Get link statistics for a note
AI agents call graph_info to retrieve information from Connect MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and reports statistics about note connections within the vault. It performs no write, delete, execute, or financial operations. The blast radius of misuse is minimal—an agent might retrieve unwanted statistics about vault structure, but cannot modify data, run code, or cause irreversible changes. Classification as Read is appropriate with low severity.
From the tool's definition Tool description states 'Get link statistics for a note' — a retrieval operation with no modification or side effects. The verb 'Get' and the nature of 'link statistics' (metadata about existing connections) indicate read-only querying.
Attacks that exploit this kind of access
Get link statistics for a note. It is categorised as a Read tool in the Connect MCP MCP Server, which means it retrieves data without modifying state.
Register the Connect MCP server in PolicyLayer and add a rule for graph_info: 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 Connect MCP. Nothing to install.
graph_info 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_info 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_info. 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_info is provided by the Connect MCP server (joch/obsidian-connect-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 →