Skavio USDC Payment Verification & Proof MCP

Invoice extract

invoice_extract

Idempotent

Extract structured invoice fields from one uploaded document, with source page count verified and a per-page cost quote. Use for invoice metadata, not generic OCR (document_ocr) or plain selectable text (pdf_to_text). This is a separately authenticated company Agent Tools relay; requires a valid Bearer API key, an enabled backend operation and an accepted payment mode. x402 returns a workload-specific quote and prepaid consumes shared company credits. Retry with the SAME idempotency_key and inputs to recover, not a new job. Admission is not delivery: poll skavio_agent_job_status, retrieve through skavio_agent_job_result, and verify SHA256. No anonymous execution.

Input Schema

Name	Required	Description	Default
`arguments`	Yes	Tool-specific structured input object. Supply the required named fields described by its JSON Schema; source bytes must respect encoded size limits. Never include wallet private keys, passwords or API tokens.
`payment_mode`	No	x402 returns a workload-specific quote; prepaid spends your existing shared company credits. No anonymous execution.	x402
`idempotency_key`	Yes	Stable job key; retry exactly the same inputs and payment mode with this key to recover safely.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 27, 2026

addedInput schema / properties / arguments / description

Added value: +"Tool-specific structured input object. Supply the required named fields described by its JSON Schema; source bytes must respect encoded size limits. Never include wallet private keys, passwords or API tokens."

Changed9 schema fields changedOct 17, 2026

changedInput schema / properties / arguments / additionalProperties
```
Previous value: -trueNew value: +false
```

addedInput schema / properties / arguments / properties

Added value: +{
+  "data_base64": {
+    "description": "Source document or audio bytes in base64, at most 3,000,000 encoded characters.",
+    "maxLength": 3000000,
+    "type": "string"
+  },
+  "units": {
+    "description": "Optional legacy count; verified against actual source bytes. Omit it for automatic measurement.",
+    "maximum": 100,
+    "minimum": 1,
+    "type": "integer"
+  }
+}

addedInput schema / properties / arguments / required
```
Added value: +[
+  "data_base64"
+]
```
removedInput schema / properties / arguments / title
```
Removed value: -"Arguments"
```

addedInput schema / properties / idempotency_key / description

Added value: +"Stable job key; retry exactly the same inputs and payment mode with this key to recover safely."

addedInput schema / properties / idempotency_key / maxLength
```
Added value: +128
```
addedInput schema / properties / idempotency_key / minLength
```
Added value: +8
```
addedInput schema / properties / idempotency_key / pattern
```
Added value: +"^[A-Za-z0-9_.:-]{8,128}$"
```

addedInput schema / properties / payment_mode / description

Added value: +"x402 returns a workload-specific quote; prepaid spends your existing shared company credits. No anonymous execution."

AddedOct 14, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Annotations only carry readOnly=false, idempotent=true, openWorld=true, destructive=false. The description adds context the annotations do not: separate Bearer authentication, an enabled backend operation, accepted payment mode, x402 quote vs prepaid credit consumption, admission-is-not-delivery async semantics, SHA256 verification, and no anonymous execution.

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?

Front-loaded with purpose and sibling exclusion, then auth, payment, recovery, and retrieval semantics in a logical order. The middle section packs several clauses into long sentences, but each sentence carries operational information rather than filler.

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

Completeness4/5

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

There is no output schema, so the description compensates by explaining that the call is asynchronous and how to obtain and verify the result. It stops short of saying which invoice fields are returned or what the quote contains, which leaves a small gap for a structured-extraction tool.

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 100%, so the schema already documents arguments, units, data_base64 size limits, payment_mode enum, and idempotency_key pattern. The description reinforces the retry meaning of idempotency_key and the two payment modes but contributes no new parameter-level detail, which is the baseline-3 situation.

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?

States a specific verb and resource ('Extract structured invoice fields from one uploaded document') plus distinguishing scope (source page count verified, per-page cost quote). It explicitly separates itself from document_ocr and pdf_to_text, so an agent can route without opening a schema.

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?

Names the two nearest alternatives and the condition that excludes them: invoice metadata rather than generic OCR or plain selectable text. It also gives the recovery rule (retry with the same idempotency_key and inputs, not a new job) and the required follow-up path (poll job status, retrieve result).

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

All Skavio USDC Payment Verification & Proof MCP tools Inspect

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.

Invoice extract

Input Schema

Schema Changelog

TDQS

Glama MCP Gateway

Resources