Skip to main content
Glama

DPX — Institutional Cross-Border Settlement

mercury.send

Destructive

Initiate a Mercury bank payment from a connected account. Supports all Mercury payment rails: ACH (0–1 days), Wire (0–1 days), Real-Time Payment / RTP (instant), International Wire (1–3 days), and Check (7–10 days).

For International Wire — the primary DPX cross-border use case — provide SWIFT/BIC code and beneficiary bank details. DPX oracle conditions and FX corridor risk should be checked via oracle.stability and market.fx before executing.

Can optionally tag the payment for automatic DPX on-chain routing — when dpxRoute:true is set, the payment memo includes the DPX executor wallet address and the Mercury webhook picks it up for USDC settlement on Base mainnet.

Use sandbox:true (default) for dry-run testing. Set sandbox:false only when ready to move real funds.

Typical cross-border flow:

  1. market.fx → check FX corridor risk for the destination currency

  2. mercury.accounts → get source accountId

  3. mercury.send (sandbox:true) → confirm payment parameters

  4. settlement.quote → get DPX fee quote for the USDC leg

  5. mercury.send (sandbox:false) → execute (requires explicit user confirmation)

  6. mercury.transactions → verify payment posted

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
noteNoPayment memo / description.
amountYesPayment amount in USD (or destination currency if specified).
sandboxNoDry run — returns what would be sent without executing. Default: true. Set false to execute.
bankCityNoBeneficiary bank city.
bankNameNoBeneficiary bank name (e.g. "Barclays Bank UK PLC").
currencyNoDestination currency for internationalWire (e.g. "GBP", "EUR"). Default USD.
dpxRouteNoIf true, appends dpx:<wallet> to the memo — triggers DPX on-chain USDC settlement via the Mercury webhook. Use this to settle the stablecoin leg of a cross-border payment.
accountIdYesSource Mercury account ID (from mercury.accounts).
swiftCodeNoBIC/SWIFT code of beneficiary bank (required for internationalWire without recipientId). E.g. "BARCGB22" for Barclays UK.
bankAddressNoBeneficiary bank street address.
bankCountryNoBeneficiary bank country — ISO 3166-1 alpha-2 (e.g. "GB", "DE", "SG").
recipientIdNoMercury saved recipient ID for internationalWire. Use this if the recipient is already saved in Mercury — skips inline bank detail fields.
accountNumberNoRecipient account number (required for ach/wire/check). Also used for IBAN on internationalWire.
paymentMethodNoPayment rail. rtp = Real-Time Payment (instant, US domestic). internationalWire = cross-border (1–3 days). Default: ach.
recipientCityNoBeneficiary city.
recipientNameNoRecipient legal name (required for ach/wire/rtp/check).
routingNumberNoRecipient routing number (required for ach/wire/check).
recipientEmailNoRecipient email (optional — for payment notification).
recipientAddressNoBeneficiary street address.
recipientCountryNoBeneficiary country — ISO 3166-1 alpha-2.
recipientPostalCodeNoBeneficiary postal code.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
idNoMercury transaction ID (present when sandbox:false and executed)
noteNoPayment memo as sent
amountNoAmount in USD
statusNoTransaction status from Mercury
sandboxNoTrue if this was a dry run
dpxTaggedNoWhether the DPX routing tag was appended
simulationNoDry-run summary (present when sandbox:true)

Schema Changelog

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

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the annotations, the description explains the sandbox mode (dry-run vs. real funds), the dpxRoute behavior (memo and webhook for USDC settlement), and the requirement for explicit user confirmation. This adds crucial context about side effects and safety.

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 long but well-structured with clear paragraphs and a numbered flow. Every sentence provides necessary context for a complex tool with 21 parameters; it is appropriately sized, though slightly verbose.

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?

The description covers prerequisites, a complete execution flow, dry-run vs. live behavior, and integration with other tools. Given the output schema and rich annotations, nothing essential is missing for the agent to use the tool 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?

Schema descriptions already cover all parameters, but the description adds semantic value by explaining parameter combinations for different rails (e.g., 'provide SWIFT/BIC and beneficiary bank details' for International Wire) and the dpxRoute flag. This cross-parameter guidance goes beyond individual field descriptions.

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?

The description states clearly 'Initiate a Mercury bank payment from a connected account' and goes on to detail all supported rails. It also distinguishes itself from siblings by highlighting the DPX cross-border use case, making its scope precise.

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?

Explicit guidance is provided: for International Wire, it specifies required parameters and prerequisites like checking oracle.stability and market.fx. The typical flow lists step-by-step interactions with sibling tools, clarifying when to use this tool vs. others.

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

Try in Browser

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.