mcpField
C
CharterBench

CharterBench

Local
charterbench.comFinance

About CharterBench

Every U.S. bank and credit union: ratios, peers, growth and change signals from FDIC/NCUA filings

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"auburnduke-charterbench": {
"command": "npx",
"args": [
"-y",
"charterbench-mcp"
],
"env": {
"CHARTERBENCH_API_KEY": "<CHARTERBENCH_API_KEY>"
}
}
}
}
Run commandnpx -y charterbench-mcp
Environment variables to set
CHARTERBENCH_API_KEYSecretCharterBench Pro API key (create one at https://www.charterbench.com/account)

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmcharterbench-mcp0.5.0

Tools

12

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
qstringNoName contains
direnumNoasc | desc
bandstringNoAsset band(s): '<100M', '100M-500M', '500M-1B', '1B-10B', '10B+' (comma-separated)
sortstringNoSort column: total_assets, assets_yoy_pct, deposits_yoy_pct, loans_yoy_pct, members_yoy_pct, roa, roe, loan_to_deposit_pct, capital_ratio_pct, efficiency_ratio, net_interest_margin, cost_of_funds, net_charge_off_rate, cre_concentration, uninsured_deposit_share, brokered_deposit_share, borrowings_to_assets, securities_loss_to_capital
typeenumNoCharter typebank | credit_union
limitintegerNoRows to return (default 25)
statestringNoComma-separated USPS state codes, e.g. 'GA,FL'
filtersobjectNoRange filters as {'<column>_min': n, '<column>_max': n}, e.g. {'deposits_yoy_pct_max': -5, 'efficiency_ratio_min': 75}
holdingstringNoHolding-company name contains (banks only), e.g. 'Truist Financial' — lists the parent's subsidiary banks

Details

The maintainer has not added details yet. Check the README in the repository.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.