Self-hosted MCP server for live documentation and code audits.
|
██████╗ ████████╗ ███╗ ███╗ ██████╗ ██████╗ ██╔════╝ ╚══██╔══╝ ████╗ ████║ ██╔════╝ ██╔══██╗ ██║ ███╗ ██║ ██╔████╔██║ ██║ ██████╔╝ ██║ ██║ ██║ ██║╚██╔╝██║ ██║ ██╔═══╝ ╚██████╔╝ ██║ ██║ ╚═╝ ██║ ╚██████╗ ██║ |
Your AI assistant just mass-produced deprecated code again.You merged it because the formatting was clean.GroundTruth fixes that.
Self-hosted MCP server. 422+ curated libraries. 100+ audit patterns. No rate limits. No API keys.Ships updates continuously — your MCP client picks them up on restart.
The problem
Your model doesn't know that React 19 killed forwardRef, that Next.js made cookies() async, or that Tailwind v4 nuked @tailwind directives. It writes deprecated patterns with full confidence. It hands you SQL injection dressed up as a query builder and uses any in TypeScript like it's a feature.
GroundTruth runs on your machine. Fetches docs from the source — llms.txt, Jina Reader, GitHub — right when you ask. 422+ curated libraries, plus npm, PyPI, crates.io, and pkg.go.dev as fallback. The audit tool reads your actual files, finds issues at exact file:line locations, and fetches the current fix from the real spec.
Install
Claude Code
claude mcp add gt -- npx -y @groundtruth-mcp/gt-mcp@latest
Cursor / Claude Desktop / VS Code
Add to your MCP config (claude_desktop_config.json, .cursor/mcp.json, or .vscode/mcp.json):
{
"mcpServers": {
"gt": {
"command": "npx",
"args": ["-y", "@groundtruth-mcp/gt-mcp@latest"]
}
}
}
No build step. No config file. Node.js 24+. Using @latest means npx pulls the newest version on every session start — you always get the latest libraries, audit patterns, and fixes without doing anything.
Optional: GitHub token
GroundTruth fetches README files, release notes, migration guides, and code examples from GitHub. Unauthenticated requests are limited to 60/hr. A token with no extra scopes takes it to 5,000/hr.
# Claude Code
claude mcp add gt -e GT_GITHUB_TOKEN=ghp_yourtoken -- npx -y @groundtruth-mcp/gt-mcp@latest
# Cursor / Claude Desktop / VS Code — add env to your config:
"env": { "GT_GITHUB_TOKEN": "ghp_yourtoken" }
What it does
Twelve tools. Each does one thing.
| Tool | What it does |
|---|---|
gt_resolve_library |
Find a library by name. Falls back to npm, PyPI, crates.io, pkg.go.dev |
gt_get_docs |
Fetch live docs for a specific topic |
gt_best_practices |
Patterns, anti-patterns, and config guidance for any library |
gt_auto_scan |
Read your manifest, fetch best practices for every dependency |
gt_search |
Search OWASP, MDN, web.dev, W3C, AI provider docs, Google APIs |
gt_audit |
Scan source files — issues at exact file:line with live fixes |
gt_changelog |
Release notes before you upgrade |
gt_compat |
Browser and runtime compatibility via MDN + caniuse |
gt_compare |
Compare 2-3 libraries side-by-side |
gt_examples |
Real-world code examples from GitHub |
gt_migration |
Migration guides and breaking changes |
gt_batch_resolve |
Resolve up to 20 libraries in one call |
How to use it
You don't need to memorize tool names. Just talk to your AI assistant.
use gt for nextjs
use gt for drizzle migrations
gt audit
use gt to check WCAG focus indicators
use gt for OpenTelemetry setup
find all issues and fix with gt
use gt for Google Gemini API
use gt for Claude tool use
Or call tools directly:
gt_resolve_library({ libraryName: "nestjs" })
gt_get_docs({ libraryId: "nestjs/nest", topic: "guards" })
gt_best_practices({ libraryId: "vercel/next.js", topic: "
Tools (12)
gt_resolve_libraryFind a library by name with fallbacks to npm, PyPI, crates.io, and pkg.go.dev.gt_get_docsFetch live docs for a specific topic.gt_best_practicesGet patterns, anti-patterns, and config guidance for any library.gt_auto_scanRead your manifest and fetch best practices for every dependency.gt_searchSearch OWASP, MDN, web.dev, W3C, AI provider docs, and Google APIs.gt_auditScan source files for issues with live fixes.gt_changelogGet release notes before upgrading.gt_compatCheck browser and runtime compatibility via MDN and caniuse.gt_compareCompare 2-3 libraries side-by-side.gt_examplesGet real-world code examples from GitHub.gt_migrationGet migration guides and breaking changes.gt_batch_resolveResolve up to 20 libraries in one call.Environment Variables
GT_GITHUB_TOKENGitHub token to increase API rate limits from 60/hr to 5,000/hr.Configuration
{"mcpServers": {"gt": {"command": "npx", "args": ["-y", "@groundtruth-mcp/gt-mcp@latest"]}}}