EveryData

Use the MCP tools everyinfra_list_capabilities and everyinfra_call_api.

1. Call everyinfra_list_capabilities first. Pass platform when the platform is already known.
2. Select the exact platform and action from the returned catalog. Read required parameters, optional parameters, max_limit and current price. Use availability only when the catalog actually returns it; catalog membership alone is not proof that live inventory exists.
3. Put only catalog-declared parameters under params. Do not add other fields, and do not guess an action name.
4. Call everyinfra_call_api. Request the largest useful result within max_limit when that avoids needless repeated charges.
5. Treat empty, partial and failed results according to the response fields. Report the returned billing block rather than estimating cost from a stale document.

EveryData returns a normalized and redacted customer contract. Do not promise raw internal output, internal identifiers, private data, or fields not present in the live capability catalog.

To clean, label or summarize collected records, use EveryAI (everyinfra_chat), which is free for accounts that have topped up. The former data cleanup tools were retired on 2026-10-09.

Setup in OpenClaw

1. Create an API key at https://everyinfra.com/en/docs?utm_source=clawhub&utm_medium=directory&utm_campaign=listing_2026q4&utm_content=everydata#quickstart and export it as EVERYINFRA_API_KEY. Capability discovery needs no key; paid calls do.
2. Add the remote MCP server once: openclaw mcp add everyinfra --url https://api.everyinfra.com/mcp --transport streamable-http, then set its Authorization: Bearer header to the key in Settings -> MCP (keep the key out of config literals). Check it with openclaw mcp doctor everyinfra --probe.
3. The live MCP tool list is the runtime truth. EveryInfra failed or empty calls are reported in the response billing block; read it instead of assuming.