AI agents call get_system_prompt_tool to retrieve information from CoordMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The name indicates this tool retrieves or queries a system prompt without modifying it. No description is provided, reducing confidence slightly, but the naming strongly suggests a read-only operation. Read operations have low severity in the context of coordination server access, as they do not alter state or trigger external actions.
From the tool's definition Tool name 'get_system_prompt_tool' suggests retrieval of a system prompt, which is a read operation. The description is empty, limiting direct evidence of its exact behavior.
Attacks that exploit this kind of access
get_system_prompt_tool. It is categorised as a Read tool in the CoordMCP MCP Server, which means it retrieves data without modifying state.
Register the Coord MCP server in PolicyLayer and add a rule for get_system_prompt_tool: 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 CoordMCP. Nothing to install.
get_system_prompt_tool 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_system_prompt_tool 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_system_prompt_tool. 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_system_prompt_tool is provided by the Coord MCP server (siddiquesahabaj/coordmcp). 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 →