XERJ
Searches documents in a concrete authorized index on your external XERJ node through its query DSL API.
What it provides
Connect an HTTPS data-service API. Storage remains external; use a tenant-scoped token and namespace on the target service. Requires your own HTTPS node and an index-scoped encoded API key. Storage and optional neural models stay on that node.
Connection requirements
Run your own XERJ node outside the bot and publish its API through HTTPS with authentication enabled. Ask the owner to mint an API key whose role_descriptors grant read on the concrete index you will search, with no wildcard names or admin privileges. Keep Bearer selected and paste the returned encoded value (base64 of id:secret), not the raw secret or node admin key. Replace INDEX_NAME with that allowed index. Neural search models are optional and remain on your external node; the example uses ordinary query DSL.
- Protocol
- REST / OpenAPI
- Endpoint
https://xerj.example.com- Authentication
- bearer
get /_security/_authenticatepost /INDEX_NAME/_search '{"size":5,"query":{"match":{"content":"deployment rollback"}}}'Where to add it
Open Dashboard Tools, select a running OpenClaw or Hermes instance, then use the card’s Install or Connect action. External services may require an HTTPS endpoint and credentials; the dashboard shows those fields before anything is saved.