// SCAN REPORT

Workflows

13 tools. 6 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 12 Jun 2026

6 can modify or destroy data

7 read-only

13 tools total

Community server · catalogue entry verified 12/06/2026

How to control Workflows ↓

TOOL MAP

What Workflows exposes to your agents

Read (7) Write / Execute (5) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Workflows tools

Destructive · High cancel_job Cancelling a job is typically an irreversible action: a running or queued job that is cancelled cannot be 'uncancelled' and its in-progress work is lost. Execute · High execute_inline_workflow This tool executes workflows (likely arbitrary YAML-defined logic), which can trigger external operations and side effects depending on workflow content. Execute · High execute_workflow This tool executes workflows—external operations whose side effects are determined by workflow content and arguments. Execute · High resume_workflow The tool name 'resume_workflow' strongly implies continuing/resuming a paused or suspended workflow execution.

6 of Workflows's 13 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Workflows

PolicyLayer is an MCP gateway — it sits between your AI agents and Workflows, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "cancel_job": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "project_sync": {
    "limits": [
      {
        "counter": "project_sync_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_job_status": {
    "limits": [
      {
        "counter": "get_job_status_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Workflows — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON WORKFLOWS →

Free to start. No card required.

FULL CATALOGUE

All 13 Workflows tools

DESTRUCTIVE 1 tools

Destructive cancel_job cancel_job

EXECUTE 4 tools

Execute execute_inline_workflow execute_inline_workflow Execute execute_workflow execute_workflow Execute project_onboard project_onboard Execute resume_workflow resume_workflow

WRITE 1 tools

Write project_sync project_sync

READ 7 tools

Read get_job_status get_job_status Read get_queue_stats Get metrics about job and IO queue health. Read get_workflow_info get_workflow_info Read get_workflow_schema get_workflow_schema Read list_jobs list_jobs Read list_workflows list_workflows Read validate_workflow_yaml validate_workflow_yaml

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Workflows

Can an AI agent delete data through the Workflows MCP server? +

Yes. The Workflows server exposes 1 destructive tools including cancel_job. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Workflows? +

The Workflows server has 1 write tools including project_sync. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Workflows.

How many tools does the Workflows MCP server expose? +

13 tools across 4 categories: Destructive, Execute, Read, Write. 7 are read-only. 6 can modify, create, or delete data.

How do I enforce a policy on Workflows? +

Register the Workflows MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Workflows tool call.

Deterministic rules across all 13 Workflows tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON WORKFLOWS →

Free to start. No card required.

13 Workflows tools catalogued and risk-classified — across an index of 43,000+ MCP servers.