easy-predict

easy-predict is an MCP server that gives your AI agent two tools: predicttimeseries — forecast the next value in any numeric series using automatic model…

CommunityOnlineNo sign-inGlobalFreeCan modify data

What it can do

  • Predict Timeseries: Predict the next value in a numeric time series. Uses automatic model selection (linear, log1p-linear, last-delta, mean) via holdout evaluation. Costs $0.01 USDC on Base via x402.
  • Detect Anomalies: Detect anomalies in a numeric series using z-score analysis. Returns flagged points with their z-scores. Costs $0.01 USDC on Base via x402.

What data it sees

Do you need an account

No: the server works without sign-in

easy-predict is an MCP server that gives your AI agent two tools:

predict_timeseries — forecast the next value in any numeric series using automatic model selection (linear, log1p, last-delta, mean) detect_anomalies — find outliers in a numeric series using z-score analysis Each tool call costs $0.01 USDC on Base, paid automatically from your local wallet via x402 micropayments. There are no API keys, no subscriptions, and no accounts — just send data, pay per use.

Your private key never leaves your machine. The MCP server runs locally via uvx, signs the payment on-device, and only sends the signed header to the API.

Setup:

{ "mcpServers": { "easy-predict": { "command": "uvx", "args": ["easy-predict-mcp"], "env": { "WALLET_PRIVATE_KEY": "0xYOUR_KEY" } } } } You need a Base wallet with a small amount of USDC (each call costs $0.01).

How to connect

How to connect easy-predict to Claude

The server address to paste into Claude settings:

https://easy-predict--rizzi-williams.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 easy-predict to ChatGPT

The server address to paste into ChatGPT settings:

https://easy-predict--rizzi-williams.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 easy-predict to Cursor

The server address to paste into Cursor settings:

https://easy-predict--rizzi-williams.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 (2)

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

predict_timeseriesPredict the next value in a numeric time series. Uses automatic model selection (linear, log1p-linear, last-delta, mean) via holdout evaluation. Costs $0.01 USDC on Base via x402.
detect_anomaliesDetect anomalies in a numeric series using z-score analysis. Returns flagged points with their z-scores. Costs $0.01 USDC on Base via x402.