Skip to main content
Glama

DPX — Institutional Cross-Border Settlement

by io.github.untitledfinancial

mercury.ach_authorize

Destructive

Screen an ACH payment through the DPX compliance oracle before execution. Runs FATF R16, GENIUS Act, MiCA, and AML checks against the recipient. Returns APPROVED / FLAGGED / BLOCKED with full compliance reasoning.

Use this tool BEFORE every ACH payment via mercury.send. ACH is hard to reverse — compliance pre-screening prevents blocked transactions and BSA/AML exposure.

Workflow:

  1. mercury.ach_authorize (screen only, autoExecute:false) → review decision

  2. If APPROVED → set autoExecute:true to send, or call mercury.send directly

  3. If FLAGGED → manual review required before proceeding

  4. If BLOCKED → do not proceed

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
noteNoPayment memo / note (optional).
amountYesPayment amount in USD.
purposeNoPayment purpose category (optional — required by Mercury for domesticWire, recommended for ACH). E.g. "Vendor", "Contractor", "Expenses".
accountIdYesSource Mercury account ID (from mercury.accounts).
autoExecuteNoIf true and compliance returns APPROVED, immediately sends the ACH payment. Default false — screen first, execute separately.
recipientIdYesMercury saved recipient ID (from mercury.send / POST /mercury/recipients).
externalMemoNoExternal memo / reference visible to recipient (optional).
recipientNameYesLegal name of the recipient entity or individual — used for compliance screening.
idempotencyKeyNoIdempotency key for safe retries. Auto-generated if omitted.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
tierNoCompliance tier — FAST_PATH, STANDARD, ENHANCED, or HOLD.
_nextNoGuidance on next action.
reasonNoHuman-readable decision summary.
decisionNoCompliance decision.
executedNoTrue if autoExecute:true and ACH was sent.
mercuryIdNoMercury transaction ID (present when executed).
authorizedNoTrue if compliance approved the payment.
complianceNoFull compliance oracle response including framework attestations.
requiresReviewNoTrue when decision is FLAGGED — manual review required.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already indicate destructiveHint=true and readOnlyHint=false, and the description adds context: it explains that setting autoExecute:true will actually send the payment, while default false is screen-only. It also mentions the compliance checks and decision outputs. It does not go into details about retries, partial failures, or network effects, but the core behavioral trait (execution vs screening) is well covered.

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

Conciseness4/5

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

The description is moderately lengthy but well structured, with a clear intro, rationale, and numbered workflow. Each sentence serves a purpose, though the intro could be tighter. The workflow steps are especially compact and high-signal.

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?

Given the tool's complexity (9 parameters, output schema, annotations), the description provides a complete picture: what it does, when to use it, how to integrate with mercury.send, and how to interpret the three decision states. The workflow fully covers the execution path, making it unambiguous for an agent to select and invoke correctly.

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

Parameters4/5

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

The input schema already covers 100% of parameters, so the baseline is 3. The description adds value by clarifying the autoExecute parameter's role in the workflow (screen-only vs send) and notes that recipientName is used for compliance screening. It does not explain every parameter, but the schema is self-sufficient; these semantic additions meaningfully enhance understanding.

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?

Starts with a specific verb and resource: 'Screen an ACH payment through the DPX compliance oracle before execution.' It clearly states the compliance checks (FATF R16, GENIUS Act, MiCA, AML) and the outcome (APPROVED / FLAGGED / BLOCKED). This distinguishes it from sibling tools like mercury.send (execution) and compliance.pep_screen (general screening) by its ACH-specific pre-execution role.

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 'Use this tool BEFORE every ACH payment via mercury.send' and explains the rationale (ACH hard to reverse, prevents blocked transactions and BSA/AML exposure). The workflow gives clear step-by-step directives for each outcome, including when to call mercury.send directly and when to avoid proceeding. This is exemplary usage guidance.

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

All DPX — Institutional Cross-Border Settlement toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.6/5.0
Disambiguation2/5

Many tools have overlapping purposes, such as multiple stablecoin routing options (route vs stability.stablecoin_route), several compliance pre-checks (flow_check, policy.check, mercury.ach_authorize), and numerous FX/stability tools (oracle.stability, stability.corridor, market.fx, fx.rate). Even with detailed descriptions, the boundaries are subtle and an agent could easily select the wrong tool.

Naming Consistency3/5

The dot-separated namespace convention is mostly consistent and readable, but verb vs noun usage varies (e.g., settlement.execute vs batch_settle vs route). Subscription tools also mix forms (intelligence.subscribe vs intelligence.subscription.get/delete), showing minor inconsistency.

Tool Count1/5

81 tools is an extreme count for a settlement server. Even accounting for the broad 'institutional' scope, the volume overwhelms the core purpose and creates a heavy cognitive load for agents, far beyond the typical 3-15 well-scoped tool set.

Completeness3/5

The core settlement lifecycle is well-covered (quote, execute, track, receipt, batch), but there are notable gaps such as missing policy update/delete and no receipt retrieval (only create). While many tangential domains are over-covered, certain CRUD operations are absent, creating dead ends.

Resources