Skip to content
MCP server

VerifyAX

Register AI agents, generate scenarios and run simulation tests on VerifyAX

Install
Pricing
Free trial
Platforms
API, CLI
Runs
Locally or Remotely
Version
0.5.0
Listing updated
1 day ago

About VerifyAX

VerifyAX is an MCP server for ai models and llm tooling. It can run locally on your machine or as a hosted remote server.

VerifyAX is a platform for testing AI agents before and after deployment, and this server is its official bridge for MCP clients. Through chat you can register an agent (A2A or API) and confirm it is reachable, generate test scenarios from skill tags, run evaluations and read scores, transcripts and credit usage without polling.

The platform's pitch is simulation: you connect an agent, define what to test, and each run produces a report with scores, transcripts and recommendations, aimed at accuracy, safety, security and compliance. It also flags when re-testing is advisable because agent behaviour drifts as models change, and can fit into CI/CD.

Authentication is a VerifyAX API key rather than OAuth, so Claude.ai custom connectors must use the no sign-in option with an Authorization header. The server runs locally over stdio or as a hosted endpoint. The site describes a free trial and credit purchases with no monthly commitment.

Install

Run in a terminal

claude mcp add --transport http mcp-server https://mcp.verifyax.com/mcp

Add to Settings → Connectors → Add custom connector

https://mcp.verifyax.com/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "mcp-server": {
      "url": "https://mcp.verifyax.com/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "mcp-server": {
      "type": "http",
      "url": "https://mcp.verifyax.com/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "mcp-server": {
      "serverUrl": "https://mcp.verifyax.com/mcp"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "mcp-server": {
      "type": "http",
      "url": "https://mcp.verifyax.com/mcp"
    }
  }
}

Configuration

  • VERIFYAX_API_KEYVerifyAX API key (Settings -> API Keys in the console). Sent to the gateway as Authorization: Bearer.Required
  • VERIFYAX_MCP_LOG_LEVELLog verbosity written to stderr: debug | info | warn | error | silent (default info).

What it does

Agent registration
Register A2A or API agents and test connectivity.
Scenario generation
Create scenarios from skill tags.
Simulation runs
Run evaluations and read scores and transcripts.
Credit visibility
See credit usage per run.
Re-verification
Flags when an agent should be re-tested.
Audit reports
Scores, transcripts and recommendations.

Good for

  • Test a customer-service agent against edge cases
  • Add agent evaluations to CI/CD
  • Check an agent's safety behaviour
  • Compare scores across agent versions

Pricing

Free trial

Free trial; credits bought as needed, no monthly commitment

Prices change. Check verifyax.com before you buy.

VerifyAX FAQ

How does it authenticate?

With a VerifyAX API key sent as a bearer token.

Can I use it in Claude.ai?

Yes, as a custom connector with no sign-in and an Authorization header.

How is it priced?

Credits are bought as needed with no monthly commitment, and there is a free trial.

Which agent types?

A2A or API agents.

Is VerifyAX free?

VerifyAX is a paid product with a free trial.

How do I add VerifyAX to Claude Code?

Run this command in your terminal: claude mcp add --transport http mcp-server https://mcp.verifyax.com/mcp

What are the best alternatives to VerifyAX?

The closest alternatives to VerifyAX are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to VerifyAX

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools