MCP.Market

Cfpb MCP server

online · 100% uptime
by pipeworx-io·io.github.pipeworx-io/cfpb·v0.2.1

CFPB MCP — Consumer Financial Protection Bureau complaint database (free, no auth)

A87/100grade A
What users say
No reviews yet
Be the first
Safety scan
A87/100

not scanned yet

Adoption
Growing

0 stars

Reviews

Write one

Nobody has reviewed Cfpb yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Cfpb tools

Tool list not cached yet. `describe` through the gateway fetches it live.

Not scanned yet. New listings are scanned within a day or two of arriving.

How Cfpb compares

Against every graded Databases MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
87/100
higher than 70% of 802 Databases servers
Uptime
100%
of our recent checks; the typical remote Databases server answers 100%
Response time
143 ms
faster than 73% of 292 Databases servers

Release history: 6 versions in the registry since 2026-04-22, latest 2026-10-31, typically one every 5 days.

Install Cfpb in Claude Code, Cursor or VS Code

claude mcp add --transport http cfpb https://gateway.pipeworx.io/cfpb/mcp
Add to Cursor

What the publisher says

From the Cfpb repository's README, as published. We do not edit it. Read it on GitHub

CFPB — Consumer Financial Protection Bureau

The CFPB's Consumer Complaint Database. Every consumer complaint filed with the CFPB about a financial product (mortgages, credit cards, debt collection, banking, payments, student loans, etc.), tagged with company, product, issue, response, and outcome. ~5M+ complaints since 2011. Free, no auth, public.

Part of Pipeworx — an MCP gateway connecting AI agents to 1679+ live data sources.

Why this matters for AI agents

For consumer-finance risk assessment, brand reputation analysis, or "is this company's posture deteriorating?" questions, CFPB complaints are the canonical leading indicator. Spikes correlate with brewing reputational issues, often before they show up in earnings.

Common flows:

  • Company posture. cfpbcompanycomplaints({company: "Wells Fargo"}) → complaint volume by year, product, issue.
  • Product breakdown. cfpbproductbreakdown → industry-wide distribution of complaints across product categories.
  • Issue-level drilldown. Filter by issue tags (e.g., "Charged fees or interest you didn't expect").

Used by the fintechcompanydeepdive compound and the financialhealth_check recipe.

Auth

None. The CFPB Consumer Complaint Database is fully public.

Product taxonomy

CFPB groups complaints into a stable taxonomy:

Product-level complaint volume varies massively. A bank with high mortgage complaints isn't directly comparable to a fintech with high "money transfer" complaints — context matters.

Update cadence

Daily. Complaints generally appear within ~15 days of submission. Consumer responses (whether the user marked the company response as "satisfactory") trickle in over weeks.

Common pitfalls

  • Volume ≠ wrongdoing. A bank with 100,000 customers and 100 complaints has a low rate; a tiny lender with 1,000 customers and 50 complaints has a much higher rate. Always normalize by customer base or AUM where possible.
  • Company name normalization. "JPMorgan Chase," "JPMorgan Chase Bank, N.A.," "Chase" — all the same company in different contexts. CFPB normalizes to a "company" field; verify by searching multiple variants.
  • Response status meaning. "Closed with relief," "Closed without relief," "Closed with monetary relief" — these are the company's own classification of the outcome. Read the per-complaint narrative for context.
  • Selection bias. Not every dissatisfied customer files with the CFPB. Volume reflects awareness of the CFPB as a recourse, not pure customer dissatisfaction. Trends over time are more meaningful than absolute counts.
  • Industry comparisons. Use cfpbproductbreakdown to anchor a company's volume against industry baseline before judging.

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "cfpb": {
      "url": "https://gateway.pipeworx.io/cfpb/mcp"
    }
  }
}

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/cfpb/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — askpipeworx, discovertools, search_within, remember/recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Cfpb: common questions

Is Cfpb MCP server safe?
Yes, by our scan: it is graded A (87/100). Read the Cfpb safety report
How do I install Cfpb?
It runs remotely at gateway.pipeworx.io. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does Cfpb need an API key?
Yes. The registry entry asks for PIPEWORX_API_KEY.
Is Cfpb maintained?
The last commit was 40 days ago (2026-09-24). The latest release is v0.2.1.
Is Cfpb up?
100% of our last 28 checks got an answer. We check remote servers about four times a day.
What can I use instead of Cfpb?
Servers from other publishers that do the same job: Appwrite MCP server, Homespun MCP server and CogniCore MCP server.
How does Cfpb compare with other Databases MCP servers?
safety score 87/100 (higher than 70% of 802 Databases servers); uptime 100% (of our recent checks; the typical remote Databases server answers 100%); response time 143 ms (faster than 73% of 292 Databases servers). Full comparison.

Alternatives to Cfpb

Same job from other publishers: the closest match first, then the best rated.

  • Appwrite
    Build and deploy backends: auth, Postgres/MySQL/vector databases, storage, functions, hosting, CDN
    A
  • Homespun
    Deploy a multi-user web app from your agent: hosting, auth, database, and permissions.
    B
  • CogniCore
    Memory, reflection and safety for AI agents. Hosted or local, no vector database.
    A
  • DBHub
    Token-efficient database MCP server for PostgreSQL, MySQL, MariaDB, SQL Server, Oracle, SQLite
    A
  • Neo4j Cypher
    A simple Neo4j MCP server that allows you to run Cypher queries against a Neo4j database.
    A

More from pipeworx-io →