Agent Status
MCP
WebMCP
Industries
Rankings
Pricing
Resources
AgentStatus
  • Discoverability See what AI says about your business. Bring your own MCP / WebMCP Add the MCP or WebMCP you already run. Selling through AI Put your products where AI agents can use them.
  • How it works
  • Pricing
  • Featured · September 2026

    State of MCP Reliability in Production

    We tested every public MCP server we could find. Calling is solved. Delivery is not.

    Read the report

    Research

    MCP Protocol Era report All reports

    Guides

    MCP Validation Buyer’s Guide MCP Reliability Playbook All guides

    Thoughts

    The blog
    Help FAQ
Sign in Start with $4.67 trial

Legal / Responsible disclosure

Security

Responsible disclosure

Effective November 20, 2026. Last updated November 20, 2026.

Contents

IntroductionHow to reportScopeSafe harborContact

In short

Send good-faith reports to legal@carmel.so. Denial-of-service, social engineering, and accessing other people's data are out of scope. This is not a bug-bounty program unless one is later published.

1. Introduction

We welcome good-faith reports of security vulnerabilities in AgentStatus. This page tells you how to report one, and what we ask you not to do. It is not a bug-bounty program unless we later publish one.

2. How to report

Send a report to legal@carmel.so. Include the affected URL or endpoint, a short description, and the steps needed to reproduce the issue. Do not include more customer data than is needed to show the issue.

We will try to acknowledge a report.

3. Scope

In scope, at a high level, are the AgentStatus website, the dashboard, and the public API that we operate. Out of scope are denial-of-service or flood testing, social engineering or phishing of our staff or customers, physical attacks, and access to data that is not yours. Do not modify or delete data that is not yours, and do not use a finding to move further through the system than is needed to show the issue.

4. Safe harbor

If you report in good faith, follow this page, and do not access more data than needed, we do not intend to bring a claim against you for that report. This is not permission to break the law.

5. Contact

Security reports and legal questions: legal@carmel.so.

An AI agent should use your business as easily as a person can.

Start with $4.67 trial
AgentStatus

Product

  • Discoverability
  • Bring your own MCP
  • Selling through AI
  • How it works
  • Pricing

Resources

  • Research
  • Guides
  • Thoughts
  • FAQ

Company

  • Privacy
  • Terms
Copyright 2026 Carmel Labs, Inc.agentstatus.dev

Cover your blind spots.

We show which tools connect across hosts, which ones break, and what to fix first.

Build an MCPBuild a WebMCP
Agent Status

Independent validation for MCP servers. We sit outside the host and the server.

Product

  • MCP overview
  • Build
  • Connection
  • Discoverability
  • Live Traffic
  • Tool classes
  • Contract
  • Host Compatibility
  • Apps
  • Multi-step
  • Supported hosts
  • Pricing
  • Developers

Index

  • MCP Index
  • MCP Methodology
  • WebMCP Index
  • WebMCP Methodology
  • TOA (MCP extension)

Resources

  • Guides & references
  • Thoughts
  • MCP reliability report
  • Help Center
  • FAQ

Company

  • Funding
  • About
  • Contact
  • LinkedIn

Legal

  • Privacy Policy
  • Terms of Service

Copyright © 2026 Carmel Labs, Inc.
All rights reserved.