NCUA credit union data

io.github.bnovariniv0.1.2更新于 Oct 8, 2026

NCUA call report data for US credit unions, 2018-2026: profiles, peer comparison, time series.

已验证Streamable HTTP可网页运行Data & Analytics Finance

概览

AI 生成的概览

查询整理后的 NCUA 信用合作社 call report 数据（2018-2026），获取机构概况、同业比较和指标时间序列。

功能: 将美国信用合作社的 NCUA call report 数据整理为可查询的表：机构概况、115 个精选 call report 字段、52 个计算指标以及数据字典。工具包括 list_fields、find_credit_union、credit_union_profile、metric_series、peer_compare 和 query_metrics，后者支持筛选、排序和限制，但不支持原始 SQL。既可作为托管远程端点使用，也可通过 DuckDB 读取 Parquet 文件在本地以 stdio 运行。
适用场景: 适合让助手回答美国信用合作社财务问题，例如贷款、存款结构、盈利、人员、效率、增长，或按资产组、州、牌照类型进行同业比较。适用于 2018 年以来的季度趋势分析，而非实时数据或 2018 年之前的数据。
运行要求: 托管端点只需网络访问，每个客户端限速每分钟 60 次请求。本地方式需要 Python 及 ncua-data-analysis 包（例如通过 uvx），会一次性将发布版 Parquet 文件下载到缓存目录，并可用环境变量 NCUA_DATA_DIR 指向已下载的文件。未声明需要账户、API 密钥或请求头。

安装前请注意

该服务为只读，不要求任何凭据。数据由信用合作社自行申报且偶尔修订；部分字段为估算或近似值，对账检查并非全部与 NCUA 公布的总数一致。合并会使跨合并期的单机构增长失去意义，用户应筛选 is_federally_insured 以匹配 NCUA 总数。

安装

在 SourceWeft 中

打开控制台中的 NCUA credit union data，将其添加到工作区。
为需要使用其工具的对话启用该服务。

Web executable，通过 Streamable HTTP。远程服务在工作区中配置后即可从网页运行时运行。

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "ncua-data-analysis": {
      "type": "http",
      "url": "https://ncua-data-analysis.fly.dev/mcp"
    }
  }
}

README

ncua-data-analysis

Clean, documented, quarterly credit union data from NCUA call reports, 2018 to today: lending, deposit mix, earnings, staffing and efficiency.

NCUA publishes every federally insured credit union's quarterly 5300 call report as free bulk files. They are hard to use: 3,300+ account columns split across 17 wide tables, form changes that move accounts around, year-to-date income, and a data dictionary written as form instructions. This project turns that into four tidy tables you can query with DuckDB, pandas or anything that reads Parquet.

Status: v0. 115 curated fields and 52 computed metrics, 34 quarters (2018 Q1 to 2026 Q2), checked against NCUA's own published totals. See what is not done yet.

Tables

Table	Grain	What it is
`dim_credit_union`	credit union x quarter	Name, location, charter type, peer group, low-income and MDI flags, and `is_federally_insured`.
`fact_call_report_curated`	credit union x quarter	115 curated account values with plain names: balance sheet, shares and capital, deposit composition (share drafts, regular, money market, certificates, IRA, non-member), loan balances by type, originations, delinquency, charge-offs, income statement, employees and branches.
`metrics`	credit union x quarter	52 computed metrics: delinquency, loan-to-share, ROA, NIM, loan and deposit mix, growth, efficiency ratio, members and assets per employee, per-branch figures, de-cumulated quarterly income.
`dictionary`	column	Description, unit, NCUA account codes, and first and last quarter each field has data.

Join on quarter + cu_number. Dollar fields are dollars. Fields ending in _ytd are year to date and reset each January (the Q4 value is the full year); metrics annualizes them.

sql

-- Which large credit unions grew auto lending fastest last year?SELECT d.name, d.state, m.auto_loan_growth_yoy, f.loans_new_vehicle + f.loans_used_vehicle AS auto_loansFROM fact_call_report_curated fJOIN dim_credit_union d USING (quarter, cu_number)JOIN metrics m USING (quarter, cu_number)WHERE f.quarter = '2026-06' AND d.is_federally_insured AND d.peer_group = 6ORDER BY m.auto_loan_growth_yoy DESC LIMIT 10;

-- Which large credit unions grew auto lending fastest last year?SELECT d.name, d.state, m.auto_loan_growth_yoy, f.loans_new_vehicle + f.loans_used_vehicle AS auto_loansFROM fact_call_report_curated fJOIN dim_credit_union d USING (quarter, cu_number)JOIN metrics m USING (quarter, cu_number)WHERE f.quarter = '2026-06' AND d.is_federally_insured AND d.peer_group = 6ORDER BY m.auto_loan_growth_yoy DESC LIMIT 10;

Run it

bash

pip install -e .ncua-data all          # download 34 quarters (~270 MB), build tables, reconcilepython -m unittest discover -s tests

pip install -e .ncua-data all          # download 34 quarters (~270 MB), build tables, reconcilepython -m unittest discover -s tests

Output lands in data/out/ as Parquet. Raw ZIPs are never committed. Links are scraped from NCUA's quarterly data page.

Numbers you can trust

For June 2026 and December 2025 the totals reconcile to the figures in NCUA's Quarterly Credit Union Data Summary: credit union count, members, loans by type, shares, net worth ratio, delinquency, income and expense. 60 of 67 checks match across six year-ends (2021 to June 2026). The 7 that do not are historical deposit lines that differ by under $0.5B (under 0.1%), for example Dec 2025 money market $367.5B versus $368.0B published. All June 2026 lines match. The likely cause is restated history in NCUA's table, which has not been confirmed. Full table: docs/RECONCILIATION.md.

Things to know before using it:

Filter to is_federally_insured. NCUA's raw files include about 85 state-chartered credit unions it does not insure. Its published totals leave them out.
The form changed in 2022 and 2023. NCUA redesigned the call report and adopted CECL, so some accounts disappear and new ones appear. Fields that span the change map both account codes (for example the allowance is Acct_719 before CECL and Acct_AS0048 after). Fields that only exist after the change say so in the dictionary.
Net worth ratio. NCUA's published ratio excludes the CECL transition provision from 2023 on. This dataset carries that provision (cecl_transition_provision) and metrics.net_worth_ratio_ex_cecl matches NCUA.
Employees are estimated. employees_fte_estimate is full-time plus half of part-time. It is not an NCUA definition and is not reconciled to a published figure.
Net charge-off ratio, ROA and NIM use NCUA's own average balances, which are not public. Metrics here use a four-quarter average and land within a few basis points of NCUA's published values, not on them.
Mergers. Credit union counts fell from 5,375 to 4,214 since 2018. A merged credit union's history stays under its old charter number, so per-institution growth across a merger is not meaningful.
Reports are self-reported and occasionally reposted as "Revised". The ZIPs are used as NCUA publishes them today.

Not done yet

Commercial-loan delinquency by type (NCUA moved these to new account codes in 2022).
More fields. The target is 150 to 200; 115 are in and verified.
Years before 2018 (the download links use two other naming patterns).
A static analytics site and natural-language querying. The dictionary is built to be the semantic layer for that.

MCP server (v1)

A local MCP server lets an AI assistant query this dataset in plain language. It runs over stdio, reads the release Parquet files with DuckDB (downloaded once to ~/.cache/ncua-data-analysis), and builds its tool descriptions from the dictionary table.

json

{  "mcpServers": {    "ncua-data": {      "command": "uvx",      "args": ["--from", "ncua-data-analysis", "ncua-data-mcp"]    }  }}

{  "mcpServers": {    "ncua-data": {      "command": "uvx",      "args": ["--from", "ncua-data-analysis", "ncua-data-mcp"]    }  }}

The package is on PyPI: https://pypi.org/project/ncua-data-analysis/. To run the latest development version instead, use "args": ["--from", "git+https://github.com/bnovarini/ncua-data-analysis", "ncua-data-mcp"].

Hosted, nothing to install: https://ncua-data-analysis.fly.dev/mcp (streamable HTTP, read-only, rate limited to 60 requests a minute per client). Add it as a remote MCP server in any client that supports one, for example {"mcpServers": {"ncua-data": {"url": "https://ncua-data-analysis.fly.dev/mcp"}}}.

[Install in Cursor] [Install in VS Code] [Install in VS Code Insiders]

Claude Code: claude mcp add --transport http ncua-data https://ncua-data-analysis.fly.dev/mcp

Tools: list_fields, find_credit_union, credit_union_profile, metric_series (one credit union or an aggregate across all), peer_compare (by asset group, state or charter), and query_metrics (filters, ordering and limits; no raw SQL). Set NCUA_DATA_DIR to use a folder of already-downloaded files. Status: first working version, tested over stdio with a real MCP client; not yet listed in the MCP registry.

Download

Ready-made Parquet files are attached to the v0.1.1 release. GitHub caps release files at 25 MB, so fact_call_report_curated and metrics come in three parts by year (2018-2020, 2021-2023, 2024-2026) with identical columns:

python

import duckdbbase = "https://github.com/bnovarini/ncua-data-analysis/releases/download/v0.1.1/"parts = [base + f"metrics_{y}.parquet" for y in ("2018_2020", "2021_2023", "2024_2026")]duckdb.sql(f"SELECT quarter, count(*) FROM read_parquet({parts}) GROUP BY 1 ORDER BY 1").show()

import duckdbbase = "https://github.com/bnovarini/ncua-data-analysis/releases/download/v0.1.1/"parts = [base + f"metrics_{y}.parquet" for y in ("2018_2020", "2021_2023", "2024_2026")]duckdb.sql(f"SELECT quarter, count(*) FROM read_parquet({parts}) GROUP BY 1 ORDER BY 1").show()

Data source and license

Data: National Credit Union Administration, 5300 Call Report Quarterly Data. NCUA does not state a license on the download page. As a US federal agency's work it is assumed to be public domain, but that assumption has not been confirmed. Credit NCUA when you use it.

Code: MIT, see LICENSE.

来源：README.md，提交 5780ed7

工具

工具元数据尚未被收录。

版本历史

v0.1.2最新Oct 8, 2026