout of one request to the base, in milliseconds (default 8000)), ERRATA_NO_TELEMETRY (Set to 1 to stop sending search misses (error type and scrubbed message) when search_error finds nothing).

Alternatives to Errata

same job, measured the same way

Python Code Validator

by statemind

Proves AI-generated Python does what you asked: lint, types, security, sandbox run, exact fixes.

3 tools answering

E2b

by mcparmory

Create and manage secure sandboxes for running AI agent code

198 installs/wk local only

Foundry MCP code mode

by foundry-mcp

Code mode (preview): the AI writes a script against a typed foundry.* API and runs it in a sandbox.

answering

Tenki Sandbox MCP

by luxorlabs

Disposable microVM sandboxes for AI agents: run code, read/write files, git, preview URLs.

334 installs/wk local only

Writingmate MCP

by writingmate

Use AI models for chat, image, and video generation from Claude Code and other MCP hosts.

answering

Overllm

by theadamdanielsson

Find the LLM/AI calls you didn't need — where plain code or a regex does the job. No model.

169 installs/wk local only

livewiki

by eduardoabreu81

A repository wiki of Markdown pages anchored to real code: read, search, and verified writes.

75 installs/wk local only

Cinch

by yusufkadry

Run AI-generated code safely. gVisor-isolated Python/JS sandboxes for any MCP client. Pay per run.

33 installs/wk local only

Errata — questions

Answers built from our own checks of this server.

Why is there no uptime for Errata?

Errata runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the npm package @formachines/errata-mcp.

How do I connect Errata?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls @formachines/errata-mcp straight from npm; nothing to host, nothing to sign up for.

Is Errata open source?

Yes — it is published under the MIT licence, written in TypeScript and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.