Self-register this agent with AgentForge. Returns an af_agent_* API key that unlocks broadcast_search and call_tool. Run once at agent startup, store the key in env as AGENTFORGE_API_KEY. No auth required for registration. Idempotent on slug — running twice produces a uniqued slug.
AI agents use register_agent to create or update resources in Agentforge Trust — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Agentforge Trust environment.
This tool creates/modifies state by registering an agent and issuing API credentials. While the description notes it is 'idempotent on slug' (suggesting repeated calls may be handled gracefully), the primary function is to write a registration record to a system. This is a Write operation rather than Execute because it doesn't trigger external operations dependent on variable arguments—it simply enrolls the agent.
From the tool's definition Tool description states 'Self-register this agent with AgentForge' and 'Returns an af_agent_* API key that unlocks broadcast_search and call_tool', indicating it creates a new registration record and generates credentials.
Attacks that exploit this kind of access
Self-register this agent with AgentForge. Returns an af_agent_* API key that unlocks broadcast_search and call_tool. Run once at agent startup, store the key in env as AGENTFORGE_API_KEY. No auth required for registration. Idempotent on slug — running twice produces a uniqued slug. It is categorised as a Write tool in the Agentforge Trust MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Agentforge Trust MCP server in PolicyLayer and add a rule for register_agent: 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 Agentforge Trust. Nothing to install.
register_agent is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the register_agent 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.
Set action: deny in the PolicyLayer policy for register_agent. 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.
register_agent is provided by the Agentforge Trust MCP server (kovy/agentforge-trust-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →