creddy-mcp

Credit-risk analytics over MCP: natural-language SQL, default scoring, and live TCMB data.

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

  • List Tables: List the available tables in the creddy analytics database.
  • Describe Schema: Return every table's columns and types. Call this first to ground SQL generation in the real schema before writing a query for ``run_query``.
  • Run Query: Run a READ-ONLY SQL SELECT query and return the result as a table. Queries run against `credit_clients` (real UCI data, 30k clients). Only a single SELECT statement is allowed; writes, DDL

What data it sees

Do you need an account

No: the server works without sign-in

Credit-risk analytics over MCP: natural-language SQL, default scoring, and live TCMB data.

How to connect

How to connect creddy-mcp to Claude

The server address to paste into Claude settings:

https://creedy-mcp--onatozmen44.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect creddy-mcp to ChatGPT

The server address to paste into ChatGPT settings:

https://creedy-mcp--onatozmen44.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect creddy-mcp to Cursor

The server address to paste into Cursor settings:

https://creedy-mcp--onatozmen44.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (9)

Raw names from tools/list. Only developers need these.

list_tablesList the available tables in the creddy analytics database.
describe_schemaReturn every table's columns and types. Call this first to ground SQL generation in the real schema before writing a query for ``run_query``.
run_queryRun a READ-ONLY SQL SELECT query and return the result as a table. Queries run against `credit_clients` (real UCI data, 30k clients). Only a single SELECT statement is allowed; writes, DDL and multiple statements are rejected and results are capped. Monetary columns are in New Taiwan Dollars (NT$); `defaulted` is a boolean target label.
tcmb_indicatorsLIVE headline Turkish indicators from TCMB (USD, EUR, gold, policy rate, ...). Optionally filter by a substring of the indicator name, e.g. 'Dolar', 'Euro', 'Altın'. Returns the current value, date and EVDS series code. Works without an API key.
tcmb_seriesFetch a specific time series from TCMB's public REST web service. `series`: one or more EVDS codes separated by '-' or ',', e.g. 'TP.DK.USD.A.YTL'. `start_date`/`end_date`: 'dd-MM-yyyy' (default: last year). Requires CREDDY_TCMB_API_KEY. Note: TCMB is migrating EVDS2->EVDS3; if the public REST endpoint has moved, set CREDDY_TCMB_BASE_URL (or use tcmb_indicators).
tcmb_searchSearch TCMB's EVDS catalog for series by topic/name (key-authenticated). Returns matching EVDS series with their code, name and frequency. Example queries: 'döviz kuru', 'kredi kartı', 'enflasyon', 'altın', 'konut'. Use a returned code with `tcmb_series` once TCMB's public REST endpoint is available. Requires CREDDY_TCMB_API_KEY.
predict_defaultPredict a client's probability of default and explain the top drivers. Trained on the real credit_clients data. `credit_limit`, `bill_sep`, `pay_amt_sep` are in NT$. `pay_sep`/`pay_aug`/`pay_jul` are the repayment status for Sep/Aug/Jul (-1/0 = paid duly, >=1 = months of delay). `sex` (erkek/kadın), `education` (lise/üniversite/yüksek lisans/diğer), `marriage` (evli/bekar/diğer). Run `creddy train-model` first.
model_metricsReturn the trained risk model's evaluation metrics and key drivers.
example_questionsReturn example analytics questions this server can answer.