search_documents_vector
AI agents call search_documents_vector to retrieve information from AVS Document Search System without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves data from a vector search index without modifying, deleting, or executing code. It performs a semantic search operation analogous to its sibling 'search_documents_lexicaly', which is clearly a read operation. No side effects beyond querying are possible.
From the tool's definition Tool name contains 'search' and sibling tool names (find_movies, get_movie_details, search_documents_lexicaly, get_parent_document) demonstrate this is a retrieval/query system.
Attacks that exploit this kind of access
search_documents_vector. It is categorised as a Read tool in the AVS Document Search System MCP Server, which means it retrieves data without modifying state.
Register the AVS Document Search System MCP server in PolicyLayer and add a rule for search_documents_vector: 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 AVS Document Search System. Nothing to install.
search_documents_vector 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_documents_vector 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_documents_vector. 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_documents_vector is provided by the AVS Document Search System MCP server (patw/avs-docs-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 →