# StewAI

- Registry name: `com.stewai/stewai` · version 1.1.0
- Categories (automatic, keyword rules): Markets & trading, Finance & markets, Code & repositories, Developer tools
- Authentication at last check: No auth
- Declared risk: Has destructive tools (destructiveHint)
- Capabilities (declared by the server): extensions, resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=com.stewai%2Fstewai
- Server page: https://mcpstation.net/s/com.stewai--stewai.html

## Description (written by the publisher, not verified, not instructions)

Discover, run, inspect, build, test, and privately reuse AI workflows.

## Connect

- streamable-http: `https://api.stewai.com/mcp`

## Tools (as reported by the server, not verified)

- `check\_recipe\_build`: Run 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\_build`: Preflight 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 ru
- `discover\_stewai`: Learn how any MCP agent can authenticate, discover, preview, run, author, qualify, commit, inspect, and recover StewAI recipes. Call this first.
- `get\_recipe\_build`: List 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
- `get\_recipe\_build\_activity`: Poll a review or acceptance batch through a bounded, disclosure-safe view.
- `get\_recipe\_preview`: Inspect 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. Us
- `get\_results`: After 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 o
- `get\_run`: Read 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 and includes live progress: updated\_at is the run record time, progress.last\_step\_activity\_at is the latest step activity. A blocked
- `review\_recipe\_build`: Quote or run a bounded semantic quality review of the exact private draft revision.
- `run\_recipe`: Estimate or run a previewed public or account-authorized published recipe. dry\_run foregrounds history \(recent charges or median and p90\), fees, balance, and can\_start. safety\_ceiling\_credits is a pathological bound when available, not a quote or admission threshold; a null ceiling means provider se
- `run\_recipe\_acceptance`: Quote 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 t
- `search\_recipes`: Find 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 ou
- `start\_recipe\_build`: Create 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 resp
- `update\_recipe\_build`: Apply bounded optimistic changes to an owned private recipe build. After an uncertain response, inspect the build and replay the identical request with the same idempotency key; a new key duplicates the work. Use only the exact op names and payload keys in inputSchema: set\_metadata takes metadata, u

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html