Weld Agentic Access
Weld exposes 65 API operations that an AI agent could call, of which 33 are state-changing ‘acting’ operations. This is a recommended x-agentic-access execution contract — the scope, audience, consequence tier, short-lived token constraints, and escalation each action should carry before it is handed to an autonomous agent.
By consequence: 32 read and 33 safety-critical.
33 operations are classed safety-critical and should require human-in-the-loop approval at runtime.
Contracts are classified heuristically from the provider’s OpenAPI and refresh on every APIs.io network build; audience is bound per deployment. The model follows Curity’s Access Intelligence (apidays Munich 2026). Browse every provider’s agent contracts at agentic-access.apis.io.
By consequence
Highest-consequence actions
The physical and safety-critical operations an agent could invoke — the ones that most warrant scoped tokens, tight TTLs, and escalation. Full per-operation contracts are in the source below.
| Method | Path | Consequence | Human-in-loop |
|---|---|---|---|
| POST | /connection_bridges | safety-critical | required |
| DELETE | /connections/{id} | safety-critical | required |
| POST | /custom_reports | safety-critical | required |
| DELETE | /elt_streams/{id} | safety-critical | required |
| POST | /elt_streams/{id}/cancel_full_refresh | safety-critical | required |
| POST | /elt_streams/{id}/request_full_refresh | safety-critical | required |
| POST | /elt_streams/{id}/request_run | safety-critical | required |
| POST | /elt_syncs | safety-critical | required |
| POST | /elt_syncs/{id} | safety-critical | required |
| DELETE | /elt_syncs/{id} | safety-critical | required |
| POST | /elt_syncs/{id}/disable | safety-critical | required |
| POST | /elt_syncs/{id}/enable | safety-critical | required |
| POST | /elt_syncs/{id}/orchestration | safety-critical | required |
| DELETE | /elt_syncs/{id}/orchestration | safety-critical | required |
| POST | /elt_syncs/{id}/source_streams | safety-critical | required |
| POST | /orchestrations/{id}/request_run | safety-critical | required |
| POST | /reverse_etl_failed_records/retry | safety-critical | required |
| POST | /reverse_etl_failed_records/retry_all | safety-critical | required |
| POST | /reverse_etl_syncs | safety-critical | required |
| POST | /reverse_etl_syncs/settings_schema | safety-critical | required |
| POST | /reverse_etl_syncs/{id} | safety-critical | required |
| DELETE | /reverse_etl_syncs/{id} | safety-critical | required |
| POST | /reverse_etl_syncs/{id}/activate | safety-critical | required |
| POST | /reverse_etl_syncs/{id}/deactivate | safety-critical | required |
| POST | /reverse_etl_syncs/{id}/request_run | safety-critical | required |
Source
Agentic Access
Work with this as data
Every access contract here is available over the APIs.io API and to AI agents over MCP. Agentic Access is not yet its own endpoint on the v1 API. Reach it through catalog search and the tag graph, or the MCP server.