filter_documents
AI agents call filter_documents to retrieve information from World Bank Documents MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool is part of a read-only document discovery API. Filtering documents retrieves or queries data without creating, modifying, or deleting content. The lack of a tool description slightly reduces confidence, but the sibling tools and server purpose clearly indicate this is a retrieval operation with no side effects.
From the tool's definition Tool name 'filter_documents' with sibling tools 'get_document', 'get_facets', 'search_documents' indicates data retrieval without side effects. Server description emphasizes 'discovery and retrieval' and 'search' capabilities.
Attacks that exploit this kind of access
filter_documents. It is categorised as a Read tool in the World Bank Documents MCP Server MCP Server, which means it retrieves data without modifying state.
Register the World Bank Documents MCP Server MCP server in PolicyLayer and add a rule for filter_documents: 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 World Bank Documents MCP Server. Nothing to install.
filter_documents 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 filter_documents 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 filter_documents. 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.
filter_documents is provided by the World Bank Documents MCP Server MCP server (mounika-nemalipuri/wb_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 →