td_get_database
AI agents call td_get_database to retrieve information from Treasure Data MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves database metadata/information from Treasure Data without modifying, deleting, or executing arbitrary operations. It matches the 'Read' category (queries data; no side effects). Low severity because accessing database metadata has limited blast radius compared to Execute or Destructive actions.
From the tool's definition Tool name 'td_get_database' indicates retrieval; server description emphasizes 'retrieve database information'; sibling tools include 'td_list_databases', 'td_list_tables', 'td_list_project_files', and 'td_read_project_file', all clearly read operations.
Attacks that exploit this kind of access
td_get_database. It is categorised as a Read tool in the Treasure Data MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Treasure Data MCP Server MCP server in PolicyLayer and add a rule for td_get_database: 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 Treasure Data MCP Server. Nothing to install.
td_get_database 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 td_get_database 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 td_get_database. 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.
td_get_database is provided by the Treasure Data MCP Server MCP server (knishioka/td-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 →