AI agents call c2pa_assertions 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 appears to retrieve or query assertions within C2PA provenance manifests based on server context. No description is provided, which slightly lowers confidence, but the pattern of read-only operations on immutable provenance data and the absence of any modifying language suggests this is a retrieval function with no side effects. Reading provenance metadata poses low risk even if misused.
From the tool's definition Server is described as 'for reading C2PA content provenance manifests' and sibling tools include read/query operations (c2pa_read, c2pa_info, c2pa_scan, c2pa_verify, c2pa_summary).
Attacks that exploit this kind of access
c2pa_assertions. 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_assertions: 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_assertions 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_assertions 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_assertions. 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_assertions 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 →