AI agents call get_agent_adapter_doc to retrieve information from Todos without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and returns adapter documentation for specific agents. It performs a query/fetch operation without modifying, creating, deleting, or executing any external operations. The blast radius is minimal as misuse would only result in the agent reading documentation it shouldn't have access to, not in data modification or financial impact.
From the tool's definition Tool name 'get_agent_adapter_doc' and description 'Get full local adapter doc for codex, claude-code, or takumi' indicate retrieval of documentation only.
Attacks that exploit this kind of access
Get full local adapter doc for codex, claude-code, or takumi. It is categorised as a Read tool in the Todos MCP Server, which means it retrieves data without modifying state.
Register the Todos MCP server in PolicyLayer and add a rule for get_agent_adapter_doc: 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 Todos. Nothing to install.
get_agent_adapter_doc 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_adapter_doc 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_adapter_doc. 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_adapter_doc is provided by the Todos MCP server (@hasna/todos). 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 →