librarian_context
AI agents call librarian_context 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.
Based on the server's purpose of providing memory, provenance checking, and metrics (all read-oriented functions), and the tool name suggesting context retrieval, this is classified as a Read operation. The empty description prevents higher confidence, but the broader server context strongly indicates this is a data retrieval tool with no side effects, making it low severity.
From the tool's definition Tool name 'librarian_context' suggests retrieving contextual information from a library system. Server description emphasizes 'pre-curated canonical memory' and 'provenance checking', implying data retrieval and lookup functions.
Attacks that exploit this kind of access
librarian_context. 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 librarian_context: 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.
librarian_context 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 librarian_context 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 librarian_context. 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.
librarian_context 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 →