AI agents call rc_get_fishbone to retrieve information from Rootcause without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves an existing Fishbone diagram (a visual representation of causal factors in root cause analysis) without modifying, deleting, or executing any operations. The verb 'Get' confirms read-only access. No side effects or external operations are triggered. The data returned is educational/analytical in nature within a medical education context, posing minimal risk if accessed by an AI agent.
From the tool's definition Tool name 'rc_get_fishbone' and description 'Get the complete Fishbone diagram for a session' indicate a retrieval operation that queries and returns structured root cause analysis data.
Attacks that exploit this kind of access
Get the complete Fishbone diagram for a session. It is categorised as a Read tool in the Rootcause MCP Server, which means it retrieves data without modifying state.
Register the Rootcause MCP server in PolicyLayer and add a rule for rc_get_fishbone: 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 Rootcause. Nothing to install.
rc_get_fishbone 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 rc_get_fishbone 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 rc_get_fishbone. 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.
rc_get_fishbone is provided by the Rootcause MCP server (u9401066/rootcause-mcp). 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 →