List all graph pages in the current Origin project with name, type, and layer count.
AI agents call tool_list_graphs to retrieve information from origin-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a query operation to enumerate and inspect existing graphs. It returns metadata without side effects, making it clearly a Read category risk. The scope is limited to one Origin project instance, and misuse would only leak information about existing visualizations, presenting minimal risk even if an AI agent were to call it unexpectedly.
From the tool's definition tool_list_graphs retrieves information about graph pages in the current project (name, type, layer count) with no modification, deletion, or execution of operations. The verb 'list' and the read-only nature of querying metadata are definitive.
Attacks that exploit this kind of access
List all graph pages in the current Origin project with name, type, and layer count. It is categorised as a Read tool in the origin-MCP MCP Server, which means it retrieves data without modifying state.
Register the origin- MCP server in PolicyLayer and add a rule for tool_list_graphs: 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 origin-MCP. Nothing to install.
tool_list_graphs 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 tool_list_graphs 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 tool_list_graphs. 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.
tool_list_graphs is provided by the origin- MCP server (zhang-923-ze/origin-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 →