Frameworks & Starter Kits
mcp-use
Last updated 2026-06-05 · benchmark checked 2026-08-13 · unchanged since 2026-07-30 — deterministic & reproducible
The fullstack MCP framework to develop MCP Apps for ChatGPT / Claude & MCP Servers for AI Agents.
Is mcp-use production-ready?
Legit.Show scores mcp-use 97 out of 100 — the simple average of its 6 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on mcp-use (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Security; its weakest is Performance. 6 of the seven frames returned a score; Accessibility was not measurable on this service and is recorded as null — not as zero. Every frame it averages is published with its evidence on the Legit.Show listing.
The 7 Frames
- Performance — 80/100
- Accessibility — not measurable on this service (null — not scored as 0)
- Security — 100/100
- Privacy — 100/100
- Reliability — 100/100
- Standards — 100/100
- Discoverability — 100/100
What we measured
- Security headers present: CSP, HSTS, X-Frame-Options, X-Content-Type-Options, Referrer-Policy.
- Served over HTTPS with a valid certificate.
- Real Lighthouse performance run — 231 ms to first byte.
- Returns a proper 404 for unknown routes.
- 3 of 3 sampled routes reachable.
- Has a reachable privacy policy.
- Sets cookies / loads scripts with no consent prompt.
- Discoverable: structured data, sitemap, OpenGraph image, canonical URL.
Who built it
Luigi Pederzani (@pederzh) · product account @manufact
Pricing
Free $0/mo with $5 credits; Hobby $25/mo with $30 credits; Startup $250/mo with $300 credits; Enterprise custom pricing. Usage-based with pay-as-you-go after included credits.
Visit mcp-use → · Alternatives to mcp-use → · How this was measured →