USE THIS to find Salesforce metadata similar to a given node OR a free-text concept. Hybrid search: fuses MiniLM-L6 vector similarity (semantic) with an FTS5 keyword leg (exact-name recall) via reciprocal rank fusion. Two modes: (1) pass
AI agents call find_similar to retrieve information from Sfgraph without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is purely a read operation that retrieves and ranks existing metadata based on similarity matching. It has no capability to modify, delete, or execute anything. The worst-case misuse would be information disclosure of existing metadata already in the knowledge graph, which is low risk compared to other categories.
From the tool's definition The tool 'find_similar' searches for Salesforce metadata using hybrid vector and full-text search. The description states it is used to 'find' metadata 'similar to a given node OR a free-text concept' and performs 'MiniLM-L6 vector similarity (semantic)' and…
Attacks that exploit this kind of access
USE THIS to find Salesforce metadata similar to a given node OR a free-text concept. Hybrid search: fuses MiniLM-L6 vector similarity (semantic) with an FTS5 keyword leg (exact-name recall) via reciprocal rank fusion. Two modes: (1) pass. It is categorised as a Read tool in the Sfgraph MCP Server, which means it retrieves data without modifying state.
Register the Sfgraph MCP server in PolicyLayer and add a rule for find_similar: 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 Sfgraph. Nothing to install.
find_similar 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 find_similar 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 find_similar. 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.
find_similar is provided by the Sfgraph MCP server (ryanstark24/sfgraph). 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 →