AI agents call get_capability_discovery 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 queries existing information about local CLI/MCP capabilities, profiles, and environment variables. It performs a search operation to discover information but does not modify, create, delete, execute commands, or perform any irreversible actions. This is a read-only operation with no side effects, placing it squarely in the Read category.
From the tool's definition The tool 'get_capability_discovery' is described as 'Search local CLI/MCP capabilities, profiles, and env vars by keyword.' The verb 'search' and the informational nature of discovering/querying capabilities, profiles, and environment variables indicate data…
Attacks that exploit this kind of access
Search local CLI/MCP capabilities, profiles, and env vars by keyword. 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_capability_discovery: 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_capability_discovery 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_capability_discovery 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_capability_discovery. 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_capability_discovery 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 →