Load an agent's system prompt and contract from the RC.
AI agents call get_agent_context to retrieve information from Metis Public Health without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only operation that retrieves configuration or prompt data. Loading system prompts and contracts does not create, modify, delete, or execute code; it simply queries and returns information. The blast radius is minimal since viewing agent configuration poses no operational risk to the system or data integrity.
From the tool's definition The tool 'get_agent_context' is described as 'Load an agent's system prompt and contract from the RC' — the verb 'Load' indicates retrieval/query of existing data with no modification or side effects.
Attacks that exploit this kind of access
Load an agent's system prompt and contract from the RC. It is categorised as a Read tool in the Metis Public Health MCP Server, which means it retrieves data without modifying state.
Register the Metis Public Health MCP server in PolicyLayer and add a rule for get_agent_context: 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 Metis Public Health. Nothing to install.
get_agent_context is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_agent_context 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 get_agent_context. 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.
get_agent_context is provided by the Metis Public Health MCP server (sveritg/metis_ph). 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 →