BigML MCP integration for AI agents.
Connect AI agents to BigML through 6 structured actions, including get model, create prediction, and delete prediction. Review authentication, inputs, workfl…
- ACTION CONTRACTS
- 6
- 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 BigML integration exposes
The BigML Agent App exposes 6 provider-backed actions for ai and data work. Its current contract lets an authorized agent retrieve compact bigml model metadata and field definitions needed for prediction input, submit a json prediction against an existing bigml model, and permanently delete one stored bigml prediction resource. 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 BigML account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.
VERIFIED ACTION SAMPLE
Real BigML capabilities.
Showing 6 of 6 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
get_modelREADRetrieve compact BigML model metadata and field definitions needed for prediction input.
INPUTS: modelId / fieldLimit / fieldOffset
create_predictionWRITESubmit a JSON prediction against an existing BigML model.
INPUTS: modelId / inputData / name / description / project
delete_predictionHIGH IMPACTPermanently delete one stored BigML prediction resource.
INPUTS: predictionId
get_predictionREADRetrieve the status and result of one BigML prediction.
INPUTS: predictionId
list_modelsREADList existing BigML supervised models with compact status details.
INPUTS: limit / offset / orderBy / project / nameContains
list_predictionsREADList stored BigML prediction resources.
INPUTS: limit / offset / orderBy / project / nameContains
INPUT CONTRACTS
Know what the action needs before it runs.
get_model
modelIdREQUIRED- A model identifier as model/ID or a bare ID.
fieldLimitOPTIONAL- The maximum fields to return.
fieldOffsetOPTIONAL- The field offset.
create_prediction
modelIdREQUIRED- A model identifier.
inputDataREQUIRED- Prediction input values.
nameOPTIONAL- An optional prediction name.
descriptionOPTIONAL- An optional description.
projectOPTIONAL- An optional project identifier.
delete_prediction
predictionIdREQUIRED- A prediction identifier.
get_prediction
predictionIdREQUIRED- A prediction identifier.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Inspect Get Model
Retrieve compact BigML model metadata and field definitions needed for prediction input. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.
get_modelControl Create Prediction
Submit a JSON prediction against an existing BigML model. Resolve the target first, present material changes for confirmation, and make retries idempotent where the provider supports it.
create_predictionVerify with Get Prediction
Retrieve the status and result of one BigML prediction. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.
get_predictionSAFETY BOUNDARY
Operate BigML with explicit limits
- Authorize BigML 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.
- Treat `delete_prediction` as high-impact operations and require an explicit approval boundary.
- No provider scope string is declared on the sampled actions. Verify the connected account's actual permissions in BigML rather than assuming unrestricted access.
- After a call, inspect the structured result and execution record before reporting that the BigML task completed successfully.
CONNECTION MODEL
API key
BigML API key sent as the api_key query parameter. Copy it from https://bigml.com/account/apikey
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
- 4
- WRITE SIGNALS
- 1
- HIGH IMPACT
- 1
- 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 BigML.