AI agents call c2pa_summary to retrieve information from Mtl C2pa without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The server's purpose is exclusively to read and query C2PA provenance metadata from media files. There is no mention of write, delete, or execute capabilities. The tool description is empty, but the context of a read-only C2PA manifest inspection tool and its sibling tools all being query/read operations justifies confident classification as Read with low severity.
From the tool's definition Tool is part of a C2PA manifest reading server. Sibling tools include 'c2pa_read', 'c2pa_verify', 'c2pa_assertions', 'c2pa_info', 'c2pa_ingredients', and 'c2pa_scan'—all of which are read/query operations on provenance manifests.
Attacks that exploit this kind of access
c2pa_summary. It is categorised as a Read tool in the Mtl C2pa MCP Server, which means it retrieves data without modifying state.
Register the Mtl C2pa MCP server in PolicyLayer and add a rule for c2pa_summary: 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 Mtl C2pa. Nothing to install.
c2pa_summary 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 c2pa_summary 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 c2pa_summary. 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.
c2pa_summary is provided by the Mtl C2pa MCP server (musictechlab/mtl-c2pa-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 →