"MCP servers for game development" matching MCP servers:

Predicts video game scores (0-100 scale, similar to Metacritic ratings) using machine learning based on game characteristics like price, release month, tags, genres, and platforms, trained on Steam game data.

Real human judgment as agent tools -- an AI agent can ask a question and get back a structured, schema-validated JSON answer from a real quality-scored human. 16 response types (yes/no, ratings, rankings, A/B tests, sentiment, image/video/audio review, voice/video/photo capture). Fully programmatic signup with a $5 free trial credit, no card required.

Provides AI agents with direct access to KingsPlaybook's sports data including confirmed lineups, player projections, game lines, and pick history via native MCP tools.

Enables querying YouTube gaming opportunity rankings to answer 'what should I record?' by providing tools for top games, game breakdowns with AI video ideas, and live topic checks.

Free competitive pricing intelligence for SMB CPG brands. Check where any product price sits in its Amazon category, track pricing trends, and compare products — no NielsenIQ or SPINS subscription needed.

Institutional-grade quantitative stock analysis and research signals for AI agents via the Model Context Protocol (MCP).

An MCP server that extracts fields from documents and holds uncertain extractions for human review, ensuring high confidence data flows automatically while uncertain cases are resolved manually.

Enables AI agents to audit Steam store pages for algorithmic health, forecast sales cones with P10/P50/P90 scenarios, and retrieve genre benchmarks for indie game market analysis.

Cross-game market intelligence and currency conversion across six MMOs, enabling unified searches, portfolio tracking, and farming optimization via MCP.

A model context protocol server designed for AI development and QA, providing AntV document context and code examples.

Enables AI agents to invoke a local Stata installation, including a Windows Stata build under Wine on Linux and macOS, for regression analysis, econometrics, paper replication, and empirical research with command guards, resource monitoring, and automatic log capture.

Read-only Model Context Protocol tools for evidence-based development cooperation and ODA research.

Enables AI assistants to access and search 3GPP telecommunications specifications through direct integration with the TSpec-LLM dataset. Provides real-time specification content, implementation requirements, and multi-spec comparisons for 3GPP standards development.

A Python MCP server providing 11 tools for querying KenPom basketball analytics, including efficiency ratings, game predictions, four factors, and more through Claude.

Enables an LLM agent to reason about live British baseball league data through typed, read-only tools for scouting reports, matchups, lineup prediction, running-game tendencies, and playoff projection, with grounded caveats and sample sizes.

Enables querying live cross-platform gaming market data — Steam players, Twitch/YouTube viewership, prices, discounts, hype, and the aggro metric — through 8 read-only tools for summaries, rankings, genre rollups, game details, and search.

A tool that helps users conduct comprehensive research on complex topics by exploring questions in depth, finding relevant sources, and generating structured, well-cited research reports.

Provides query capabilities for global economic and social development data from the World Bank Open Data API.

Enables AI assistants to answer tennis tactical questions using shot-by-shot charted match data, producing game plans, serve and return tendencies, scouting reports, match forecasts, and explanations of why a match turned. Exposes read-only tools for player reports, head-to-head game plans, match breakdowns, and tactical leaderboards, each with confidence margins and links to full pages.

Enables LLM clients to access crop yield predictions from RGB imagery, topic-based PDF literature, and soil lab/moisture CSV data.

Remote MCP server for the Torn City API v2, enabling querying of player, faction, market, and other game data, plus aggregated intelligence reports, all via natural language.

Enables comprehensive academic research by searching and analyzing papers from PubMed, Google Scholar, ArXiv, and JSTOR. Provides full-text access, citation management, and research organization through five powerful consolidated tools.

MCP server for publishing markdown AI research entries to a Convex database. Supports both development and production environments with secure deployment credentials.

Enables AI agents to manage citations in Microsoft Word via EndNote, including DOI-verified paper search, RIS import/export, and genuine CWYW IEEE citations.

Enables AI assistants to research the Asphalt 8 game engine through class-catalog lookup, Ghidra-based decompilation, notes, card writing, and quality checks, saving work to local drafts for later export and review.

Provides AI assistants with access to authentic World of Tanks Blitz game data including tank statistics, armor values, map terrain features, equipment, crew skills, and camouflages parsed directly from local game files.

Grades prediction market trade logs to determine if a strategy has a statistically significant, fee-adjusted edge using out-of-sample holdout, returning a signed verdict.

Enables agents to compute deterministic phase-locking value, signal-to-noise ratio, and subcortical temporal envelope encoding fidelity through JSON-RPC tool calls.

A Windows-optimized server providing universal data analytics for JSON and CSV files through over 32 tools including schema discovery and interactive visualizations. It is specifically designed for seamless integration with Claude Desktop on Windows.

Enables AI assistants to run local, model-backed decisions on short passages and routing choices, and to check whether exactly supplied text supports a scientific claim, returning the full probability distribution, review-policy status, and provenance details. All evaluation stays on the local machine with no cloud inference, and flagged results are surfaced for human review rather than treated as conclusions.