AI agents call c2pa_ingredients 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 designed exclusively for reading and analyzing C2PA (Coalition for Content Provenance and Authenticity) metadata from media files. The 'ingredients' concept in C2PA refers to source materials and references embedded in manifests—a read-only data structure. The tool retrieves and queries this metadata with no side effects, making it a Read category risk.
From the tool's definition Server description states 'reading C2PA content provenance manifests' and 'queries about AI-generated content, signatures, and provenance.' Tool name 'c2pa_ingredients' follows the pattern of sibling tools (c2pa_read, c2pa_info, c2pa_scan, c2pa_verify,…
Attacks that exploit this kind of access
c2pa_ingredients. 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_ingredients: 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_ingredients 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_ingredients 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_ingredients. 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_ingredients 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 →