APIpie AI MCP integration for AI agents.
Connect AI agents to APIpie AI through 4 structured actions, including list detailed models, create chat completion, and create embedding. Review authenticat…
- ACTION CONTRACTS
- 4
- 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 APIpie AI integration exposes
The APIpie AI Agent App exposes 4 provider-backed actions for ai and developer tools work. Its current contract lets an authorized agent list detailed apipie ai model metadata available to the current api key, create a non-streaming apipie ai openai-compatible chat completion, and generate apipie ai embeddings for one or more text inputs. 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 APIpie AI account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.
VERIFIED ACTION SAMPLE
Real APIpie AI capabilities.
Showing 4 of 4 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
list_detailed_modelsREADList detailed APIpie AI model metadata available to the current API key.
create_chat_completionWRITECreate a non-streaming APIpie AI OpenAI-compatible chat completion.
INPUTS: model / messages / frequency_penalty / logit_bias / max_tokens
create_embeddingWRITEGenerate APIpie AI embeddings for one or more text inputs.
INPUTS: model / input / encoding_format / dimensions / user
list_modelsREADList the APIpie AI models available to the current API key.
INPUT CONTRACTS
Know what the action needs before it runs.
create_chat_completion
modelREQUIRED- The APIpie AI model identifier to use.
messagesREQUIRED- The ordered conversation history sent to the model.
frequency_penaltyOPTIONAL- The frequency penalty applied to repeated tokens.
logit_biasOPTIONAL- Any JSON object.
max_tokensOPTIONAL- The maximum number of tokens to generate.
create_embedding
modelREQUIRED- The APIpie AI embedding model identifier to use.
inputREQUIRED- The text input to embed.
encoding_formatOPTIONAL- The format of the returned embedding vectors.
dimensionsOPTIONAL- The number of dimensions in the output embedding vector.
userOPTIONAL- An end-user identifier for monitoring or abuse detection.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Inspect List Detailed Models
List detailed APIpie AI model metadata available to the current API key. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.
list_detailed_modelsControl Create Chat Completion
Create a non-streaming APIpie AI OpenAI-compatible chat completion. Resolve the target first, present material changes for confirmation, and make retries idempotent where the provider supports it.
create_chat_completionVerify with List Models
List the APIpie AI models available to the current API key. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.
list_modelsSAFETY BOUNDARY
Operate APIpie AI with explicit limits
- Authorize APIpie 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 APIpie AI rather than assuming unrestricted access.
- After a call, inspect the structured result and execution record before reporting that the APIpie AI task completed successfully.
CONNECTION MODEL
API key
APIpie AI API key used with the Authorization Bearer header. Create or manage keys at https://apipie.ai/profile/api-keys.
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
- 2
- 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 APIpie AI.