AI agents call lsfusion_retrieve_docs to retrieve information from Lsfusion without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves documentation via the RAG system with no side effects. The empty description lowers confidence slightly, but the server context (RAG-powered search, vector database) and naming convention ('retrieve') strongly indicate a read-only query operation. No data modification, execution, financial, or destructive actions are implied.
From the tool's definition Tool name contains 'retrieve' and sits within a documentation search server ('Enables RAG-powered documentation search'). The server description explicitly mentions 'documentation search' capabilities.
Attacks that exploit this kind of access
lsfusion_retrieve_docs. It is categorised as a Read tool in the Lsfusion MCP Server, which means it retrieves data without modifying state.
Register the Lsfusion MCP server in PolicyLayer and add a rule for lsfusion_retrieve_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 Lsfusion. Nothing to install.
lsfusion_retrieve_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 lsfusion_retrieve_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 lsfusion_retrieve_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.
lsfusion_retrieve_docs is provided by the Lsfusion MCP server (lsfusion/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 →