Search ProudNet documentation for specific topics
AI agents call search_proudnet_docs to retrieve information from ProudNet Document MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and searches documentation without modifying, executing code, deleting data, or creating financial obligations. It has no side effects beyond information retrieval. The low severity reflects minimal harm from misuse—worst case being exposure of already-public documentation or excessive API calls.
From the tool's definition Tool name 'search_proudnet_docs' and description 'Search ProudNet documentation for specific topics' indicate a query-only operation over documentation.
Attacks that exploit this kind of access
Search ProudNet documentation for specific topics. It is categorised as a Read tool in the ProudNet Document MCP MCP Server, which means it retrieves data without modifying state.
Register the ProudNet Document MCP server in PolicyLayer and add a rule for search_proudnet_docs: 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 ProudNet Document MCP. Nothing to install.
search_proudnet_docs 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 search_proudnet_docs 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 search_proudnet_docs. 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.
search_proudnet_docs is provided by the ProudNet Document MCP server (nettention/proudnet-document-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 →