get_my_agents

List your saved agents with their IDs, API keys, and status. Agents are saved locally when created via create_agent. Also fetches latest status from the server.

SERVERConviction SOURCEabcxz/conviction-fm

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade D, identity unverified Pull the record →

This record as markdown: /tools/abcxz-conviction-fm/get-my-agents.md

WHAT IT DOES

What get_my_agents does on Conviction

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

RISK

Why get_my_agents is rated Low

This is a Read operation—it queries and retrieves data (agent configurations, identifiers, and state) without creating, modifying, or deleting anything. However, the severity is elevated to 'medium' rather than 'low' because the tool exposes sensitive authentication credentials (API keys), which could enable account takeover or unauthorized agent manipulation if disclosed to an attacker.

From the tool's definition The tool 'get_my_agents' explicitly lists agents with their IDs, API keys, and status. The description states it 'List[s] your saved agents' and 'Fetches latest status from the server', indicating retrieval without modification.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs get_my_agents safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Conviction, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For get_my_agents, this is the rule to start with:

get_my_agents Allowed

get_my_agents is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "get_my_agents": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Conviction, apply this rule, and every get_my_agents call is checked against it from then on.

FAQ

Questions about get_my_agents

What does the get_my_agents tool do? +

List your saved agents with their IDs, API keys, and status. Agents are saved locally when created via create_agent. Also fetches latest status from the server. It is categorised as a Read tool in the Conviction MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_my_agents? +

Register the Conviction MCP server in PolicyLayer and add a rule for get_my_agents: 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 Conviction. Nothing to install.

What risk level is get_my_agents? +

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

Can I rate-limit get_my_agents? +

Yes. Add a rate_limit block to the get_my_agents 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 get_my_agents completely? +

Set action: deny in the PolicyLayer policy for get_my_agents. 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 get_my_agents? +

get_my_agents is provided by the Conviction MCP server (abcxz/conviction-fm). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Conviction, and thousands of servers like it.

This server

All 10 Conviction tools →

Across the catalogue

get_cocktail_by_category on Cocktails RAG MCP Server →get_torrent_detail on M-Team MCP Server →aiva_get_affiliate on AIVA MCP Server →get-chuck-categories on Jokes MCP Server → The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →