prose_provenance
AI agents call prose_provenance to retrieve information from Librarian MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Provenance checking is fundamentally a read operation—it retrieves metadata about the source and history of content to verify authenticity or attribution. While the tool description is empty (lowering confidence slightly), the server context and naming strongly indicate this is a query/lookup function with no side effects. No financial, destructive, or execution risk is apparent.
From the tool's definition Tool name 'prose_provenance' suggests checking or querying the origin/source of prose content. Server description emphasizes 'provenance checking' as a core function.
Attacks that exploit this kind of access
prose_provenance. It is categorised as a Read tool in the Librarian MCP MCP Server, which means it retrieves data without modifying state.
Register the Librarian MCP server in PolicyLayer and add a rule for prose_provenance: 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 Librarian MCP. Nothing to install.
prose_provenance 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 prose_provenance 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 prose_provenance. 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.
prose_provenance is provided by the Librarian MCP server (liana-banyan/librarian-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 →