AI agents call c2pa_scan 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 tool is part of an MCP server explicitly designed for reading and querying C2PA provenance data from media files. 'Scan' in this context refers to analyzing or examining manifest contents, consistent with the server's stated purpose of 'enabling natural language queries about AI-generated content, signatures, and provenance.' No side effects, modifications, deletions, or financial operations are indicated.
From the tool's definition Tool name 'c2pa_scan' on a server described as 'reading C2PA content provenance manifests' with sibling tools all prefixed 'c2pa_' that perform read operations (c2pa_read, c2pa_info, c2pa_verify, c2pa_assertions, c2pa_ingredients, c2pa_summary).
Attacks that exploit this kind of access
c2pa_scan. 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_scan: 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_scan 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_scan 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_scan. 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_scan 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 →