retry_session

THE RISK

High Risk

Why retry_session needs a policy

This tool re-triggers execution of a workflow session or task, which constitutes running external operations. Misuse could cause unintended repeated execution of workflows, potentially with side effects such as data modifications, resource consumption, or triggering downstream processes.

From the tool's definition 'Retry a failed session from the beginning or a specific task' — triggers re-execution of a workflow session or specific task

Documented attack patterns abuse exactly the kind of access retry_session gives an agent:

POLICY

How to control retry_session

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. This is the rule we recommend for retry_session:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "retry_session": {
      "limits": [
        {
          "counter": "retry_session_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

retry_session stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

Create a free account and register Treasure Data MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Treasure Data MCP Server tools

Destructive execute Execute write operations (UPDATE, DELETE, INSERT, etc.) when enable_updates=true Destructive kill_attempt Request cancellation of a running attempt Execute retry_attempt Retry a specific failed attempt with resume capabilities Write use_database Switch the current database context for subsequent queries 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

All 23 Treasure Data MCP Server tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Treasure Data MCP Server → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about retry_session

What does the retry_session tool do? +

Retry a failed session from the beginning or a specific task. It is categorised as a Execute tool in the Treasure Data MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on retry_session? +

Register the Treasure Data MCP Server MCP server in PolicyLayer and add a rule for retry_session: 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.

What risk level is retry_session? +

retry_session is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit retry_session? +

Yes. Add a rate_limit block to the retry_session 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.

How do I block retry_session completely? +

Set action: deny in the PolicyLayer policy for retry_session. 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.

What MCP server provides retry_session? +

retry_session is provided by the Treasure Data MCP Server MCP server (treasure-data/td-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Treasure Data MCP Server tool call.

Start from Treasure Data MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →