append_recipe_build_upload
ChatGPTAppend one ordered UTF-8 text chunk to an existing private build upload.
approve_recipe_budget
ChatGPTRedeem one exact budget capability for one private build revision.
begin_recipe_build_upload
ChatGPTBegin one bounded chunked upload for a private recipe build.
bind_recipe_resource
ChatGPTApprove one exact frozen resource selector for a supervised acceptance handoff.
cancel_recipe_activity
ChatGPTCancel one supervised acceptance activity. Cancellation is irreversible.
check_recipe_build
ChatGPTRun free deterministic lint, render, policy, and compiler checks. Omit fixtures for the normal structural check; a supplied fixture probe must also provide every referenced upstream dependency value.
commit_recipe_acceptance_upload
ChatGPTVerify and commit one completed chunk upload as the full acceptance suite.
commit_recipe_build
ChatGPTPreflight and privately publish only the exact fully qualified recipe revision. A successful commit returns a private editor URL and, when current run access permits it, a recipe_ref. Preview that reference before any dry run: authoring contract handles and node IDs are not the positional input_N run handles. The recipe stays private, unlisted, and unreviewed; commit never lists, prices, or publishes it in the public marketplace.
commit_recipe_research_upload
ChatGPTVerify and commit one completed chunk upload as the build's research evidence.
commit_recipe_spec_upload
ChatGPTVerify and commit one completed chunk upload as the full recipe specification.
discover_stewai
ChatGPTLearn how any MCP agent can authenticate, discover, preview, run, author, qualify, commit, inspect, and recover StewAI recipes. Call this first.
estimate_recipe_run
ChatGPTEstimate one previewed recipe without starting it. Return historical charges, fees, wallet balance, admission status, and the safety ceiling when one can be calculated.
get_recipe_acceptance_plan
ChatGPTRead or page through the behavioral acceptance plan for one private build.
get_recipe_activity_billing
ChatGPTRead billing results for one recipe build activity.
get_recipe_activity_coverage
ChatGPTRead coverage results for one recipe build activity.
get_recipe_authoring_guidance
ChatGPTRead versioned authoring rules and matched archetype guidance for one private build.
get_recipe_build
ChatGPTList or inspect only the authenticated creator's private recipe builds. To list builds omit both build_ref and view; limit/cursor paginate that list. With or without build_ref, use view='authoring_schema' and schema_name='update_recipe_build', 'acceptance_suite', or 'start_recipe_build' to read the complete executable JSON Schema when a client hides nested operation or assertion fields. Large acceptance_plan reads return data.suite_page JSON fragments: append content in offset order, pass data.next_cursor as cursor until null, then parse the complete suite and verify its sha256. Small plans retain data.suite. Use view='capabilities' to discover the complete 24-handler authoring and automatic-acceptance capability catalog.
get_recipe_build_activity
ChatGPTPoll a review or acceptance batch through a bounded, disclosure-safe view.
get_recipe_build_contracts
ChatGPTRead the declared input and output contracts of one private build.
get_recipe_build_node
ChatGPTRead one node from a private build by its exact node identifier.
get_recipe_build_research
ChatGPTRead the research policy, tier, and recorded evidence for one private build.
get_recipe_build_schemas
ChatGPTRead the named JSON schemas stored in one private build.
get_recipe_capability
ChatGPTRead the complete contract for one supported recipe node type.
get_recipe_details
ChatGPTRead the authorized published details and executable contracts for one opaque recipe reference. Follow next_cursor until null. This tool never executes a recipe.
get_recipe_model
ChatGPTRead the authoring contract for one exact model identifier.
get_recipe_preview
ChatGPTInspect a safe summary with bounded method and limitations excerpts, output-contract state, and evidence context. For complete authorized published details and executable contracts, use view=details. Concatenate content fragments in offset order per section; decode JSON sections after completion. Use next_cursor with the same recipe_ref until null. Opaque internals remain withheld.
get_results
ChatGPTAfter a finished run, read view=steps with detail=full first and follow next_cursor; every step the user paid for is part of the result. Declared outputs are the pinned summary, not the whole result. Read declared outputs or a sanitized per-step trace from an owned run, including signed chunks for oversized steps. view=steps returns compact summaries, 10 per page by default and at most 20 (limit 1-20); follow next_cursor until it is null, pass detail=full for whole steps, or use view=step with step_id for one full step. Open recipes expose all authorized steps; closed recipes expose only input and output steps. Sensitive values stay redacted. Step reads are provisional until get_run reports a finished status. If outputs is empty, read view=steps; for a failed run, read the failed step and let the user decide. Present completed outputs as polished Markdown or text: lead with the useful outcome, add At a glance, supported strengths, impact-ordered findings, and concrete next steps; end with evidence, uncertainty, limitations, charged credits, and a clickable run link using run_url with the run ID as its label. Render JSON as readable tables or bullets and HTML as content, not markup. Cross-check material claims against supplied source and cited evidence; describe unsupported or high-stakes conclusions as findings to verify. Say blocking only when the recipe explicitly classifies the item that way and evidence supports it. Keep diagnostics, safety ceilings, and platform plumbing out of the main answer; billing receipt issues stay quiet and never suppress ready results.
get_run
ChatGPTRead an owned run, view=history to resume normal runs (recipe_ref/status/cursor/limit), or view=diagnostics for its settled UI receipt. Default status requires run_id.
get_run_diagnostics
ChatGPTRead settled billing diagnostics for one owned run.
get_run_step
ChatGPTRead one sanitized full step result from an owned run by exact step identifier.
get_run_step_chunk
ChatGPTRead one signed continuation chunk for an oversized run step result.
list_recipe_activity_assertions
ChatGPTPage through assertion results for one recipe acceptance activity.
list_recipe_activity_nodes
ChatGPTPage through node-level results for one recipe build activity.
list_recipe_build_activities
ChatGPTList recent review and acceptance activities for one private build.
list_recipe_build_capabilities
ChatGPTPage through the supported authoring capabilities for one private build.
list_recipe_build_handoffs
ChatGPTList supervised acceptance handoffs for one private build.
list_recipe_build_nodes
ChatGPTList node identifiers and node types in one private build.
list_recipe_build_resources
ChatGPTList resource requirements from the newest handoff for one private build.
list_recipe_builds
ChatGPTList recent private recipe builds owned by the authenticated creator.
list_recipe_capability_types
ChatGPTList the supported recipe node capability types.
list_recipe_models
ChatGPTList models available to recipe authoring.
list_run_steps
ChatGPTPage through sanitized step summaries or full step results from one owned run.
list_runs
ChatGPTList recent runs owned by the authenticated account, with optional recipe and status filters.
preflight_recipe_build
ChatGPTVerify commit readiness and issue a short-lived commit capability for one exact qualified build revision.
quote_recipe_acceptance
ChatGPTQuote selected or complete behavioral acceptance cases without starting them.
quote_recipe_review
ChatGPTQuote the bounded semantic review of one exact private build revision without starting it.
record_recipe_research
ChatGPTReplace the bounded research evidence recorded for one private build.
render_recipe_build
ChatGPTRender one private recipe build with optional fixture values without executing it.
restore_recipe_build
ChatGPTRestore one archived private recipe build at an exact revision.
resume_recipe_activity
ChatGPTResume one approved supervised acceptance activity; this may spend credits and call external providers.
review_recipe_build
ChatGPTQuote or run a bounded semantic quality review of the exact private draft revision.
run_recipe
ChatGPTExecute a previewed recipe using its opaque reference and synthetic input handles.
run_recipe_acceptance
ChatGPTQuote or run selected or complete behavioral acceptance cases for an exact private draft revision. Quotes explain enforced input bounds, output caps and retry allowances in acceptance_cost. Preserve representative fixtures and assertions; remove unnecessary model stages rather than weakening tests to lower a quote. Paid work requires an approved budget. A full run that needs user approval returns supervised_required before any case, reservation, or external effect; first bind every returned required resource with update_recipe_build bind_resource, then open action_url for user approval, and finally resume the same activity with update_recipe_build resume_activity.
search_recipes
ChatGPTFind safe public recipes and published recipes available to the current account. results are direct fits (exact or strong); related_results are adjacent recipes, not direct fits. Each row states its output contract, past-run cost history and, for reviewed public recipes, that safety review is not output-quality validation. required_inputs and required_outputs match exact handles or normalized labels, never meanings. When paging.has_more is true, repeat the identical call with cursor=next_cursor.
set_recipe_acceptance_cases
ChatGPTReplace the complete behavioral acceptance suite of one private build.
set_recipe_contracts
ChatGPTReplace the declared input and output contracts of one private build.
set_recipe_metadata
ChatGPTReplace selected name, description, UI, or comment metadata on one private build.
start_recipe_build
ChatGPTCreate a private recipe build from a bounded intent and declared contract. Recipe inputs are strings: use type:string, positive maxLength, and only minLength:1 on required inputs. Richer input constraints must be handled in recipe logic and tested, not claimed as enforced by the input node. The response returns the stored contracts when they fit the bounded result; the archetype bundle is optional guidance, not the build contract. Optionally provide source_recipe_ref to adapt an owned recipe or a fully viewable public-open recipe into a new private draft.
update_recipe_build
ChatGPTReplace the complete executable specification of one private recipe build at an exact revision. This overwrites the prior draft specification.
check_recipe_build
Claudecommit_recipe_build
Claudediscover_stewai
Claudeget_recipe_build
Claudeget_recipe_build_activity
Claudeget_recipe_preview
Claudeget_results
Claudeget_run
Claudereview_recipe_build
Clauderun_recipe
Clauderun_recipe_acceptance
Claudesearch_recipes
Claudestart_recipe_build
Claudeupdate_recipe_build
Claude