lookup_paper
AI agents call lookup_paper to retrieve information from Cpp26 Adapter without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves reference data from a static corpus of C++ standards papers. It performs a lookup operation with no side effects—it neither modifies the papers, executes code, nor triggers external operations. The empty description slightly reduces confidence, but the server context and tool name are clear enough to classify this as a read-only query tool.
From the tool's definition Tool name 'lookup_paper' combined with server description indicating a 'reference' corpus of C++26 papers with 'lookup' and 'search' capabilities.
Attacks that exploit this kind of access
lookup_paper. It is categorised as a Read tool in the Cpp26 Adapter MCP Server, which means it retrieves data without modifying state.
Register the Cpp26 Adapter MCP server in PolicyLayer and add a rule for lookup_paper: 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 Cpp26 Adapter. Nothing to install.
lookup_paper 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 lookup_paper 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 lookup_paper. 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.
lookup_paper is provided by the Cpp26 Adapter MCP server (parasxos/cpp26-adapter). 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 →