AI agents call read_graph 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 'read_graph' tool appears to query or retrieve data from a knowledge graph without modifying, deleting, or executing operations. No side effects are evident from the name or server context. Empty description lowers confidence slightly, but the name and pattern of sibling tools strongly indicate a Read category operation.
From the tool's definition Tool name is 'read_graph'; description is empty but the name and context of sibling tools (get_related, get_session) suggest this retrieves graph data. Sibling tools include create/delete operations, positioning read_graph as a retrieval operation.
Attacks that exploit this kind of access
read_graph. 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 read_graph: 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.
read_graph 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 read_graph 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 read_graph. 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.
read_graph 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 →