ballranks-mcp.yml
Ball Ranks serves a read-only remote Model Context Protocol server (Streamable HTTP) on its own host. A GET answers 405 by design; an anonymous POST initialize and tools/list answer 200 with four tools, each annotated read-only, non-destructive and idempotent.
One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.
Endpoint
Hosted endpoint · transport streamable-http
Connect
This is a remote MCP server — point an MCP client at the endpoint URL. Clients with native remote support (Claude, Cursor, VS Code, …):
For stdio-only clients (older Claude Desktop, etc.), bridge with mcp-remote:
If the server requires authentication, add the provider's token/header (e.g. an X-API-Key) per its docs. A quick reachability check:
Tool quality observed · not scored
tools with readOnly / destructive hints
parameters described (26 total)
state-changing tools without destructiveHint
tool-list tokens (4 tools)
tools over ~1,200 tokens
From an anonymous initialize + tools/list capture measured 2026-10-20; tokens are chars/3.6 of each tool definition. Recorded for the Kin Score's agent readiness as an observed signal — it contributes no points yet.
Tools
get_week_rankings— Return published weekly fantasy football rankings for one position, week, and scoring format. Use this for start/sit comparisons or a ranked position list. This tool does not support basketball.get_season_rankings— Return a paginated Ball Ranks season ranking board for fantasy basketball or football. Basketball uses nine-category per-game rankings; football accepts standard, half-PPR, or PPR scoring.get_player_rankings— Look up one player's published Ball Ranks season ranking by player ID or slug. Use this when the user asks where a specific player ranks.get_player_projections— Look up one player's published season projection, or a weekly football projection, by player ID or slug. Weekly projections require scope=weekly and a week number.
About MCP
The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.
Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.
Work with this as data
Every MCP server here is available over the APIs.io API and to AI agents over MCP.