Skip to main content
Glama
jflamb

FDIC BankFind MCP Server

by jflamb

Search Institution Financial Data

fdic_search_financials
Read-onlyIdempotent

Get quarterly Call Report data (balance sheet, income, capital, performance ratios) for FDIC-insured banks, filtered by certificate number, report date, or custom criteria.

Instructions

Use this when the user wants quarterly Call Report data (balance sheet, income, capital, performance ratios) for FDIC-insured institutions. Filter by CERT and/or REPDTE plus optional ElasticSearch filters. See fdic://schemas/financials for the full 1,100+ field catalog.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
certNoFilter by FDIC Certificate Number to get financials for a specific institution
limitNoMaximum number of records to return (1-10000, default: 20)
fieldsNoComma-separated list of FDIC field names to return. Leave empty to return all fields. Field names are ALL_CAPS (e.g., NAME, CERT, ASSET, DEP, STALP). Example: NAME,CERT,ASSET,DEP,STALP
offsetNoNumber of records to skip for pagination (default: 0)
repdteNoFilter by Report Date (REPDTE) in YYYYMMDD format (quarter-end: 0331, 0630, 0930, 1231). If omitted, returns all available dates (sorted most recent first).
filtersNoFDIC API filter using ElasticSearch query string syntax. Combine conditions with AND/OR, use quotes for multi-word values, and [min TO max] for ranges (* = unbounded). Common fields: NAME (institution name), STNAME (state name), STALP (two-letter state code), CERT (certificate number), ASSET (total assets in $thousands), ACTIVE (1=active, 0=inactive). Examples: STNAME:"California", ACTIVE:1 AND ASSET:[1000000 TO *], NAME:"Chase"
sort_byNoField name to sort results by. Example: ASSET, NAME, FAILDATE
sort_orderNoSort direction: DESC (descending, default for most recent first) or ASC (ascending)DESC

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
countYes
totalYes
offsetYes
has_moreYes
truncatedNo
financialsYes
next_offsetNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed15 schema fields changedv3.0.1
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
    • addedInput schema / properties / cert / maximum
      Added value: +9007199254740991
    • addedInput schema / properties / offset / maximum
      Added value: +9007199254740991
    • changedOutput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
    • addedOutput schema / properties / count / maximum
      Added value: +9007199254740991
    • addedOutput schema / properties / count / minimum
      Added value: +-9007199254740991
    • changedOutput schema / properties / financials / items / additionalProperties
      Previous value: -trueNew value: +{}
    • addedOutput schema / properties / financials / items / properties / CERT / maximum
      Added value: +9007199254740991
    • addedOutput schema / properties / financials / items / properties / CERT / minimum
      Added value: +-9007199254740991
    • addedOutput schema / properties / next_offset / maximum
      Added value: +9007199254740991
    • addedOutput schema / properties / next_offset / minimum
      Added value: +-9007199254740991
    • addedOutput schema / properties / offset / maximum
      Added value: +9007199254740991
    • addedOutput schema / properties / offset / minimum
      Added value: +-9007199254740991
    • addedOutput schema / properties / total / maximum
      Added value: +9007199254740991
    • addedOutput schema / properties / total / minimum
      Added value: +-9007199254740991
  2. Changed2 schema fields changedv1.26.0
    • changedInput schema / properties / repdte / description
      Previous value: -"Filter by Report Date (REPDTE) in YYYYMMDD format. FDIC data is published quarterly on call report dates: March 31, June 30, September 30, and December 31. Example: 20231231 for Q4 2023. If omitted, returns all available dates (sorted most recent first by default)."New value: +"Filter by Report Date (REPDTE) in YYYYMMDD format (quarter-end: 0331, 0630, 0930, 1231). If omitted, returns all available dates (sorted most recent first)."
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "$schema": "http://json-schema.org/draft-07/schema#",
      +  "additionalProperties": false,
      +  "properties": {
      +    "count": {
      +      "type": "integer"
      +    },
      +    "financials": {
      +      "items": {
      +        "additionalProperties": true,
      +        "properties": {
      +          "ASSET": {
      +            "type": "number"
      +          },
      +          "CERT": {
      +            "type": "integer"
      +          },
      +          "DEP": {
      +            "type": "number"
      +          },
      +          "EEFFR": {
      +            "type": "number"
      +          },
      +          "IDT1CER": {
      +            "type": "number"
      +          },
      +          "LNLSDEPR": {
      +            "type": "number"
      +          },
      +          "NAME": {
      +            "type": "string"
      +          },
      +          "NCLNLSR": {
      +            "type": "number"
      +          },
      +          "NETINC": {
      +            "type": "number"
      +          },
      +          "NIMY": {
      +            "type": "number"
      +          },
      +          "REPDTE": {
      +            "type": [
      +              "string",
      +              "number"
      +            ]
      +          },
      +          "ROA": {
      +            "type": "number"
      +          },
      +          "ROE": {
      +            "type": "number"
      +          }
      +        },
      +        "type": "object"
      +      },
      +      "type": "array"
      +    },
      +    "has_more": {
      +      "type": "boolean"
      +    },
      +    "next_offset": {
      +      "type": "integer"
      +    },
      +    "offset": {
      +      "type": "integer"
      +    },
      +    "total": {
      +      "type": "integer"
      +    },
      +    "truncated": {
      +      "type": "boolean"
      +    }
      +  },
      +  "required": [
      +    "total",
      +    "offset",
      +    "count",
      +    "has_more",
      +    "financials"
      +  ],
      +  "type": "object"
      +}
  3. First observedv1.1.3

TDQS

A4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, covering the safety profile. The description adds context about the data type and points to the field catalog (fdic://schemas/financials), which is useful. It does not add details about rate limits, pagination behavior beyond schema, or response format, but since annotations carry the main behavioral burden, a 3 is appropriate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences with no filler. The first sentence front-loads the purpose (quarterly Call Report data), and the second gives filtering guidance and a pointer to the full field catalog. Every word earns its place; it is concise and well-structured.

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?

Given that an output schema exists (so return values are defined) and the input schema covers all 8 parameters with descriptions, the description adds enough context: the data type, primary filters, and a reference to the extensive field catalog. It does not mention default sorting or pagination, but those are covered in the parameter descriptions. The tool is relatively complex, yet the description, combined with schema, provides adequate guidance.

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%, meaning every parameter has a description in the input schema. The tool description mentions CERT and REPDTE as filters, but this merely restates what the schema already documents. It does not add syntax details, relationships between parameters, or compensate for any gaps because there are none. Thus baseline 3 applies.

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 explicitly states the tool provides quarterly Call Report data (balance sheet, income, capital, performance ratios) for FDIC-insured institutions, which clearly distinguishes it from sibling tools like fdic_search_summary (summary data), fdic_search_demographics (demographics), and fdic_search_institutions (institution info). It also names the primary filters (CERT and REPDTE), making the purpose unambiguous.

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 begins with 'Use this when the user wants quarterly Call Report data', which gives clear context for when to invoke it. However, it does not explicitly mention alternatives or exclusions, even though many sibling tools exist. It could say 'for summary data use fdic_search_summary' etc., but the absence of explicit when-not guidance keeps it at a 4 rather than a 5.

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