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.

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

High RISK CLASS

Category Execute

Parameters 90 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-tool-search-and-execution.md

WHAT IT DOES

What AgentPMT-Tool-Search-and-Execution does on AgentPMT - The Marketplace For Autonomous Agents

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.

Parameter	Type	Required	Description
`page`	integer	—	Page number for pagination (1-based). Used when listing tools.
`query`	string	—	Search query for text and semantic matching. If provided, performs hybrid search.
`action`	string	—	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	—	Custom message to include in credential request notification (for request_credentials action)
`tool_id`	string	—	Tool/product ID (required for get_schema and use actions)
`page_size`	integer	—	Number of results per page (1-100)
`tool_name`	string	—	Alternative: Tool name to search for (for use action, searches then executes first match)
`parameters`	object	—	Parameters to pass to the tool when using 'use' action
`workflow_id`	string	—	Workflow/skill chain ID. If provided, returns all tools from that workflow.

Parameters from the server's own tool schema.

RISK

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 definition 'Search and Execution - Unified interface for discovering, searching, and using AgentPMT tools' and 'Access tools required for workflows and skills here'

Risk signalsAccepts freeform code/query input (query)

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs AgentPMT-Tool-Search-and-Execution 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-Tool-Search-and-Execution, this is the rule to start with:

AgentPMT-Tool-Search-and-Execution Rate-limited

AgentPMT-Tool-Search-and-Execution 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-Tool-Search-and-Execution": {
      "limits": [
        {
          "counter": "agentpmt-tool-search-and-execution_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-Tool-Search-and-Execution call is checked against it from then on.

FAQ

Questions about AgentPMT-Tool-Search-and-Execution

What does the AgentPMT-Tool-Search-and-Execution tool do? +

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. 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-Tool-Search-and-Execution accept? +

AgentPMT-Tool-Search-and-Execution accepts 9 parameters: page, query, action, message, tool_id, page_size, tool_name, parameters, workflow_id. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on AgentPMT-Tool-Search-and-Execution? +

Register the AgentPMT - The Marketplace For Autonomous Agents MCP server in PolicyLayer and add a rule for AgentPMT-Tool-Search-and-Execution: 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-Tool-Search-and-Execution? +

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

Can I rate-limit AgentPMT-Tool-Search-and-Execution? +

Yes. Add a rate_limit block to the AgentPMT-Tool-Search-and-Execution 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-Tool-Search-and-Execution completely? +

Set action: deny in the PolicyLayer policy for AgentPMT-Tool-Search-and-Execution. 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-Tool-Search-and-Execution? +

AgentPMT-Tool-Search-and-Execution 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

generate_and_execute_test on Percepta MCP Server → All high-risk MCP tools → The MCP Attack Database →

Guides

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