Skip to main content
Glama
QuantLedger 73-Engine CPA, FASB GAAP, IRC Tax, Valuation & SEC 10-K MCP Server

QuantLedger 73-Engine CPA, FASB GAAP, IRC Tax, Valuation & SEC 10-K MCP Server

Official

Execute Deterministic GAAP, IRC Tax, DCAA or Credit Math Engine (Cloud REST)

execute_institutional_math_engine
Read-onlyIdempotent

Execute 73 deterministic accounting, tax, valuation, and statutory finance engines across 57 US jurisdictions using structured data or contract text to produce calculation results.

Instructions

Executes any of the 73 deterministic quantitative & statutory accounting/finance engines (BI-01 to BI-73: ASC 842 leases, ASC 606 SSP, ASC 326 CECL, ASC 740, IRC Sec 382/174/41/409A/163j/280G, Form 990 UBIT, DCAA CAS 410/418 wrap rates, CMS RBRVS, Altman Z-Score, QoE EBITDA, 19 U.S.C. 1401a customs) across 57 US jurisdictions via QuantLedger REST API (requires RAPIDAPI_KEY).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "engine_code": "<engine_code>"
    },
    "name": "execute_institutional_math_engine"
  }
}

Input Schema

NameRequiredDescriptionDefault
engine_codeYesEngine code from BI-01 through BI-73 (call list_institutional_math_suites_73 first to inspect inputs).
jurisdictionNo2-letter US State, DC, PR, GU, VI, AS, MP, or US Federal code.DC
naics_or_sicNo6-digit NAICS, 4-digit SIC, or 8-digit GICS code.541211
structured_inputsNoNumeric key-value inputs (trial balance, lease schedule, cost pools, cap table). Pass {} for statutory baseline.
unstructured_contextNoOptional contract clause, lease excerpt, or CSV text for quote-verified extraction.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.1.0

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, and open-world, and the description is consistent with all of them. Beyond the annotations it adds genuinely useful context: the computation is deterministic (explaining the idempotency), it is a cloud REST call via QuantLedger, and it requires a RAPIDAPI_KEY. It stops short of 5 because it says nothing about rate limits, failure modes for invalid engine codes, or latency.

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?

A single front-loaded sentence with the verb first and no filler or repetition; the statutory enumeration is dense but each item is informative. It is a long sentence, but no clause is clearly disposable.

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

Completeness3/5

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

For a complex 5-parameter tool with a nested free-form object and no output schema, the description covers what it computes and the auth requirement but leaves the agent guessing about response shape, error behavior, and the recommended inspect-then-execute sequence. The gap is not fatal, since the schema carries the input contract, but it is a real one for a tool this complex.

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 all five parameters and the baseline is 3. The description adds moderate value by cataloging the engine domains behind engine_code and anchoring the jurisdiction parameter to 57 US jurisdictions, helping an agent pick a code, but it gives no extra guidance on how to shape structured_inputs (trial balance vs. lease schedule vs. cap table) or unstructured_context.

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 description names a specific verb ("Executes") and a precisely scoped resource: 73 deterministic statutory/quantitative engines from BI-01 to BI-73, with concrete domain examples (ASC 842, IRC Sec 382, DCAA CAS 410, Altman Z-Score). Any agent knows exactly what class of computation happens here. It does not, however, explicitly distinguish itself from siblings like get_live_us_statutory_rates_and_57_jurisdictions or list_institutional_math_suites_73 in the description text, so it stops short of a 5.

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?

Usage is implied by stating that the tool executes deterministic engines, which signals "use this for numeric/statutory computation." The only routing hint (call list_institutional_math_suites_73 first to inspect inputs) lives in the engine_code schema field, not the description, and there is no when-not-to-use or alternative-selection guidance. The RAPIDAPI_KEY mention is a prerequisite, not a usage rule.

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