Extract metadata from any webpage — title, description, Open Graph tags, Twitter Cards, JSON-LD structured data, favicon, canonical URL, and more.
AI agents call metadata to retrieve information from Junipr MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves publicly available metadata from webpages. It performs no write, delete, code execution, or financial operations. The blast radius of misuse is minimal—an agent could only gather information that is already publicly accessible on target URLs. No data is modified, deleted, or executed.
From the tool's definition Tool name is 'metadata' and description states it 'Extract[s] metadata from any webpage' — retrieves title, description, Open Graph tags, Twitter Cards, JSON-LD data, favicon, canonical URL.
Attacks that exploit this kind of access
Extract metadata from any webpage — title, description, Open Graph tags, Twitter Cards, JSON-LD structured data, favicon, canonical URL, and more. It is categorised as a Read tool in the Junipr MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Junipr MCP Server MCP server in PolicyLayer and add a rule for metadata: 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 Junipr MCP Server. Nothing to install.
metadata 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 metadata 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 metadata. 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.
metadata is provided by the Junipr MCP Server MCP server (junipr-labs/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 →