AI agents call get_meta_tag to retrieve information from Ogimage without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool takes an OG image URL and returns HTML meta tag markup. It performs no write operations, does not execute code or commands, makes no external state changes, and does not delete or move data. It is purely a data retrieval/formatting operation, consistent with the 'Read' category. Severity is low because even if misused, generating a meta tag string has negligible blast radius.
From the tool's definition The tool 'generates the HTML meta tag for an OG image URL' — it retrieves or constructs metadata in a read-only format (HTML meta tag output) without modifying any data or triggering side effects.
Attacks that exploit this kind of access
Generate the HTML meta tag for an OG image URL. It is categorised as a Read tool in the Ogimage MCP Server, which means it retrieves data without modifying state.
Register the Ogimage MCP server in PolicyLayer and add a rule for get_meta_tag: 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 Ogimage. Nothing to install.
get_meta_tag 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 get_meta_tag 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 get_meta_tag. 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.
get_meta_tag is provided by the Ogimage MCP server (ogimage-art/mcp-server). 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 →