CFPB consumer complaints
CFPB consumer complaints: 18M records, 3.85M archived narratives. Search, counts, trends.
我该使用它吗
质量与安全性
发现（1）
- LOWTool 'get_complaint' description lacks action verb在 get_complaint 中
基于对工具定义和协议合规性的自动分析。
上下文开销
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中：
{
"mcpServers": {
"cfpb-complaints-analysis": {
"url": "https://cfpb-complaints-analysis.fly.dev/mcp"
}
}
}远程端点
https://cfpb-complaints-analysis.fly.dev/mcpstreamable-http它能做什么
工具清单
工具（10）
⚪dataset_info
What this dataset is: row counts, date ranges, narrative coverage, and the narrative freeze. Call first when unsure about coverage.
输入模式
{
"type": "object",
"properties": {},
"title": "dataset_infoArguments"
}🟢list_values(field, search, product, limit)
List the values of a field with complaint counts, to find exact product/issue/response names. field is one of: product, sub_product, issue, sub_issue, company_response, company_public_response, submitted_via, state, timely_response. Optional search narrows by substring; product narrows issues to that product. Filters: company (exact name as in find_company), company_contains (substring), product, sub_product, issue, product: CFPB renamed credit reporting twice, so it appears under three product names (use list_values field=product), company_response (exact CFPB value, case-insensitive), submitted_via, state (2 letters), tag (e.g. 'Servicemember', 'Older American'), timely (true/false), date_from/date_to (YYYY-MM-DD or YYYY-MM, on date received).
输入模式
{
"type": "object",
"properties": {
"field": {
"title": "Field",
"type": "string"
},
"search": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Search"
},
"product": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Product"
},
"limit": {
"default": 50,
"title": "Limit",
"type": "integer"
}
},
"required": [
"field"
],
"title": "list_valuesArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"items": {
"additionalProperties": true,
"type": "object"
},
"title": "Result",
"type": "array"
}
},
"required": [
"result"
],
"title": "list_valuesOutput"
}🟢find_company(name, limit)
Find companies by name. CFPB lists the same firm under variants and subsidiaries (e.g. 'EQUIFAX, INC.', 'Equifax Information Services LLC'), so this returns every matching name with complaint counts and first/last dates; pass the exact names you want to other tools via company, or use company_contains for all variants at once.
输入模式
{
"type": "object",
"properties": {
"name": {
"title": "Name",
"type": "string"
},
"limit": {
"default": 25,
"title": "Limit",
"type": "integer"
}
},
"required": [
"name"
],
"title": "find_companyArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"items": {
"additionalProperties": true,
"type": "object"
},
"title": "Result",
"type": "array"
}
},
"required": [
"result"
],
"title": "find_companyOutput"
}🟢complaint_counts(group_by, company, company_contains, product, sub_product, ...)
Count complaints, optionally grouped. group_by is one or two of: year, quarter, month, product, sub_product, issue, sub_issue, company, state, company_response, company_public_response, submitted_via, timely_response. Returns complaints, timely_rate, monetary_relief_rate, nonmonetary_relief_rate, in_progress_rate per group (rates are fractions of that group's complaints). Counts are raw complaint counts, not adjusted for company size. In progress and Untimely response are CFPB response categories, not outcomes. Filters: company (exact name as in find_company), company_contains (substring), product, sub_product, issue, product: CFPB renamed credit reporting twice, so it appears under three product names (use list_values field=product), company_response (exact CFPB value, case-insensitive), submitted_via, state (2 letters), tag (e.g. 'Servicemember', 'Older American'), timely (true/false), date_from/date_to (YYYY-MM-DD or YYYY-MM, on date received).
输入模式
{
"type": "object",
"properties": {
"group_by": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Group By"
},
"company": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Company"
},
"company_contains": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Company Contains"
},
"product": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Product"
},
"sub_product": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Sub Product"
},
"issue": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Issue"
},
"state": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "State"
},
"date_from": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Date From"
},
"date_to": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Date To"
},
"company_response": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Company Response"
},
"timely": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"default": null,
"title": "Timely"
},
"submitted_via": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Submitted Via"
},
"tag": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Tag"
},
"has_narrative": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"default": null,
"title": "Has Narrative"
},
"order_by": {
"default": "complaints",
"title": "Order By",
"type": "string"
},
"limit": {
"default": 25,
"title": "Limit",
"type": "integer"
},
"offset": {
"default": 0,
"title": "Offset",
"type": "integer"
}
},
"title": "complaint_countsArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"items": {
"additionalProperties": true,
"type": "object"
},
"title": "Result",
"type": "array"
}
},
"required": [
"result"
],
"title": "complaint_countsOutput"
}🟡trend(period, company, company_contains, product, issue, ...)
Complaints over time (month, quarter or year), for one filter set. Set period to month, quarter or year. The latest period is partial. In progress and Untimely response are CFPB response categories, not outcomes. Filters: company (exact name as in find_company), company_contains (substring), product, sub_product, issue, product: CFPB renamed credit reporting twice, so it appears under three product names (use list_values field=product), company_response (exact CFPB value, case-insensitive), submitted_via, state (2 letters), tag (e.g. 'Servicemember', 'Older American'), timely (true/false), date_from/date_to (YYYY-MM-DD or YYYY-MM, on date received).
输入模式
{
"type": "object",
"properties": {
"period": {
"default": "month",
"title": "Period",
"type": "string"
},
"company": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Company"
},
"company_contains": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Company Contains"
},
"product": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Product"
},
"issue": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Issue"
},
"state": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "State"
},
"date_from": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Date From"
},
"date_to": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Date To"
},
"company_response": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Company Response"
},
"tag": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Tag"
},
"submitted_via": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Submitted Via"
}
},
"title": "trendArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"items": {
"additionalProperties": true,
"type": "object"
},
"title": "Result",
"type": "array"
}
},
"required": [
"result"
],
"title": "trendOutput"
}⚪company_profile(company, company_contains, date_from, date_to, product)
Profile of one company (or all name variants via company_contains): totals, first/last complaint, top products, issues, states, response outcomes, yearly counts. Counts are not adjusted for company size. Optional date_from/date_to/product.
输入模式
{
"type": "object",
"properties": {
"company": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Company"
},
"company_contains": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Company Contains"
},
"date_from": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Date From"
},
"date_to": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Date To"
},
"product": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Product"
}
},
"title": "company_profileArguments"
}⚪compare_companies(companies, product, issue, state, date_from, ...)
Side-by-side comparison of up to 6 companies on the same filters: complaints, timely_rate, relief rates, top product and top issue each. Each entry in companies is matched as a substring on the company name (all variants combined). Counts are not adjusted for company size.
输入模式
{
"type": "object",
"properties": {
"companies": {
"items": {
"type": "string"
},
"title": "Companies",
"type": "array"
},
"product": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Product"
},
"issue": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Issue"
},
"state": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "State"
},
"date_from": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Date From"
},
"date_to": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Date To"
}
},
"required": [
"companies"
],
"title": "compare_companiesArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"items": {
"additionalProperties": true,
"type": "object"
},
"title": "Result",
"type": "array"
}
},
"required": [
"result"
],
"title": "compare_companiesOutput"
}🟢search_narratives(query, phrase, any_of, company, company_contains, ...)
Keyword search over archived complaint narratives (frozen at 2026-08-14; CFPB stopped publishing them in September 2026). query: words that must all appear (case-insensitive), or use phrase for an exact phrase, or any_of for alternatives. Returns a snippet per complaint plus its structured fields, newest first (date order, not relevance-ranked: every result contains all your words); use get_complaint for the full text. Searches scan text, so narrow with date_from/date_to, company/company_contains, product or state when you can: an unfiltered search over all years can time out. Filters: company, company_contains, product, state (2 letters), date_from/date_to (YYYY-MM-DD or YYYY-MM), plus issue, sub_product, company_response, timely, tag (these are slower).
输入模式
{
"type": "object",
"properties": {
"query": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Query"
},
"phrase": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Phrase"
},
"any_of": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Any Of"
},
"company": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Company"
},
"company_contains": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Company Contains"
},
"product": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Product"
},
"sub_product": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Sub Product"
},
"issue": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Issue"
},
"state": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "State"
},
"date_from": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Date From"
},
"date_to": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Date To"
},
"company_response": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Company Response"
},
"timely": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"default": null,
"title": "Timely"
},
"tag": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Tag"
},
"limit": {
"default": 10,
"title": "Limit",
"type": "integer"
},
"offset": {
"default": 0,
"title": "Offset",
"type": "integer"
}
},
"title": "search_narrativesArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"items": {
"additionalProperties": true,
"type": "object"
},
"title": "Result",
"type": "array"
}
},
"required": [
"result"
],
"title": "search_narrativesOutput"
}🟢count_narratives(query, phrase, any_of, group_by, company, ...)
Count how many archived narratives match a keyword search, optionally grouped by year, month, product, company, issue or state. Same search and filter arguments as search_narratives (without the slower issue/response filters). Use this for 'how many complaints mention X'. Counts only complaints that have a narrative (through 2026-08-14), not all complaints. Narrow with date, company or product when you can.
输入模式
{
"type": "object",
"properties": {
"query": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Query"
},
"phrase": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Phrase"
},
"any_of": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Any Of"
},
"group_by": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Group By"
},
"company": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Company"
},
"company_contains": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Company Contains"
},
"product": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Product"
},
"state": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "State"
},
"date_from": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Date From"
},
"date_to": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Date To"
},
"limit": {
"default": 25,
"title": "Limit",
"type": "integer"
}
},
"title": "count_narrativesArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"items": {
"additionalProperties": true,
"type": "object"
},
"title": "Result",
"type": "array"
}
},
"required": [
"result"
],
"title": "count_narrativesOutput"
}🟢get_complaint(complaint_id)
One complaint by its CFPB Complaint ID: all structured fields and, when archived, the full narrative.
输入模式
{
"type": "object",
"properties": {
"complaint_id": {
"title": "Complaint Id",
"type": "integer"
}
},
"required": [
"complaint_id"
],
"title": "get_complaintArguments"
}社区
证据