Find a path of nodes from A to B (by id or label/type).
AI agents call graph-path to retrieve information from MCP Index Notes without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries existing graph data to discover relationships and paths between concepts. It has no side effects, does not modify the knowledge graph, and does not execute code or trigger external operations. It is a pure read operation consistent with search and query semantics.
From the tool's definition Tool performs a graph traversal query to find a path between two nodes, returning relational data without modifying, deleting, or executing external operations. Description indicates read-only retrieval: 'Find a path of nodes from A to B'.
Attacks that exploit this kind of access
Find a path of nodes from A to B (by id or label/type). It is categorised as a Read tool in the MCP Index Notes MCP Server, which means it retrieves data without modifying state.
Register the MCP Index Notes MCP server in PolicyLayer and add a rule for graph-path: 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 MCP Index Notes. Nothing to install.
graph-path 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 graph-path 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 graph-path. 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.
graph-path is provided by the MCP Index Notes MCP server (vjsr007/mcp-index-notes). 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 →