ParlayAPI MCP Server
Official first-party MCP server (parlayapi-mcp) exposing sports odds, props, prediction-market data, live previews, source-quality proof, and agent signup as 22 tools. Local stdio transport only — no hosted/remote endpoint is published. Distributed on PyPI, as a Claude Desktop .mcpb bundle, and registered in the official MCP registry as io.github.JacobiusMakes/parlayapi. Nine tools work keyless (signup, checkout-link, magic-link, pricing, live previews, source quality, coverage); the rest need a PARLAYAPI_KEY API key.
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.
Descriptor
Candidate descriptor · transport stdio
Tools
parlayapi_signup— Create a free-tier account, return API key + claim URL + upgrade URLparlayapi_checkout_link— Stripe upgrade URL for any tierparlayapi_magic_link— Email a passwordless login linkparlayapi_get_pricing— Current public pricing and credit tiersparlayapi_live_sports— Active live sports, event counts, and book countsparlayapi_live_search— Search live teams, players, and sport keysparlayapi_live_command_center— Public best-line preview from /liveparlayapi_source_quality— Public source freshness and quality metadataparlayapi_book_coverage— Public per-book five-gate coverage proofparlayapi_list_sports— All available sport keysparlayapi_get_odds— Game-level odds (h2h, spreads, totals) for a sportparlayapi_get_props— Player prop odds for a sportparlayapi_best_line— Best price per outcome across bookmakersparlayapi_verdict— One-call "should I bet this?" fair price vs market, best bettable book, plain-English BET/PASS callparlayapi_set_bettable_books— Remember the user's region/books so verdicts skip books they can't useparlayapi_parlay_verdict— Grade a multi-leg parlay — combined fair price, best book, EV, weakest leg, correlation warnings, payoutparlayapi_best_bets— Ranked +EV plays for a sport, scoped to bettable books, plus edge alertsparlayapi_account_info— Tier, credits remaining, billing periodparlayapi_find_arbitrage— Cross-book arbitrage candidates, 3-way markets includedparlayapi_find_ev— Positive-EV bets vs a sharp book's no-vig fair lineparlayapi_consensus— Consensus (average) odds across all bookmakers per marketparlayapi_find_middles— Cross-book middle opportunities
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.