find_folder_by_name
AI agents call find_folder_by_name to retrieve information from DCI MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to retrieve or query folder metadata by name, which is consistent with Read operations. No side effects, modifications, or deletions are implied by the name. Confidence is moderately high despite the empty description, as the naming convention strongly suggests a retrieval operation. Severity is low because folder lookup has minimal blast radius.
From the tool's definition Tool name 'find_folder_by_name' indicates a search/lookup operation. Description is empty, but the name pattern and context (DCI MCP Server with Google Drive integration) suggest it queries folders by name without modifying data.
Attacks that exploit this kind of access
find_folder_by_name. It is categorised as a Read tool in the DCI MCP Server MCP Server, which means it retrieves data without modifying state.
Register the DCI MCP Server MCP server in PolicyLayer and add a rule for find_folder_by_name: 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 DCI MCP Server. Nothing to install.
find_folder_by_name 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 find_folder_by_name 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 find_folder_by_name. 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.
find_folder_by_name is provided by the DCI MCP Server MCP server (redhat-community-ai-tools/dci-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 →