Returns the full definition of a named Cursor agent.
AI agents call cursor_get_agent to retrieve information from Clodbridge without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves configuration data about a Cursor agent. It does not create, modify, delete, or execute any operations—it only reads and returns existing definitions. The blast radius of misuse is minimal: exposing agent definitions could leak internal configuration details, but cannot directly harm systems or data.
From the tool's definition Tool returns the definition of a named agent; the verb 'get' and description 'returns' indicate a retrieval operation with no side effects. The sibling tools (cursor_get_*, cursor_list_*) all follow read-only patterns.
Attacks that exploit this kind of access
Returns the full definition of a named Cursor agent. It is categorised as a Read tool in the Clodbridge MCP Server, which means it retrieves data without modifying state.
Register the Clodbridge MCP server in PolicyLayer and add a rule for cursor_get_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 Clodbridge. Nothing to install.
cursor_get_agent 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 cursor_get_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 cursor_get_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.
cursor_get_agent is provided by the Clodbridge MCP server (rethunk-ai/clodbridge). 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 →