Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@AWP MCP Server Generate an agent.json for my customer support website"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Give your AI assistant native knowledge of the Agent Web Protocol.
This MCP server provides Claude Code (and any MCP-compatible AI tool) with direct access to the AWP specification, a validator, and a generator for agent.json files.
Add to your Claude Code MCP configuration (~/.claude/mcp.json):
{
"mcpServers": {
"awp": {
"command": "npx",
"args": ["awp-mcp-server"]
}
}
}Restart Claude Code. Your assistant now has these tools:
Related MCP server: MCP Server for OSCAL
Tool | Description |
| Get the full AWP specification |
| Validate an agent.json file |
| Generate an agent.json from parameters |
| Get example agent.json files |
| Step-by-step implementation guide |
Once installed, just ask Claude Code naturally:
"Generate an agent.json for my API"
"Validate my agent.json"
"What fields does agent.json support?"
"Make my site agent-ready"
MIT
This server cannot be deployed
Trust signals for AI agents: an open agent-readiness standard and developer tool guide. Read-only.
Public agentic AI doctrine tools plus authenticated architecture, design, and spec validators.
Real-time Amazon, WIPO & PACER data for AI agents — 19 tools via the MCP protocol.
A registry of AI agent tools — MCP servers, APIs, CLIs, SDKs — kept current by automated ingestion.
