Trent MCP integration for AI agents.
Connect AI agents to Trent through 1 structured actions, including send chat. Review authentication, inputs, workflows, and safety guidance.
- ACTION CONTRACTS
- 1
- AUTHENTICATION
- API key
- SOURCE STATUS
- Provider-backed
CATALOG SOURCE REVIEWED AUGUST 23, 2026 / ACTION NAMES AND SCHEMAS DERIVED FROM WORKING MACHINES PROVIDER SOURCE
CAPABILITY PROFILE
What the Trent integration exposes
The Trent Agent App exposes 1 provider-backed actions for ai and security work. Its current contract lets an authorized agent send one message to trent's chat endpoint and return the assembled response content plus thread metadata. These operations are called through Working Machines as typed capabilities rather than through browser navigation or copied UI steps.
A connection uses API key. Before execution, the agent can inspect the selected action, its required fields, declared scopes, and expected output contract. Provider credentials remain inside the Working Machines runtime; the calling agent receives the capability and its structured result, not the underlying secret.
For reliable operation, start with the narrowest action that satisfies the task, resolve stable provider identifiers before changing state, and validate the returned object or status after execution. Availability still depends on the connected Trent account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.
VERIFIED ACTION SAMPLE
Real Trent capabilities.
Showing 1 of 1 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
send_chatWRITESend one message to Trent's chat endpoint and return the assembled response content plus thread metadata.
INPUTS: message / context / thread_id / client_info
INPUT CONTRACTS
Know what the action needs before it runs.
send_chat
messageREQUIRED- The chat message or audit prompt to send to Trent.
contextOPTIONAL- Optional context string sent with the message.
thread_idOPTIONAL- Optional Trent thread ID for continuing an existing conversation.
client_infoOPTIONAL- Client metadata sent to Trent for attribution and troubleshooting.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Inspect Send Chat
Send one message to Trent's chat endpoint and return the assembled response content plus thread metadata. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.
send_chatControl Send Chat
Send one message to Trent's chat endpoint and return the assembled response content plus thread metadata. Resolve the target first, present material changes for confirmation, and make retries idempotent where the provider supports it.
send_chatVerify with Send Chat
Send one message to Trent's chat endpoint and return the assembled response content plus thread metadata. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.
send_chatSAFETY BOUNDARY
Operate Trent with explicit limits
- Authorize Trent with API key and grant only the provider access required by the selected actions.
- 1 action is change-capable by name. Confirm the target identity and material parameters before allowing a write.
- Do not infer permission from catalog visibility. Workspace policy, connection identity, and upstream authorization still govern execution.
- No provider scope string is declared on the sampled actions. Verify the connected account's actual permissions in Trent rather than assuming unrestricted access.
- After a call, inspect the structured result and execution record before reporting that the Trent task completed successfully.
CONNECTION MODEL
API key
Trent API key sent with the Authorization header. Get OpenClaw access and create your key from Trent's OpenClaw setup flow: https://trent.ai/openclaw/
Working Machines stores provider credentials behind the execution boundary. An agent can use an authorized connection identity, but catalog discovery alone does not reveal OAuth tokens, API keys, or provider secrets.
- READ SIGNALS
- 0
- WRITE SIGNALS
- 1
- HIGH IMPACT
- 0
- REVIEW SIGNALS
- 0
EVIDENCE AND AVAILABILITY
Provider reference
Action names, input fields, authentication types, and counts on this page are generated from the Working Machines provider catalog. Provider behavior, quotas, object semantics, account eligibility, and regional availability remain governed by Trent.