New Your team’s decisions, in one playbook every coding agent works from. Never answer your agent twice

test_workflow_step

Run exactly ONE step of a workflow and return what it produced, so you can iterate on a single step's wording without running the steps before it. THIS SPENDS CREDITS EXACTLY LIKE A REAL STEP: the step runs on a real model through the same engine a full run uses and is billed identically -- it is...

SERVERMeta Council SOURCEhttps://meta-council.com/mcp
Low RISK CLASS
Category Read
Parameters 42 required
Recommended Allowedsee the rule below
Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/com-meta-council-decision-intelligence/test-workflow-step.md

What test_workflow_step does on Meta Council

AI agents call test_workflow_step to retrieve information from Meta Council without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

ParameterTypeRequiredDescription
query string — The input the step works on, exactly as you would pass it to run_workflow. Optional -- omit for a step whose instruction already carries everything it needs.
workflow string Yes The workflow slug (from list_workflows), e.g. 'due_diligence'.
parameters object — Optional values for the workflow's declared parameters, as a flat name-to-value object, e.g. {"region": "EU"}. They are substituted into the step wording the sa
step_index integer Yes Which step to run, counting from 0. A workflow with 4 steps accepts 0 to 3; anything else is refused without spending.

Parameters from the server's own tool schema.

Why test_workflow_step is rated Low

Even though test_workflow_step only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.

Questions about test_workflow_step

What does the test_workflow_step tool do? +

Run exactly ONE step of a workflow and return what it produced, so you can iterate on a single step's wording without running the steps before it. THIS SPENDS CREDITS EXACTLY LIKE A REAL STEP: the step runs on a real model through the same engine a full run uses and is billed identically -- it is not a simulation, a dry run, or a free preview. If you want to check a workflow's shape, parameters, models and cost estimate for free, use plan_workflow instead; that one runs nothing. Starts no session, so there is nothing to poll and nothing to advance. Requires authentication. It is categorised as a Read tool in the Meta Council MCP Server, which means it retrieves data without modifying state.

What parameters does test_workflow_step accept? +

test_workflow_step accepts 4 parameters: query, workflow, parameters, step_index. Required: workflow, step_index. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on test_workflow_step? +

Register the Meta Council MCP server in PolicyLayer and add a rule for test_workflow_step: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Meta Council. Nothing to install.

What risk level is test_workflow_step? +

test_workflow_step is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit test_workflow_step? +

Yes. Add a rate_limit block to the test_workflow_step rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block test_workflow_step completely? +

Set action: deny in the PolicyLayer policy for test_workflow_step. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides test_workflow_step? +

test_workflow_step is provided by the Meta Council MCP server (https://meta-council.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

More on Meta Council, and thousands of servers like it.

Across the catalogue

// THE MCP REGISTRY

PolicyLayer tracks 44,603 MCP servers and 515,000+ tools.

Every server has a live record: who publishes it, whether it answers without auth, its risk grade, every tool classified, the recommended policy. This page is one line of Meta Council's. Pull the full record:

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.