Extract and analyze metadata from files (images, PDFs, Office docs):
AI agents call metadata_analysis to retrieve information from MCP OSINT Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Metadata extraction is fundamentally a query/retrieval operation. It does not create, modify, delete, execute code, or trigger external systems. The metadata analysis itself is local file inspection with no destructive or financial implications. Even in an OSINT context, this is passive reconnaissance.
From the tool's definition Tool performs 'Extract and analyze metadata from files' — a read-only operation that retrieves information from existing files without modifying them. No side effects or state changes.
Attacks that exploit this kind of access
Extract and analyze metadata from files (images, PDFs, Office docs):. It is categorised as a Read tool in the MCP OSINT Server MCP Server, which means it retrieves data without modifying state.
Register the MCP OSINT Server MCP server in PolicyLayer and add a rule for metadata_analysis: 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 MCP OSINT Server. Nothing to install.
metadata_analysis 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_analysis 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_analysis. 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_analysis is provided by the MCP OSINT Server MCP server (lliwi/osint-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 →