# AgentPMT-Tool-Search-and-Execution

AgentPMT Tool Search and Execution - Unified interface for discovering, searching, and using AgentPMT tools without MCP refresh. Access tools required for workflows and skills here.

Agent View of the PolicyLayer registry record for `AgentPMT-Tool-Search-and-Execution`. HTML page: https://policylayer.com/tools/agentpmt-agentic-marketplace/agentpmt-tool-search-and-execution

## Facts

- Tool: `AgentPMT-Tool-Search-and-Execution`
- Server: AgentPMT - The Marketplace For Autonomous Agents (`agentpmt/agentic-marketplace`) — https://policylayer.com/tools/agentpmt-agentic-marketplace.md
- Homepage: https://github.com/agentpmt/agentic-marketplace
- Risk category: Execute (High risk)
- Registry record: grade C, identity unverified
- Server rate-limited: no
- Parameters: 9
- Recommended policy verdict: Rate-limited

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `page` | integer | no | Page number for pagination (1-based). Used when listing tools. |
| `query` | string | no | Search query for text and semantic matching. If provided, performs hybrid search. |
| `action` | string | no | Operation to perform: get_tools (discover tools - list/search/workflow), get_schema (full tool schema by ID), request_credentials (email user to add credentials |
| `message` | string | no | Custom message to include in credential request notification (for request_credentials action) |
| `tool_id` | string | no | Tool/product ID (required for get_schema and use actions) |
| `page_size` | integer | no | Number of results per page (1-100) |
| `tool_name` | string | no | Alternative: Tool name to search for (for use action, searches then executes first match) |
| `parameters` | object | no | Parameters to pass to the tool when using 'use' action |
| `workflow_id` | string | no | Workflow/skill chain ID. If provided, returns all tools from that workflow. |

Parameters from the server's own tool schema.

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "AgentPMT-Tool-Search-and-Execution",
    "arguments": {}
  }
}
```

## Why AgentPMT-Tool-Search-and-Execution is rated High

This tool both discovers and executes arbitrary AgentPMT tools on demand. The 'execution' capability means it can trigger any downstream tool in the ecosystem — spanning communication, data analytics, development, file management, and more — making the blast radius extremely broad.

From the tool's own definition: "'Search and Execution - Unified interface for discovering, searching, and using AgentPMT tools' and 'Access tools required for workflows and skills here'"

Risk signals: Accepts freeform code/query input (query)

## Use case

AI agents invoke AgentPMT-Tool-Search-and-Execution 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.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches AgentPMT - The Marketplace For Autonomous Agents:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "AgentPMT-Tool-Search-and-Execution": {
      "limits": [
        {
          "counter": "agentpmt-tool-search-and-execution_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on AgentPMT - The Marketplace For Autonomous Agents (3)

- `AgentPMT-Workflow-Skills` — Execute — https://policylayer.com/tools/agentpmt-agentic-marketplace/agentpmt-workflow-skills.md
- `AgentPMT-Send-Human-Request` — Other — https://policylayer.com/tools/agentpmt-agentic-marketplace/agentpmt-send-human-request.md
- `AgentPMT-Report-Tool-Issue` — Write — https://policylayer.com/tools/agentpmt-agentic-marketplace/agentpmt-report-tool-issue.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=agentpmt-agentic-marketplace · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/agentpmt-agentic-marketplace