Skip to main content
Glama
emiliaprotocol

emilia-mcp-server

Official

ep_guard_action

Submit an action for human authorization before performing irreversible operations such as payments, deletions, or record changes. Returns a receipt ID to track approval status.

Instructions

Request authorization before an irreversible action: payments, wire transfers, fund releases, deletions, record or account changes, or sending messages with real-world effect. Submits the exact action for policy evaluation and human authorization. This MCP tool does not itself sit at the executor choke point: even after approval, the executor MUST match the returned action_hash and atomically consume the receipt before effect. If BLOCKED, poll ep_check_signoff with the receipt_id.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
amountNoAmount, for payments/releases.
summaryNoOne-line, human-readable description the approver will see.
currencyNoISO currency code, e.g. "USD".
risk_flagsNoOptional risk signals, e.g. ["new_destination","after_hours"].
action_typeYesKind of action, e.g. "large_payment_release", "vendor_bank_account_change", "ai_agent_payment_action".
destinationNoWhere funds or data are going (account, address).
organization_idYesThe organization this action belongs to.
target_resource_idYesWhat is being acted on — an invoice id, account id, or record id.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.2

TDQS

A4.7/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Describes the full workflow: it only requests authorization, returns an action_hash/receipt, and does not itself execute. States the executor must match and atomically consume the receipt before effect, so side effects and handoff are transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Compact and well-structured; first sentence states purpose, second explains submission, third clarifies executor responsibility and polling behavior. No redundant detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite no output schema, the description provides enough information about returned artifacts (action_hash, receipt_id) and next steps (poll on BLOCKED) to use the tool correctly. Sibling tools are also referenced where relevant.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema covers 100% of parameters with meaningful descriptions. The tool description adds overall context but no additional per-parameter meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states it requests authorization before an irreversible action and submits the exact action for policy evaluation/human signoff. Distinguishes it from execution and from the sibling polling tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly instructs to use it before irreversible actions and directs the caller to poll ep_check_signoff if BLOCKED. Also clarifies it is not the executor and that the executor must consume the receipt, giving clear when/when-not guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools