// SCAN REPORT

Treasure Data MCP Server

23 tools. 5 can modify or destroy data without limits.

2 destructive tools with no built-in limits. Policy required.

Last updated: 12 Jun 2026

5 can modify or destroy data

18 read-only

23 tools total

Community server · catalogue entry verified 12/06/2026

How to control Treasure Data MCP Server ↓

TOOL MAP

What Treasure Data MCP Server exposes to your agents

Read (18) Write / Execute (3) Destructive / Financial (2)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Treasure Data MCP Server tools

Destructive · Critical execute This tool explicitly executes write operations including DELETE, which is irreversible. Destructive · High kill_attempt Killing/cancelling a running workflow attempt stops it permanently; any in-progress work is lost and the attempt cannot be resumed, making this an irreversible destructive action with high blast radius if misused against Execute · High retry_attempt This tool re-runs a failed workflow attempt, which constitutes executing an external operation. Execute · High retry_session This tool re-triggers execution of a workflow session or task, which constitutes running external operations.

5 of Treasure Data MCP Server's 23 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Treasure Data MCP Server

PolicyLayer is an MCP gateway — it sits between your AI agents and Treasure Data MCP Server, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "execute": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "use_database": {
    "limits": [
      {
        "counter": "use_database_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "current_database": {
    "limits": [
      {
        "counter": "current_database_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Treasure Data MCP Server — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON TREASURE DATA →

Free to start. No card required.

FULL CATALOGUE

All 23 Treasure Data MCP Server tools

DESTRUCTIVE 2 tools

Destructive execute Execute write operations (UPDATE, DELETE, INSERT, etc.) when enable_updates=true Destructive kill_attempt Request cancellation of a running attempt

EXECUTE 2 tools

Execute retry_attempt Retry a specific failed attempt with resume capabilities Execute retry_session Retry a failed session from the beginning or a specific task

WRITE 1 tools

Write use_database Switch the current database context for subsequent queries

READ 18 tools

Read current_database Get the current database context being used for queries Read describe_table Get column information for a specific table Read get_attempt_tasks List all tasks within an attempt with their execution status Read get_parent_segment [EXPERIMENTAL] Get details of a specific parent segment by its ID. Requires parent_segment_id parameter. Use l Read get_segment [EXPERIMENTAL] Get detailed information about a specific segment including its filtering rules. Requires both Read get_session_attempts Get detailed information about all attempts for a specific session Read get_task_logs Retrieve logs for a specific task Read list_activations [EXPERIMENTAL] List all activations (syndications) for a specific segment. Requires both parent_segment_id and Read list_databases List all available databases in Treasure Data Read list_parent_segments [EXPERIMENTAL] List all parent segments (audiences) in Customer Data Platform. No parameters required. Read list_projects List all workflow projects Read list_segments [EXPERIMENTAL] List all segments under a specific parent segment. Requires parent_segment_id parameter. Use li Read list_sessions List workflow execution sessions with filtering options Read list_tables List all tables in a specific database Read list_workflows List workflows. Optionally filter by project name. Read parent_segment_sql [EXPERIMENTAL] Get the SQL statement for a parent segment (audience). Requires parent_segment_id parameter. Us Read query Execute a read-only SQL query (SELECT, SHOW, DESCRIBE) using Trino SQL dialect with Treasure Data UDFs. For be Read segment_sql [EXPERIMENTAL] Get the SQL statement for a segment with filtering conditions applied to the parent segment (au

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Treasure Data MCP Server

Can an AI agent delete data through the Treasure Data MCP Server MCP server? +

Yes. The Treasure Data MCP Server server exposes 2 destructive tools including execute, kill_attempt. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Treasure Data MCP Server? +

The Treasure Data MCP Server server has 1 write tools including use_database. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Treasure Data MCP Server.

How many tools does the Treasure Data MCP Server MCP server expose? +

23 tools across 2 categories: Execute, Read. 18 are read-only. 5 can modify, create, or delete data.

How do I enforce a policy on Treasure Data MCP Server? +

Register the Treasure Data MCP Server MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Treasure Data MCP Server tool call.

Deterministic rules across all 23 Treasure Data MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON TREASURE DATA →

Free to start. No card required.

23 Treasure Data MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.