Lighthouse for AI agents — test if APIs and services are properly accessible to AI agents
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"agent-validator-mcp-server","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# Agent Interface Validator 🔍 **Lighthouse for AI agents** — test if APIs and services are properly accessible to AI agents. Get scores, grades, and actionable recommendations. ## Installation ```bash pip install agent-validator-mcp-server ``` ```json {"mcpServers": {"validator": {"command": "uvx", "args": ["agent-validator-mcp-server"]}}} ``` ## Tools | Tool | Description | |------|-------------| | `validate_api_endpoint` | Test a single API endpoint (score 0-100) | | `validate_openapi_spec` | Check an OpenAPI spec for agent-friendliness | | `check_agent_interface_url` | Check if a domain has an Agent Interface spec | ## License MIT
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.