Skip to main content
Glama

cryptotaxedge

by io.github.sturs49
OverviewDiscussionsAdmin

Classify transaction batch

classify_batch
Read-onlyIdempotent

Classify a batch of blockchain transactions (up to 100) using CryptoTaxEdge's classification engine. Built for accounting platforms integrating CryptoTaxEdge as their classification layer. Returns per-transaction: category (the open vocabulary the engine emits, for example swap, transfer, staking, reward, airdrop, income_receipt, fee_payment, borrow, repay, collateral_supply, collateral_withdraw, liquidity_add, liquidity_remove, wrap, unwrap, liquid_staking_mint, bridge_transfer, nft_mint, spam, unclassified; the full set with house treatments is at https://cryptotaxedge.com/standard/#categories and grows additively, so branch exhaustive logic on treatment, never on category), treatment (closed enum: disposal, income, non_taxable, expense, needs_review; needs_review means no treatment is asserted), tax_category (the engine's stored treatment value, kept for existing hosts), taxable, confidence score, needs_review, ledger_action, protocol, description (plain-English reasoning, also returned as explanation for existing clients), assets (sent, received, gas) and a reliability envelope with an explicit route-to-review flag. Complex multi-step transactions (flash loans, batch NFT sales, bridges, DCA programs) additionally return a per-leg breakdown and a preparer-ready memo with IRS citations. EVM + Solana. Pass engagement_id / firm_id to apply firm-specific classification policy when configured.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
firm_idNo(Optional) host-side firm identifier. When firm classification policy is configured, applies that firm's confidence thresholds + CoA overrides.
transactionsYesArray of transactions to classify (max 100 per call).
engagement_idNo(Optional) host-side engagement identifier. Reserved for firm-policy + engagement-record correlation. No effect today; forward-compatible.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed8 schema fields changed
    • changedInput schema / properties / transactions / items / properties / chain / description
      Previous value: -"Chain slug (e.g. \"ethereum\", \"polygon\", \"bsc\", \"arbitrum\", \"base\", \"optimism\", \"avalanche\", \"solana\"). Optional; CTE auto-detects if omitted."New value: +"Chain slug (e.g. \"ethereum\", \"polygon\", \"bsc\", \"arbitrum\", \"base\", \"optimism\", \"avalanche\", \"solana\"). Optional; CryptoTaxEdge auto-detects the chain if omitted."
    • addedOutput schema / properties / results / items / properties / assets
      Added value: +{
+  "description": "Net asset movements, same shape as REST /v1: sent and received legs plus the gas leg (null when not attributable). Present when the engine response carries them.",
+  "properties": {
+    "gas": {
+      "type": [
+        "object",
+        "null"
+      ]
+    },
+    "received": {
+      "type": "array"
+    },
+    "sent": {
+      "type": "array"
+    }
+  },
+  "type": "object"
+}
    • changedOutput schema / properties / results / items / properties / category / description
      Previous value: -"Canonical category (closed enum, see https://cryptotaxedge.com/taxonomy)"New value: +"Canonical category. Open vocabulary that only grows additively; tolerate unfamiliar values and branch exhaustive logic on treatment instead. Full set with house treatments: https://cryptotaxedge.com/standard/#categories"
    • addedOutput schema / properties / results / items / properties / description
      Added value: +{
+  "description": "Plain-English reasoning for the verdict, same field as REST /v1.",
+  "type": [
+    "string",
+    "null"
+  ]
+}
    • addedOutput schema / properties / results / items / properties / explanation / description
      Added value: +"Deprecated alias of description, kept for existing clients."
    • changedOutput schema / properties / results / items / properties / explanation / type
      Previous value: -"string"New value: +[
+  "string",
+  "null"
+]
    • addedOutput schema / properties / results / items / properties / ledger_action
      Added value: +{
+  "description": "Suggested ledger label for posting, same field as REST /v1.",
+  "type": [
+    "string",
+    "null"
+  ]
+}
    • addedOutput schema / properties / results / items / properties / treatment / description
      Added value: +"Closed five-value tax treatment enum, safe to switch on exhaustively. needs_review means no treatment is asserted."
  2. First observed

TDQS

A4.4/5.0
Behavior5/5

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

The description goes far beyond the annotations by detailing the output contract, the open-ended category vocabulary, the closed treatment enum with needs_review semantics, and the warning to branch on treatment rather than category. It also discloses complex multi-step transaction handling, supported chains, and the route-to-review flag, all without contradicting the readOnly/openWorld/idempotent annotations.

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 front-loaded and information-dense. The category enumeration and warning are verbose but operationally important for correct use of the open-world output. It earns its length, though it could be slightly tightened.

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?

For a tool with real complexity, the description covers the output fields, treatment semantics, open-vocabulary behavior, multi-leg transaction handling, chain support, and firm policy parameters. There is no significant missing information that would prevent an agent from invoking it correctly.

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?

The input schema already covers all parameters with 100% description coverage, so the baseline applies. The description adds some context around firm_id/engagement_id and the 100-transaction limit, but does not substantially re-explain individual parameters beyond the schema.

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 a specific operation ('classify a batch of blockchain transactions'), the resource (CryptoTaxEdge classification engine), and the batch scope (up to 100). The explicit 'batch' framing distinguishes it from the sibling classify_transaction even without naming it directly.

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?

The description clearly frames when this tool is appropriate: batched classification for accounting platforms, with guidance on passing firm_id/engagement_id to apply firm-specific policy. It lacks explicit exclusion language like 'for single transactions use classify_transaction instead,' but the context is otherwise clear.

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

All cryptotaxedge 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