AgentPMT-Workflow-Skills

AgentPMT Workflow Skills - Fetch, Search, and Use Agent Workflows and Skills. Use to retrieve, initiate, and complete workflows.

SERVERAgentPMT - The Marketplace For Autonomous Agents SOURCEagentpmt/agentic-marketplace

High RISK CLASS

Category Execute

Parameters 80 required

Recommended Rate-limitedsee the rule below

Registry record Grade C, identity unverified Pull the record →

This record as markdown: /tools/agentpmt-agentic-marketplace/agentpmt-workflow-skills.md

WHAT IT DOES

What AgentPMT-Workflow-Skills does on AgentPMT - The Marketplace For Autonomous Agents

AI agents invoke AgentPMT-Workflow-Skills to trigger actions in AgentPMT - The Marketplace For Autonomous Agents. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

Parameter	Type	Required	Description
`skip`	integer	—	Number of results to skip for pagination
`limit`	integer	—	Maximum results to return (1-200)
`query`	string	—	Optional substring search over name/description (case-insensitive)
`action`	string	—	Operation to perform: search, get_workflow_skill, start_workflow, end_workflow, get_active_workflow, get_instructions
`rating`	integer	—	Workflow rating from 1-5 stars (required for end_workflow)
`comment`	string	—	Comment about the workflow experience (required for end_workflow)
`skill_id`	string	—	Skill chain ObjectId (required for get_workflow_skill, start_workflow, end_workflow)
`suggested_improvements`	string	—	Suggested improvements or changes to the workflow (optional)

Parameters from the server's own tool schema.

RISK

Why AgentPMT-Workflow-Skills is rated High

While the tool includes a read/search component ('Fetch, Search'), its primary purpose includes initiating and completing workflows, which constitutes executing external operations with effects that depend on arguments. Workflows can span communication, data modification, file management, and more, making misuse potentially high-impact across multiple domains.

From the tool's definition 'retrieve, initiate, and complete workflows' — the tool triggers and executes agent workflows and skills, not merely reading data

Risk signalsAccepts freeform code/query input (query)

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs AgentPMT-Workflow-Skills safely

PolicyLayer is an MCP gateway: it sits between your AI agents and AgentPMT - The Marketplace For Autonomous Agents, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For AgentPMT-Workflow-Skills, this is the rule to start with:

AgentPMT-Workflow-Skills Rate-limited

AgentPMT-Workflow-Skills stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "AgentPMT-Workflow-Skills": {
      "limits": [
        {
          "counter": "agentpmt-workflow-skills_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect AgentPMT - The Marketplace For Autonomous Agents, apply this rule, and every AgentPMT-Workflow-Skills call is checked against it from then on.

FAQ

Questions about AgentPMT-Workflow-Skills

What does the AgentPMT-Workflow-Skills tool do? +

AgentPMT Workflow Skills - Fetch, Search, and Use Agent Workflows and Skills. Use to retrieve, initiate, and complete workflows. It is categorised as a Execute tool in the AgentPMT - The Marketplace For Autonomous Agents MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

What parameters does AgentPMT-Workflow-Skills accept? +

AgentPMT-Workflow-Skills accepts 8 parameters: skip, limit, query, action, rating, comment, skill_id, suggested_improvements. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on AgentPMT-Workflow-Skills? +

Register the AgentPMT - The Marketplace For Autonomous Agents MCP server in PolicyLayer and add a rule for AgentPMT-Workflow-Skills: 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 AgentPMT - The Marketplace For Autonomous Agents. Nothing to install.

What risk level is AgentPMT-Workflow-Skills? +

AgentPMT-Workflow-Skills is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit AgentPMT-Workflow-Skills? +

Yes. Add a rate_limit block to the AgentPMT-Workflow-Skills 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 AgentPMT-Workflow-Skills completely? +

Set action: deny in the PolicyLayer policy for AgentPMT-Workflow-Skills. 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 AgentPMT-Workflow-Skills? +

AgentPMT-Workflow-Skills is provided by the AgentPMT - The Marketplace For Autonomous Agents MCP server (agentpmt/agentic-marketplace). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on AgentPMT - The Marketplace For Autonomous Agents, and thousands of servers like it.

This server

All 4 AgentPMT - The Marketplace For Autonomous Agents tools → High-risk tools on this server →

Across the catalogue

All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →