find_mentions
AI agents call find_mentions to retrieve information from Backlink SEO without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves or queries web pages and mentions—classic Read category behavior with no destructive, write, execute, or financial effects. Severity is low because misuse would only expose publicly available SEO/competitive intelligence data. Confidence is 0.85 (not higher) due to empty description for this specific tool, though server context is clear.
From the tool's definition Tool name 'find_mentions' combined with server description explicitly stating it 'surface[s] pages that mention a brand (linked or not)' indicates data retrieval.
Attacks that exploit this kind of access
find_mentions. It is categorised as a Read tool in the Backlink SEO MCP Server, which means it retrieves data without modifying state.
Register the Backlink SEO MCP server in PolicyLayer and add a rule for find_mentions: 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 Backlink SEO. Nothing to install.
find_mentions 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_mentions 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_mentions. 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_mentions is provided by the Backlink SEO MCP server (vipulawl/mcp-backlink-for-seo). 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 →