Koskamo

skforecast-ai MCP

An MCP server that enables coding agents to perform deterministic time series forecasting on CSV files. It profiles data, selects models using fixed rules, generates reproducible Python scripts, and provides metrics and prediction intervals without relying on the LLM for decision-making.

Visit skforecast

Package and access

Local package with source-attributed installation metadata. Koskamo does not execute packages during review.

skforecast-ai MCP logo, by skforecastCommunity listingLocal stdioSource reviewed; not executedPublished by skforecast
Vendor documentation

Checks and signals

Each line is separate evidence, not a trust score.

  • Popularity 52 GitHub stars

What you can do with it

  • Forecast the next 12 months of data from a CSV file
  • Compare candidate models and show a performance leaderboard
  • Retrieve the exact Python script that produced a forecast

Source and maintenance

Community listingRegistry 0.4.2Apache-2.0
mcp-registry: io.github.skforecast/skforecast-ai@0.4.2Source repositoryProject website
Last repository push
Latest release
v0.4.2
Maintenance checked

Packages and installation

Source-provided package data. Koskamo has not executed or live-probed this package.

skforecast-ai-mcp 0.4.2

pypiuvx
skforecast-ai-mcp package definition
{
  "version": "0.4.2",
  "transport": "stdio",
  "identifier": "skforecast-ai-mcp",
  "runtimeHint": "uvx",
  "registryType": "pypi",
  "packageArguments": [
    {
      "name": "--allow-dir",
      "type": "named",
      "format": "filepath",
      "isRequired": true,
      "description": "Absolute path of the directory the server may read CSV files from. Give the narrowest one that holds your data."
    }
  ]
}

Tools

Reported by the attributed source; not independently observed by Koskamo.

No tool definitions available.

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · repository · passed · metadata changed · updated
  • · backfill · recorded · Pre-expansion baseline; unobserved rich metadata remains unknown

Connect from your client

Each snippet configures the same source-provided package; replace placeholders before use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Cursor

Merge this local stdio configuration, replace every placeholder environment value, and restart Cursor. Koskamo has not executed this package.
Cursor configuration
{
  "mcpServers": {
    "skforecast-ai-mcp": {
      "command": "uvx",
      "args": [
        "skforecast-ai-mcp==0.4.2"
      ]
    }
  }
}

Cline

Merge this local stdio configuration, replace every placeholder environment value, and restart Cline. Koskamo has not executed this package.
Cline configuration
{
  "mcpServers": {
    "skforecast-ai-mcp": {
      "command": "uvx",
      "args": [
        "skforecast-ai-mcp==0.4.2"
      ]
    }
  }
}

VS Code

Merge this local stdio configuration, replace every placeholder environment value, and restart VS Code. Koskamo has not executed this package.
VS Code configuration
{
  "servers": {
    "skforecast-ai-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "skforecast-ai-mcp==0.4.2"
      ]
    }
  }
}

Claude Desktop

Merge this local stdio configuration, replace every placeholder environment value, and restart Claude Desktop. Koskamo has not executed this package.
Claude Desktop configuration
{
  "mcpServers": {
    "skforecast-ai-mcp": {
      "command": "uvx",
      "args": [
        "skforecast-ai-mcp==0.4.2"
      ]
    }
  }
}

Let your agent find its tools

Find servers like skforecast-ai MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 4,833