Errata MCP Server
OfficialProvides Errata correction data for npm packages, allowing agents to check a package and version for known outdated code patterns, retrieve verified fixes, search related errors, and report feedback on entries.
Provides Errata correction data for PyPI packages, allowing agents to check a package and version for known outdated code patterns, retrieve verified fixes, search related errors, and report feedback on entries.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
@formachines/errata-mcp
An MCP server for Errata: places where AI models write outdated code for PyPI and npm libraries, each with a fix verified in a sandbox. Three tools; stdio; no API key.
Install
Claude Code:
claude mcp add errata -- npx -y @formachines/errata-mcpAny client with a JSON config (Claude Desktop, Cursor, Windsurf, VS Code …):
{
"mcpServers": {
"errata": { "command": "npx", "args": ["-y", "@formachines/errata-mcp"] }
}
}Node 20 or newer. Registry name: ai.formachines/errata.
Related MCP server: driftwatch-mcp
Tools
tool | input | answer |
|
|
|
|
|
|
|
|
|
Each entry in an answer carries verdict (apply / lead / none), grade (verified / possible /
not_affected / unknown), reason, wrong, right, detect, error, fails_on, verified_on, url.
Example, check_package {"ecosystem":"pypi","package":"click","version":"8.5.0"} against the live base:
{"status":"found","package":"pypi/click","installed":"8.5.0","entries":[{"id":"pypi/click/8.5.0/0001","verdict":"apply","grade":"verified","reason":"checked on click 8.5.0; installed 8.5.0; proof.auto_apply true","symbol":"click.Parameter","wrong":"parameter = click.Parameter([\"--x\"])","right":"parameter = click.Option([\"--x\"])","detect":["click.Parameter"],"error":"Can't instantiate abstract class Parameter with abstract methods _parse_decls, add_to_parser","fails_on":"8.5.0","verified_on":["8.5.0"],"url":"https://formachines.ai/errata/pypi/click/0001-click-parameter/"}]}and the same package at a version nobody checked, "version":"8.6.0":
status: "unconfirmed_version", verdict lead, reason installed 8.6.0 is newer than the versions checked (8.5.0);
one checked version is not a range.
Rule
One rule for the server, the CLI, the skill and the site (printed in every page footer, llms.txt and the JSON
agent_rule): apply a correction on your own only when the installed version is one it was checked on
(versions.checked_on: fails_on and every recheck) and its proof.auto_apply is true. A newer version than the
checked ones, one between works_on and fails_on, or an unknown one is lead; works_on or older is none.
Merged and withdrawn entries are never offered: answers list them under not_offered with the entry that carries a
merged one now. report refuses them before sending. An unreachable base is technical_error with isError: true,
never no_coverage.
Environment
variable | default |
|
|
|
|
|
|
|
|
|
|
Requests carry the User-Agent formachines-errata-mcp/<version>, so the site counts MCP traffic apart.
Overhead
Measured 2026-11-02 against formachines.ai: the first check_package costs 3 requests (index 5.9 kB, changelog 31 kB,
the package JSON 5–12 kB), later calls in the next ten minutes only the package JSON (or nothing, when cached).
search_error costs one 31 kB request for the error index. Answers are compact: 0.6 kB for click, 1.9 kB for
typescript (two entries), 0.9 kB for a matched error.
What the server does not promise
Not a full scan. The base covers a few dozen packages;
no_coveragemeans no corrections, not that the code is current.No range proof. One checked version is not a range; newer versions are
lead.Not an applier. The server never edits code;
applysays the base allows applying the fix as is.Reports are not published.
reportsends to a quarantine that is rechecked in the sandbox before anything changes; a note is never shown to other agents.No offline mode. Without the network every tool answers
technical_error.
Check it yourself
npx -y @modelcontextprotocol/inspector --cli npx -y @formachines/errata-mcp --method tools/listDevelopment
npm install
npm test
npm run typecheck
npm packsrc/core is shared with errata-cli and kept identical in both. Tests run against a snapshot of formachines.ai/errata in test/fixtures/site (2026-11-02); npm test starts the built server over stdio with the SDK client and runs the seven acceptance cases; scripts/inspect-live.sh repeats them with MCP Inspector against the live base. server.json follows the registry schema 2025-12-11.
MIT licence. The data is CC BY 4.0 (formachines.ai/errata).
This server cannot be deployed
Maintenance
Related MCP Connectors
Production errors your coding agent can read: search, stack traces, context, trends, resolve.
Real-time Python package and vulnerability data for AI coding agents.
Package intelligence for AI agents across npm, PyPI, crates.io and deps.dev. No API keys.
Package intelligence for AI agents across npm, PyPI, crates.io and deps.dev. No API keys.
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceProvides verified fixes for real developer errors to AI agents via MCP, with free sample fixes and paid per-lookup transactions on Base mainnet. Enables searching fixes, browsing the catalog, retrieving offers and fixes, and submitting new fixes.1-
- AlicenseNot gradedqualityBmaintenanceEnables AI coding agents to identify exactly what broke between two dependency versions, with citations for every claim, and to verify package existence to catch typosquatting, all without requiring an API key.MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI coding assistants to search reproducibly verified bug fixes, compatibility recipes, and code patches, and to submit new solutions for automated sandbox verification.MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to search a shared, receipt-verified base of troubleshooting experience by raw error and environment, retrieve full repair cards with root cause, steps and verification, and report the outcome of the revision they actually applied. Agents can also submit, comment on, and correct pitfalls, so a problem solved once is reused instead of retried locally.MIT