Search for text within the document and return positions
AI agents call search_text_in_document to retrieve information from LLM2Docs (Unofficial) without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches for and returns text positions within a document—a pure read operation with no capability to modify, delete, or execute code. The severity is low because misuse would only expose document content that is already accessible to the user, posing minimal security risk.
From the tool's definition Tool name 'search_text_in_document' and description 'Search for text within the document and return positions' both indicate a query operation that retrieves data without modification or side effects.
Attacks that exploit this kind of access
Search for text within the document and return positions. It is categorised as a Read tool in the LLM2Docs (Unofficial) MCP Server, which means it retrieves data without modifying state.
Register the LLM2Docs (Unofficial) MCP server in PolicyLayer and add a rule for search_text_in_document: 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 LLM2Docs (Unofficial). Nothing to install.
search_text_in_document 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_text_in_document 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_text_in_document. 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_text_in_document is provided by the LLM2Docs (Unofficial) MCP server (nomannayeem/google-docs-mcp-server). 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 →