Product

MCPscore

by mcp-box

Product website
https://mcpscore.dev/
Documentation
https://docs.mcpscore.dev/
Categories
Agent Readiness Tools Developer Tools

Description

Deterministic MCP server auditor with weighted findings and machine-readable JSON and SARIF reports.

AI-native score

How ready this product is for agents to use, on a 0–100 scale across four weighted dimensions. Security is one of them, so a high score is not a substitute for your own security or vendor-risk review. How is this scored?

Research coverage: 42% of the scored decision fields carry a confirmed value. Unresearched fields score zero in the grade above.

Integration2/10Trust0/6Portability4/4Security0/4Tier D27/100
Component Raw Weight Contribution
Integration 2/10 35% 7.0
Trust 0/6 30% 0.0
Portability 4/4 20% 20.0
Security 0/4 15% 0.0
Signals that fired
  • Integration: Command-line interface (+1) ; SDK / developer kit (+1)
  • Portability: Open standards (+1) ; No proprietary-SDK lock-in (+1) ; Self-hostable (+1) ; Open source (+1)
Signals not researched

These gaps cover the fields used in the AI-native score.

  • Integration surfaces: llms.txt, Headless signup, Native connectors
  • Trust & data policy: Trust center, Multi-factor authentication, Zero data retention, No generative AI training, Hard budget caps, Sandbox environment, Data export, Data import, Standard protocol access, Documented provider swap
  • Security & compliance: Compliance certifications, Access controls

Trust & data policy

Open standards
Yes
No proprietary-SDK lock-in
Yes
Self-hostable
Yes
Open source
Yes
Source code
https://github.com/mcp-box/mcpscore
Self-hosting guide
https://github.com/mcp-box/mcpscore#install

Not yet researched Trust center, Multi-factor authentication, Zero data retention, No generative AI training, Hard budget caps, Sandbox environment, Data export, Data import, Standard protocol access, Documented provider swap

What it does

Capabilities

  • MCP Server Auditing

    Audit an MCP server's protocol conformance and security posture.

    View 2 products

Jobs to be done

  • Audit an MCP server

    Evaluate an MCP server's compliance and security and get a machine-readable report.

    View 2 products

Integration surfaces

How an agent connects to this product and finds its documentation. The largest dimension of the AI-native score (35%).

WebMCP
No

Command-line interfaces

Developer kits

Confirmed absent MCP servers , Agent2Agent (A2A) servers , API specs , Agent skills

Not yet researched llms.txt, Headless signup, Native connectors

Offers

No offers recorded.

Reviews

No approved reviews yet.

RSS: approved reviews

Catalog activity

Track how this entry changes as proposals are opened and merged.

RSS: merged changes · RSS: open proposals

Products from other publishers that share a job-to-be-done or category, most-shared first.

  • MCP Server Registry and Security Scorer by George Kioko Unrated

    Same job: Audit an MCP server (not assessed)

  • Is Agentic by Vercel Tier D
    Agent Readiness Tools Developer Tools
  • AX Check by Gauge Tier D
    Agent Readiness Tools Developer Tools
  • anc by Brett Davies Unrated
    Agent Readiness Tools Developer Tools
  • Is Your Site Agent-Ready? by Cloudflare Unrated
    Agent Readiness Tools Developer Tools
  • Postmark by Postmark Tier B
    Developer Tools Email API / Transactional Email

Own this product? Add a directory badge to your site

Link your site back to this Open Agent Guide listing.

MCPscore — listed on Open Agent Guide MCPscore — listed on Open Agent Guide

HTML

<a href="https://www.openagentguide.com/organizations/mcp-box/products/mcpscore/?utm_source=badge&amp;utm_medium=referral">
  <img src="https://www.openagentguide.com/organizations/mcp-box/products/mcpscore/badge.svg" alt="MCPscore — listed on Open Agent Guide" height="64" />
</a>

Markdown

[![MCPscore — listed on Open Agent Guide](https://www.openagentguide.com/organizations/mcp-box/products/mcpscore/badge.svg?style=flat)](https://www.openagentguide.com/organizations/mcp-box/products/mcpscore/?utm_source=badge&utm_medium=referral)

The badge shows only that this product is listed; it makes no grade claim and can’t be self-set. How scoring works

Ready to decide?

Tier D · 27/100 AI-native · 42% researched.

Visit MCPscore