block_sender · Tru MCP: Risk & Policy

WHAT IT DOES

What block_sender does on Tru

AI agents use block_sender to create or update resources in Tru — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tru environment.

PARAMETERS

Parameter	Type	Required	Description
`reason`	string	—	Reason for blocking (e.g. 'spam', 'unwanted charges')
`sender_email`	string	Yes	Email address of the sender to block

Parameters from the server's own tool schema.

WHY IT NEEDS A POLICY

Why block_sender needs a policy

This tool creates or modifies account state (a blocklist entry) reversibly. It does not delete data, move money, or execute arbitrary code. It is Write rather than Destructive because blocking is typically reversible (unblocking restores the previous state).

From the tool's definition 'Block a sender from sending you payment requests' — modifies account permissions/rules by adding a sender to a blocklist, preventing future payment requests from that sender. This is reversible (the sender can be unblocked).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

block_sender Rate-limited

block_sender stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "block_sender": {
      "limits": [
        {
          "counter": "block_sender_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Tru, so you can run agents against it safely.

FAQ

Questions about block_sender

What does the block_sender tool do? +

Block a sender from sending you payment requests. Blocked senders cannot create charges for your account. Requires login first. It is categorised as a Write tool in the Tru MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does block_sender accept? +

block_sender accepts 2 parameters: reason, sender_email. Required: sender_email. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on block_sender? +

Register the Tru MCP server in PolicyLayer and add a rule for block_sender: 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 Tru. Nothing to install.

What risk level is block_sender? +

block_sender is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit block_sender? +

Yes. Add a rate_limit block to the block_sender 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 block_sender completely? +

Set action: deny in the PolicyLayer policy for block_sender. 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 block_sender? +

block_sender is provided by the Tru MCP server (tru-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.