Wiro MCP Server

Official

Overview Schema Source Related Servers Discussions Admin

Create a Wiro workflow

create_workflow

Saves a new private workflow in your API key's workspace from a step graph, validates it against the live model catalog, fills defaults, and returns its slug, link, and input keys.

Instructions

Save a new private workflow in the API key's workspace from a step graph. Read get_playbook topic "workflow-graph" first: it has the graph format, the reference syntax and examples. Check every model's parameter ids and values with get_model_schema: a model step's values, such as a duration, a size or an option, are checked when that step runs. Wiro checks the graph against the live model catalog, fills catalog defaults and lays the steps out before saving; every problem it finds comes back together, so fix them all and call again. Set every model input you care about: a left-out one gets the model's default (the Notes in the result list what was filled). The graph can be at most 40 KB of JSON with those defaults. Free. Each call creates another workflow. The result gives the full slug, the page link and the input keys, so no get_workflow call is needed to run it.

Input Schema

Name	Required	Description
`tags`	No	Up to 20 tags.
`title`	Yes	Workflow title (1-160 characters).
`contents`	Yes	The workflow graph (version "1"): {version, nodes, output, schema, metadata}. Read get_playbook topic "workflow-graph" for the format and an example.
`description`	No	What the workflow does (up to 1000 characters).

Output Schema

Name	Required	Description	Default
`url`	Yes
`state`	No
`title`	Yes
`inputs`	Yes
`outputs`	Yes
`renamed`	Yes
`fullSlug`	Yes
`warnings`	Yes
`nextAction`	No
`updatetime`	No

Schema Changelog

Changes observed during successful MCP inspections.

Addedv1.4.1Nov 1, 2026

TDQS

A4.8/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations cover the safety profile (non-readonly, non-idempotent, non-destructive), and the description adds substantial beyond-schema behavior: catalog validation against the live model catalog, default filling with Notes in the result, atomic error aggregation, a 40 KB size cap, and that the call is free.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Dense but front-loaded: creation semantics first, then prerequisites, then validation/defaults behavior, then limits and result. It is long and some clauses stack heavily, but nearly every sentence carries actionable information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a nested-graph creation tool with an available output schema, the description still describes the return (full slug, page link, input keys) and preempts the common failure mode, leaving no critical gap for an agent to call it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3; the description goes further by explaining that contents is a step graph, that model input values are validated at step run time, and that omitted inputs receive model defaults and are listed in Notes.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Save a new private workflow in the API key's workspace from a step graph') and clarifies scope with 'Each call creates another workflow', which separates it from update_workflow/clone_workflow/save_workflow_from_agent siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit prerequisites: read get_playbook topic 'workflow-graph' first, then verify model parameters with get_model_schema. It also tells the agent what to do on failure ('fix them all and call again') and that no get_workflow call is needed afterward.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.