VerifyAX MCP
Enables conversational access to the VerifyAX agent-evaluation platform, exposing tools for agent evaluation workflows through natural language.
README
VerifyAX MCP
Conversational access to the VerifyAX agent-evaluation platform, plus the typed SDK it is built on. Two packages in one pnpm monorepo:
| Package | Description |
|---|---|
@verifyax/sdk |
Typed TypeScript client for the VerifyAX REST API. Reusable by any consumer. |
@verifyax/mcp-server |
MCP server exposing 12 VerifyAX tools mapped to user intents. Built on the SDK. |
This complements (does not replace) the verifyax-api skill:
the skill is for developers writing code; the MCP server is for conversational workflows.
Install the MCP server
Requires Node ≥ 20 and a VerifyAX API key (Settings → API Keys in the console).
Claude Code:
claude mcp add verifyax --env VERIFYAX_API_KEY=sk-ver-api-... -- npx -y @verifyax/mcp-server
Claude Desktop (claude_desktop_config.json):
{
"mcpServers": {
"verifyax": {
"command": "npx",
"args": ["-y", "@verifyax/mcp-server"],
"env": { "VERIFYAX_API_KEY": "sk-ver-api-..." }
}
}
}
Restart the client, then describe what you want. See
packages/mcp-server for the full tool list and configuration.
What you can ask
Once installed, just describe the task — Claude picks the tool:
- “List the skill tags I can use for an interview scenario on VerifyAX.”
- “Register the A2A agent at https://my-agent.example.com and run a quick interview eval.”
- “Generate an info_exchange scenario tagged empathy and coordination, then show me the scores.”
- “What did my last 5 simulation runs cost?”
Blocking tools (generate_scenario, evaluate_agent) poll internally and return only when the
work completes (typically 30s–5min) — no manual status checks.
Troubleshooting
- “VERIFYAX_API_KEY is not set” — the key isn’t reaching the server. Check the
envblock in your MCP client config. - Authentication failed — the key is invalid, revoked, or from the wrong environment. Mint a fresh one in the console.
- Tool calls don’t appear — MCP clients load tools at startup; restart the client (or start a new session) after adding the server.
- Want logs? Set
VERIFYAX_MCP_LOG_LEVEL=debug. Logs are structured JSON on stderr; stdout is reserved for the MCP protocol.
Status
See PLAN.md for the phased execution plan and CLAUDE.md for project
context and architecture decisions. Contributions welcome — see CONTRIBUTING.md.
Development
Requires Node ≥ 20 and pnpm 10.
pnpm install # install workspace dependencies
pnpm build # build all packages (topological order)
pnpm test # run unit tests
pnpm lint # lint
pnpm format # format with prettier
Network-dependent suites: pnpm test:integration (live API, needs VERIFYAX_TEST_KEY) and
pnpm test:conformance (spawns the built MCP server over stdio).
Privacy
The MCP server sends no telemetry. It talks only to the VerifyAX API using the key you
provide via VERIFYAX_API_KEY.
License
Apache-2.0. See LICENSE.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.