mcp.xynaptic

bank-transaction-categorize

Xynaptic Bank Transaction Categorize — bring your own transactions (CSV rows or objects: date, label, amount): we normalize multi-bank formats and return per-transaction category, merchant, income/expense, recurrence detection. POST body: { transactions: [ {date, label, amount}, ... ], max 200 } or { csv: raw rows }. Hybrid statistical + LLM, merchant patterns, nothing stored. [price: $0.020 per call, x402/USDC]

Input Schema

TableJSON Schema

Name	Required	Description	Default
`body`	No	JSON request body (POST endpoint)
`params`	No	optional query parameters

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedOct 2, 2026

changedInput schema / properties / body / description

Previous value: -"JSON body for POST endpoints (e.g. insurance, ai-chat, production-risk)"New value: +"JSON request body (POST endpoint)"

addedInput schema / properties / body / properties

Added value: +{
+  "output": {
+    "description": "example: [{\"category\":\"food_and_drinks\",\"merchant\":\"Cafe de la Gare\",\"kind\":\"expense\",\"re",
+    "type": "string"
+  },
+  "transactions": {
+    "description": "example: [{\"date\":\"2026-09-01\",\"label\":\"CAFE DE LA GARE PARIS\",\"amount\":-4.2},{\"date\":\"20",
+    "type": "string"
+  }
+}

changedInput schema / properties / params / description

Previous value: -"query parameters, e.g. {city: 'Paris', type: 'Appartement'}"New value: +"optional query parameters"

addedInput schema / required
```
Added value: +[]
```

First observedOct 1, 2026

TDQS

A4.1/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses the hybrid statistical+LLM approach, that nothing is stored, the 200-row cap, and the x402/USDC payment model at $0.020 per call. It does not cover failure modes or rate limits, but the privacy and billing behavior are unusually well surfaced.

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?

Information-dense and front-loaded — what it does, what you give it, what it returns, then body shapes and pricing. It is a single long line rather than clean sentences, but every clause carries payload with no 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?

For a 2-param nested tool with no output schema, the description supplies the return fields and input constraints an agent needs to call it correctly. No annotation or output schema to lean on, and only edge-case/error behavior is left unstated.

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 coverage is 100%, so the baseline is 3, but the description adds real semantics the schema lacks: the mutually exclusive body shapes ({transactions:[...]} vs {csv: raw rows}), the required fields per row (date, label, amount), and the max-200 constraint.

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+resource (categorize bank transactions) and enumerates the outputs produced: category, merchant, income/expense, recurrence detection. The scoping phrase 'bring your own transactions' plus the accepted input shapes cleanly separates it from siblings like bank-statement-parse.

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

Usage Guidelines3/5

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

The description makes the invocation context obvious (you supply transactions as an object array or raw CSV), but it never says when to prefer this over bank-statement-parse, bank-reconciliation, or bank-spending-goals, nor any when-not conditions. Usage is implied rather than routed.

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

All mcp.xynaptic 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.

Resources

Need Help?