CustomGPT.ai MCP integration for AI agents.
Connect AI agents to CustomGPT.ai through 7 structured actions, including get agent, create conversation, and list agents. Review authentication, inputs, wor…
- ACTION CONTRACTS
- 7
- 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 CustomGPT.ai integration exposes
The CustomGPT.ai Agent App exposes 7 provider-backed actions for ai and productivity work. Its current contract lets an authorized agent get details and current status for a customgpt agent, create a customgpt conversation for an agent and return its session id, and list customgpt agents in the authenticated account with optional pagination. 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 CustomGPT.ai account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.
VERIFIED ACTION SAMPLE
Real CustomGPT.ai capabilities.
Showing 7 of 7 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
get_agentREADGet details and current status for a CustomGPT agent.
INPUTS: projectId / width / height
create_conversationWRITECreate a CustomGPT conversation for an agent and return its session ID.
INPUTS: projectId / name
list_agentsREADList CustomGPT agents in the authenticated account with optional pagination.
INPUTS: page / duration / order / orderBy / width
list_conversationsREADList conversations for a CustomGPT agent.
INPUTS: projectId / page / order / orderBy / userFilter
list_documentsREADList indexed documents in a CustomGPT agent knowledge base.
INPUTS: projectId / page / limit / order / search
list_messagesREADList messages in a CustomGPT conversation.
INPUTS: projectId / sessionId / page / order / includeInsights
send_messageWRITESend a non-streaming text prompt to a CustomGPT conversation and return the agent response.
INPUTS: projectId / sessionId / prompt / lang / externalId
INPUT CONTRACTS
Know what the action needs before it runs.
get_agent
projectIdREQUIRED- The unique CustomGPT agent identifier used in project path parameters.
widthOPTIONAL- Embed-code width to request from CustomGPT.
heightOPTIONAL- Embed-code height to request from CustomGPT.
create_conversation
projectIdREQUIRED- The unique CustomGPT agent identifier used in project path parameters.
nameOPTIONAL- Optional conversation name.
list_agents
pageOPTIONAL- Page number to retrieve. Page numbering starts at 1.
durationOPTIONAL- The duration filter for agents when supported by CustomGPT.
orderOPTIONAL- Sort direction for CustomGPT list results.
orderByOPTIONAL- CustomGPT field used to sort list results.
widthOPTIONAL- Embed-code width to request from CustomGPT.
list_conversations
projectIdREQUIRED- The unique CustomGPT agent identifier used in project path parameters.
pageOPTIONAL- Page number to retrieve. Page numbering starts at 1.
orderOPTIONAL- Sort direction for CustomGPT list results.
orderByOPTIONAL- CustomGPT field used to sort list results.
userFilterOPTIONAL- Conversation user-type filter.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Inspect Get Agent
Get details and current status for a CustomGPT agent. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.
get_agentControl Create Conversation
Create a CustomGPT conversation for an agent and return its session ID. Resolve the target first, present material changes for confirmation, and make retries idempotent where the provider supports it.
create_conversationVerify with List Agents
List CustomGPT agents in the authenticated account with optional pagination. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.
list_agentsSAFETY BOUNDARY
Operate CustomGPT.ai with explicit limits
- Authorize CustomGPT.ai with API key and grant only the provider access required by the selected actions.
- 2 actions are 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 CustomGPT.ai rather than assuming unrestricted access.
- After a call, inspect the structured result and execution record before reporting that the CustomGPT.ai task completed successfully.
CONNECTION MODEL
API key
CustomGPT API key sent as an Authorization Bearer token. Create it in the CustomGPT profile API tab: https://app.customgpt.ai/profile#api.
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
- 5
- WRITE SIGNALS
- 2
- 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 CustomGPT.ai.