prismic_get_refs
AI agents call prismic_get_refs to retrieve information from Prismic Content MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name follows the standard 'get' convention for read operations. Although the description is empty, the naming pattern and the context of sibling tools that are all retrieval-based operations strongly suggest this retrieves reference data from Prismic (likely document refs, release refs, or similar metadata). This is a query/retrieval operation with no side effects.
From the tool's definition Tool named 'prismic_get_refs' with 'get' prefix, consistent with sibling tools that are all read operations (prismic_get_document, prismic_get_documents, prismic_get_media, prismic_get_releases, prismic_get_repository_context, prismic_get_shared_slice,…
Attacks that exploit this kind of access
prismic_get_refs. It is categorised as a Read tool in the Prismic Content MCP MCP Server, which means it retrieves data without modifying state.
Register the Prismic Content MCP server in PolicyLayer and add a rule for prismic_get_refs: 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 Prismic Content MCP. Nothing to install.
prismic_get_refs 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 prismic_get_refs 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 prismic_get_refs. 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.
prismic_get_refs is provided by the Prismic Content MCP server (rahulpowar/prismic-content-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 →