Skip to main content
Glama
cliwant

mcp-sam-gov

by cliwant

fdic_bank_failures

Read-only

Retrieve historical FDIC-insured bank failures and assistance transactions for counterparty due diligence. Filter by state, year, or certificate to identify red-flagged institutions.

Instructions

Historical FDIC-insured bank failures & assistance transactions (keyless FDIC BankFind, api.fdic.gov/banks/failures) — B2G counterparty / entity due-diligence: a failed or FDIC-assisted institution is a red flag, and CERT links a failure back to fdic_search_institutions / fdic_institution_financials. Exact-key filters: state (2-letter → PSTALP — NOTE the /failures state field is PSTALP, NOT STALP), failYear (→ FAILYR; e.g. 2023 → the 5 real 2023 failures incl. Silicon Valley Bank & First Republic Bank), cert (→ CERT, the STABLE entity key). limit (≤1000, def 100), offset (≤100000), sortBy (allowlisted enum FAILDATE/COST/QBFASSET/QBFDEP/NAME/FAILYR, def FAILDATE), sortOrder (def DESC → most-recent first). Returns { failures:[{ name, cert, failDate, failYear, city, state, resolutionType, resolutionFund, estimatedLossUSD, depositsUSD, assetsUSD, id }] }. NO name/city filter — FDIC's /failures search param is IGNORED (it returns the whole dataset), so name/city are SHOWN in each row but NOT searchable; to find a specific bank's failure, resolve its CERT via fdic_search_institutions then filter here by cert. HONESTY: totalAvailable is the EXACT meta.total (stable across offset — never the page length); failDate is normalized from FDIC's M/D/YYYY to ISO YYYY-MM-DD (an unrecognized value is surfaced raw + disclosed, never nulled/fabricated); COST/QBFDEP/QBFASSET are $thousands normalized to whole USD ×1000 (null-never-0 — a genuine 0 = a fully-assisted no-loss stays 0, a NEGATIVE COST = a net DIF recovery/gain not a loss, absent → null); the ONLY honest empty is meta.total:0/data:[] ⇒ complete:true/total:0, every other envelope (400 errors[]/404/non-JSON/missing meta or data) THROWS (never a fake empty); the point-in-time snapshot build time is disclosed. NOTE: FDIC keys on CERT, not SAM UEI/DUNS.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
certNoFilter by FDIC certificate number (the STABLE entity key; → CERT filter). Resolve a bank's CERT via fdic_search_institutions.
limitNoRows per page, 1..1000, default 100.
stateNoFilter by 2-letter US state code (uppercase; → PSTALP filter — the /failures state field is PSTALP, NOT STALP). e.g. 'CA'.
offsetNo0-based row offset for pagination, 0..100000, default 0.
sortByNoSort field (allowlisted enum; default FAILDATE = failure date). An unknown field is rejected before fetch.
failYearNoFilter by year of failure (→ FAILYR filter). 1934..current UTC year. e.g. 2023 → the 5 real 2023 failures (Silicon Valley Bank, Signature Bank, First Republic Bank, Heartland Tri-State Bank, Citizens Bank).
sortOrderNoSort direction, default DESC (most-recent failures first).
Behavior5/5

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

Goes far beyond annotations by detailing data normalization (dates to ISO, financials to USD), handling of zeros and negatives, error behavior (throws on non-200), and disclosure of snapshot build time. All annotations (readOnlyHint, openWorldHint) are respected and expanded.

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?

Long but well-structured with clear sections; front-loads purpose and use. Every sentence is informative, though some internal detail (e.g., HONESTY block) could be slightly condensed without losing clarity.

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?

Fully covers return shape, pagination, sorting, filtering limitations, data integrity, and cross-tool linking. Lacks output schema but description provides return field list. Handles complexity of 7 parameters and many siblings comprehensively.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Adds significant meaning beyond the schema: explains field name mappings (PSTALP vs STALP, FAILYR), provides examples for failYear, clarifies that sortBy unknown fields are rejected, and notes bounds for limit/offset. Schema coverage is 100%, but description still adds value.

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?

Clearly identifies the tool as returning historical FDIC-insured bank failures and assistance transactions, with specific verb 'returns' and resource. Distinguishes from sibling FDIC tools by noting CERT links to fdic_search_institutions and fdic_institution_financials.

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

Usage Guidelines5/5

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

Provides explicit guidance on when to use (due diligence on failed institutions), how to filter (exact-key filters for state, failYear, cert), and what not to do (no name/city filter; alternative: resolve CERT via fdic_search_institutions). Includes defaults, limits, and examples.

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/cliwant/mcp-sam-gov'

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