Skip to main content
Glama
jflamb

FDIC BankFind MCP Server

by jflamb

Search Bank Failures

fdic_search_failures
Read-onlyIdempotent

Search FDIC bank failure data to find details on failed financial institutions, including failure dates, resolution types, costs, and acquiring institutions.

Instructions

Search for details on failed FDIC-insured financial institutions.

Returns data on bank failures including failure date, resolution type, estimated cost to the FDIC Deposit Insurance Fund, and acquiring institution info.

Common filter examples:

  • By state: STALP:CA (two-letter state code)

  • By year range: FAILDATE:[2008-01-01 TO 2010-12-31]

  • Recent failures: FAILDATE:[2020-01-01 TO *]

  • By resolution type: RESTYPE:PAYOFF or RESTYPE:"PURCHASE AND ASSUMPTION"

  • Large failures by cost: COST:[100000 TO *] (cost in $thousands)

  • By name: NAME:"Washington Mutual"

Resolution types (RESTYPE): PAYOFF = depositors paid directly, no acquirer PURCHASE AND ASSUMPTION = acquirer buys assets and assumes deposits PAYOUT = variant of payoff with insured-deposit transfer

Key returned fields:

  • CERT: FDIC Certificate Number

  • NAME: Institution name

  • CITY, STALP (two-letter state code), STNAME (full state name): Location

  • FAILDATE: Date of failure (YYYY-MM-DD)

  • SAVR: Savings association flag (SA) or bank (BK)

  • RESTYPE: Resolution type (see above)

  • QBFASSET: Total assets at failure ($thousands)

  • COST: Estimated cost to FDIC Deposit Insurance Fund ($thousands)

Args:

  • filters (string, optional): ElasticSearch query filter

  • fields (string, optional): Comma-separated field names

  • limit (number): Records to return (default: 20)

  • offset (number): Pagination offset (default: 0)

  • sort_by (string, optional): Field to sort by (e.g., FAILDATE, COST)

  • sort_order ('ASC'|'DESC'): Sort direction (default: 'ASC')

Prefer concise human-readable summaries or tables when answering users. Structured fields are available for totals, pagination, and failure records.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
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"
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
limitNoMaximum number of records to return (1-10000, default: 20)
offsetNoNumber of records to skip for pagination (default: 0)
sort_byNoField name to sort results by. Example: ASSET, NAME, FAILDATE
sort_orderNoSort direction: ASC (ascending) or DESC (descending)ASC

Implementation Reference

  • The handler function for the `fdic_search_failures` tool, which queries the failures endpoint and formats the response.
    async (params) => {
      try {
        const response = await queryEndpoint(ENDPOINTS.FAILURES, params);
        const records = extractRecords(response);
        const pagination = buildPaginationInfo(
          response.meta.total,
          params.offset ?? 0,
          records.length,
        );
        const output = { ...pagination, failures: records };
        const text = truncateIfNeeded(
          formatSearchResultText("failures", records, pagination, [
            "CERT",
            "NAME",
            "CITY",
            "STALP",
            "FAILDATE",
            "COST",
            "RESTYPE",
          ]),
          CHARACTER_LIMIT,
          "Request fewer fields, narrow your filters, or paginate with limit/offset.",
        );
        return {
          content: [{ type: "text", text }],
          structuredContent: output,
        };
      } catch (err) {
        return formatToolError(err);
      }
    },
  • Registration of the `fdic_search_failures` tool.
      server.registerTool(
        "fdic_search_failures",
        {
          title: "Search Bank Failures",
          description: `Search for details on failed FDIC-insured financial institutions.
    
    Returns data on bank failures including failure date, resolution type, estimated cost to the FDIC Deposit Insurance Fund, and acquiring institution info.
    
    Common filter examples:
      - By state: STALP:CA (two-letter state code)
      - By year range: FAILDATE:[2008-01-01 TO 2010-12-31]
      - Recent failures: FAILDATE:[2020-01-01 TO *]
      - By resolution type: RESTYPE:PAYOFF or RESTYPE:"PURCHASE AND ASSUMPTION"
      - Large failures by cost: COST:[100000 TO *]  (cost in $thousands)
      - By name: NAME:"Washington Mutual"
    
    Resolution types (RESTYPE):
      PAYOFF = depositors paid directly, no acquirer
      PURCHASE AND ASSUMPTION = acquirer buys assets and assumes deposits
      PAYOUT = variant of payoff with insured-deposit transfer
    
    Key returned fields:
      - CERT: FDIC Certificate Number
      - NAME: Institution name
      - CITY, STALP (two-letter state code), STNAME (full state name): Location
      - FAILDATE: Date of failure (YYYY-MM-DD)
      - SAVR: Savings association flag (SA) or bank (BK)
      - RESTYPE: Resolution type (see above)
      - QBFASSET: Total assets at failure ($thousands)
      - COST: Estimated cost to FDIC Deposit Insurance Fund ($thousands)
    
    Args:
      - filters (string, optional): ElasticSearch query filter
      - fields (string, optional): Comma-separated field names
      - limit (number): Records to return (default: 20)
      - offset (number): Pagination offset (default: 0)
      - sort_by (string, optional): Field to sort by (e.g., FAILDATE, COST)
      - sort_order ('ASC'|'DESC'): Sort direction (default: 'ASC')
    
    Prefer concise human-readable summaries or tables when answering users. Structured fields are available for totals, pagination, and failure records.`,
          inputSchema: CommonQuerySchema,
          annotations: {
            readOnlyHint: true,
            destructiveHint: false,
            idempotentHint: true,
            openWorldHint: true,
          },
        },
Behavior4/5

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

Annotations already provide readOnlyHint=true, destructiveHint=false, openWorldHint=true, and idempotentHint=true. The description adds valuable behavioral context beyond annotations by explaining what data is returned (failure date, resolution type, cost, acquiring institution info), providing resolution type definitions, and specifying key returned fields. It also includes guidance about preferring concise human-readable summaries or tables.

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 well-structured with clear sections: purpose statement, return data explanation, common filter examples, resolution type definitions, key returned fields, and parameter listing. While comprehensive, some sections (like the detailed field descriptions) could be more concise. Most sentences earn their place by providing useful information.

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?

Given the tool's complexity (search with multiple parameters), rich annotations (4 hints), and 100% schema coverage, the description provides excellent contextual completeness. It explains what the tool does, what data it returns, how to use filters, defines key concepts (resolution types), and provides usage guidance. The absence of an output schema is compensated by the detailed explanation of returned fields.

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 fully documents all 6 parameters. The description adds minimal parameter semantics beyond the schema - it lists the parameters in the Args section but provides no additional explanation about their usage or relationships. The baseline of 3 is appropriate when the schema does the heavy lifting.

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 clearly states the tool searches for details on failed FDIC-insured financial institutions, specifying the verb 'search' and resource 'failed FDIC-insured financial institutions'. It distinguishes from siblings like fdic_search_institutions (general institutions) and fdic_get_institution_failure (specific failure) by focusing on filtered search of failure data.

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 provides clear context for when to use this tool (searching for bank failure details) and includes common filter examples that guide usage. However, it doesn't explicitly state when to use alternatives like fdic_get_institution_failure for a specific institution's failure or fdic_search_institutions for non-failed institutions.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/jflamb/fdic-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server