AI agents call get_related to retrieve information from Rawthink without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs semantic search to retrieve related historical information from the knowledge graph. It retrieves data without modifying, deleting, or executing external operations. The blast radius of misuse is minimal—an agent could retrieve irrelevant or sensitive past context, but cannot modify or destroy data. This is a straightforward Read operation.
From the tool's definition Tool name is 'get_related' and description states 'Find related past thoughts — quick semantic search.' This is a query/search operation with no modification capabilities.
Attacks that exploit this kind of access
Find related past thoughts — quick semantic search. It is categorised as a Read tool in the Rawthink MCP Server, which means it retrieves data without modifying state.
Register the Rawthink MCP server in PolicyLayer and add a rule for get_related: 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 Rawthink. Nothing to install.
get_related 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_related 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_related. 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_related is provided by the Rawthink MCP server (ygtalp/rawthink-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 →