Skip to main content
Glama

agent-transaction-control

by network.flint
OverviewDiscussionsAdmin

FLINT Scout: Pre-Transaction Fraud Prevention

run_flint_scout
Destructive

Use this tool to scan an intended agent transaction before execution. Two ways to pay for a scan. Credits first: buy credits once with scout_credits_topup (one $1.00 x402 payment for 100 scans), then call this tool with the same session_token and no payment_signature; FLINT draws one credit and runs the scan immediately, with no wallet signature for that call. x402 per call second: with no session_token, the first call returns a $0.01 x402 payment challenge without running the scan; a wallet-enabled client signs that challenge and retries with payment_signature. Either way, when the call returns a 402 instead of a result, the result carries pay_recipe with concrete next steps: an awal command, a local script, the credits path, and the browser flow. After a paid or credit-funded scan completes, FLINT returns a signed authority decision. When receipt issuance succeeds for a paid scan, it also returns a separately signed settlement receipt and durable receipt URL; otherwise it reports receipt unavailability without inviting a paid retry. Payment to FLINT is distinct from the transaction being scanned and is not proof of agent authority.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nonceNoReplay-protection nonce. Generated automatically if omitted.
timestampNoISO-8601 request timestamp. Generated automatically if omitted.
agent_claimNoOptional bounded agent hints. Self-asserted values do not establish authority.
passport_idNoOptional FLINT Agent Passport. Verified payer-wallet and mandate bindings may strengthen the decision.
transactionYes
session_tokenNoOptional agent session token from auth_verify_otp. When present with no payment_signature, FLINT draws one prepaid Scout credit instead of requiring an x402 payment for this call. Buy credits first with scout_credits_topup.
payment_signatureNoOpaque caller-signed x402 PAYMENT-SIGNATURE value from a wallet-enabled client. Never provide a private key or seed phrase.
merchant_referenceNoOptional merchant reference. Must match transaction.reference when both are supplied.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / session_token
      Added value: +{
+  "description": "Optional agent session token from auth_verify_otp. When present with no payment_signature, FLINT draws one prepaid Scout credit instead of requiring an x402 payment for this call. Buy credits first with scout_credits_topup.",
+  "pattern": "^flint_sess_[A-Za-z0-9_-]{40,}$",
+  "type": "string"
+}
  2. Added

TDQS

A4.1/5.0
Behavior5/5

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

Annotations only flag readOnly=false/destructive=true/openWorld; the description supplies the why — a credit is drawn per credit-path call and payment is taken on the x402 path — plus 402 challenge behavior, the pay_recipe fallback, conditional receipt issuance, and the explicit caveat that payment to FLINT is not proof of authority. That is materially more than the annotations convey.

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?

Purpose is front-loaded and the payment mechanics are ordered credits-first, then x402, then fallbacks. It is dense and somewhat long, with a few clauses ('no wallet signature for that call') that could be trimmed, but nothing is wasted given the absent output schema.

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?

With no output schema, the description carries the return-side burden and does so: signed authority decision, conditional signed settlement receipt and durable URL, and the 402 pay_recipe shape. An agent has enough to call it, fund it, and interpret both success and failure.

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 description coverage is 88%, so the schema already documents session_token, payment_signature, nonce, and transaction fields in detail. The description's payment narrative mostly restates what session_token's own schema description says, adding only marginal relational clarity about the two paths.

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

Purpose4/5

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

The first sentence gives a specific verb and resource with timing: 'scan an intended agent transaction before execution.' That scope cleanly separates it from verify_agent_authority and report_scout_outcome, though no sibling is named explicitly.

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

Usage Guidelines4/5

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

It states when to use it (pre-execution) and lays out two mutually exclusive payment paths (prepaid credits via scout_credits_topup vs. per-call x402) with the exact triggering conditions for each. It does not compare against competing authority tools, so tool selection is still inferred.

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

All agent-transaction-control toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources