AI agents call c2pa_read 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 a C2PA (Coalition for Content Provenance and Authenticity) reading/verification server. The 'read' naming convention combined with the server's stated purpose of reading manifests and the read-only nature of sibling verification/query tools (scan, verify, summary, info) indicates this performs data retrieval with no side effects.
From the tool's definition Tool name 'c2pa_read' with server purpose of 'reading C2PA content provenance manifests from media files' and sibling tools (c2pa_assertions, c2pa_info, c2pa_ingredients, c2pa_scan, c2pa_summary, c2pa_verify) all indicate query/retrieval operations without…
Attacks that exploit this kind of access
c2pa_read. 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_read: 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_read 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_read 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_read. 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_read 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 →