td_read_project_file
AI agents call td_read_project_file 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.
The 'read' prefix in the tool name and the context of sibling read-only operations (list, get, download) indicate this tool retrieves project file contents without side effects. Despite empty description, the naming convention and server purpose support a Read classification. Confidence is moderate because the description is empty; if it performed destructive or executory operations it would be documented.
From the tool's definition Tool name 'td_read_project_file' contains 'read' indicating data retrieval; sibling tools like 'td_list_databases', 'td_list_projects', 'td_list_tables', 'td_download_project_archive' and server description mentioning 'retrieve database information' suggest…
Attacks that exploit this kind of access
td_read_project_file. 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_read_project_file: 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_read_project_file 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_read_project_file 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_read_project_file. 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_read_project_file 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 →