StewAI is an MCP server with 14 tools an agent can call, among them check_recipe_build, commit_recipe_build, discover_stewai. It answers at https://api.stewai.com/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 10 September 2026; the last check, on 19 October 2026, succeeded.
Discover, run, inspect, build, test, and privately reuse AI workflows.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
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. Inputs: build_ref, fixtures, render_only |
commit_recipe_build | Preflight and privately publish only the exact fully qualified recipe revision. Inputs: build_ref, revision, mode, commit_capability, idempotency_key |
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_buil Inputs: build_ref, view, node_id, node_type, model_id, schema_name |
get_recipe_build_activity | Poll a review or acceptance batch through a bounded, disclosure-safe view. Inputs: activity_ref, cursor, section |
get_recipe_preview | Inspect a safe summary, or page complete authorized published details and executable contracts with view=details. Concatenate content fragments in offset order per section; decode JSON sections after completion. Use next_cursor with the sam Inputs: recipe_ref, view, cursor |
get_results | Read declared outputs or a sanitized per-step trace from an owned run, including signed chunks for oversized steps. Inputs: run_id, view, cursor, limit, step_id, chunk_ref |
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. Inputs: run_id, view, recipe_ref, status, cursor, limit |
review_recipe_build | Quote or run a bounded semantic quality review of the exact private draft revision. Inputs: build_ref, revision, mode, idempotency_key |
run_recipe | Estimate or run a previewed public or account-authorized published recipe. Inputs: recipe_ref, inputs, idempotency_key, dry_run |
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; r Inputs: build_ref, revision, mode, case_ids, idempotency_key |
search_recipes | Find safe public recipes and published recipes available to the current account. Inputs: query, sources, required_inputs, required_outputs, runnable_only |
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 Inputs: name, intent, input_contract, output_contract, capabilities, risk_domains |
update_recipe_build | Apply bounded optimistic changes to an owned private recipe build. If ops appear as unknown, first read get_recipe_build view='authoring_schema', schema_name='update_recipe_build'; read schema_name='acceptance_suite' for all behavioral asse |
Every block below points at https://api.stewai.com/mcp. Pick your client and copy.
claude mcp add --transport http stewai https://api.stewai.com/mcp
{
"mcpServers": {
"stewai": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://api.stewai.com/mcp"]
}
}
}{
"mcpServers": {
"stewai": {
"url": "https://api.stewai.com/mcp"
}
}
}{
"servers": {
"stewai": {
"type": "http",
"url": "https://api.stewai.com/mcp"
}
}
}{
"context_servers": {
"stewai": {
"url": "https://api.stewai.com/mcp"
}
}
}{
"mcpServers": {
"stewai": {
"serverUrl": "https://api.stewai.com/mcp"
}
}
}{
"mcpServers": {
"stewai": {
"url": "https://api.stewai.com/mcp"
}
}
}name: StewAI
version: 0.0.1
schema: v1
mcpServers:
- name: StewAI
type: streamable-http
url: https://api.stewai.com/mcp{
"mcpServers": {
"stewai": {
"httpUrl": "https://api.stewai.com/mcp"
}
}
}{
"mcpServers": {
"stewai": {
"type": "http",
"url": "https://api.stewai.com/mcp"
}
}
}{
"mcpServers": {
"stewai": {
"url": "https://api.stewai.com/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fapi.stewai.com%2Fmcp&type=streamable_http&id=stewai&name=StewAI
It answered our last check on 19 October 2026 in 288 ms. Over 6 checks since 10 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by stewai.com and served from api.stewai.com, the vendor's own domain: https://api.stewai.com/mcp.
14, as returned by the server's own tools/list on 11 September 2026: check_recipe_build, commit_recipe_build, discover_stewai, get_recipe_build, get_recipe_build_activity, get_recipe_preview, get_results, get_run, and 6 more.
It answered our last check on 19 October 2026 in 288 ms. Over 6 checks since 10 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://api.stewai.com/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: com.stewai. Endpoint host: api.stewai.com. ARD identifier: urn:air:com.stewai:mcp:stewai.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.