Read XMP metadata from an image with option for extended XMP segments
AI agents call read-xmp to retrieve information from Exif without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool extracts XMP (Extensible Metadata Platform) metadata from images. XMP metadata is informational content (author, keywords, copyright, etc.) stored within image files. The operation is purely read-only—it queries and retrieves metadata without altering the image, executing code, or affecting system state.
From the tool's definition Tool name 'read-xmp' and description 'Read XMP metadata from an image' indicate retrieval of data with no side effects. XMP is a metadata standard embedded in images; reading it does not modify, execute operations, or cause destructive changes.
Documented attack patterns abuse exactly the kind of access read-xmp gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Exif, and nothing reaches the server without passing your rules. This is the rule we recommend for read-xmp:
{
"version": "1",
"default": "deny",
"tools": {
"read-xmp": {}
}
}read-xmp is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Read XMP metadata from an image with option for extended XMP segments. It is categorised as a Read tool in the Exif MCP Server, which means it retrieves data without modifying state.
Register the Exif MCP server in PolicyLayer and add a rule for read-xmp: 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 Exif. Nothing to install.
read-xmp 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 read-xmp 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 read-xmp. 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.
read-xmp is provided by the Exif MCP server (stass/exif-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 7 Exif tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
7 Exif tools catalogued and risk-classified — across an index of 42,500+ MCP servers.