"Steam Deck" matching MCP servers:

Enables creating and managing AI-powered slide decks on deck.4hum.ai with tools to save, update, generate images, and list decks.

An MCP server for the FlashLearnAI public API that enables AI-powered flashcard deck generation, browsing sets, SM-2 spaced-repetition study sessions, and API usage tracking through natural language.

Enables orchestrating a reusable team of expert agents (PM, architecture, development, QA, security) to analyze a project's files and produce consolidated recommendations. It exposes tools to list experts, ask a single expert, or run the full team from MCP clients.

Enables LLMs to access Blackbird AI's services through the Model Context Protocol, using Blackbird API credentials for authentication.

Scores submitted prose against the FAA plain-language standard and returns it rewritten to the pass bar, exposing score_prose and improve_prose tools that report findings, a numeric score, and the best-scoring rewrite.

Syncs Epic/GOG/Steam game libraries with Chinese metadata, enabling AI agents to recommend games through natural language conversation.

Enables Alexa+ agents and other MCP hosts to analyze dry exam/card pulse text from a mock trading desk, returning structured test results, signals, problems, needs, alarms, and recommendations over Streamable HTTP. It works with an offline rules engine and optional Nebius Token Factory enrichment.

Enables users to run synthetic support-agent evaluations, preserve and inspect traces, score results deterministically, inject failures, and enforce release review gates through MCP tools, resources, and prompts.

Enables users to compare model-and-service-line offers against explicit task token ceilings and budgets, create expiring quotes, and record duplicate-safe simulated approvals through real MCP tools without executing models or making payments.

Enables agents and Blender users to generate game-ready art through a set of Blender tools covering concept image generation, image-to-3D mesh creation, mesh cleanup, PBR material assignment, greybox level layout, camera pathing and still or sequence rendering. Every action runs headless Blender, returns machine-readable JSON with pass/fail self-checks such as triangle budget, scale, pivot and clearance, so agents can verify and fix each step unattended.

Enables founder ops assistants to retrieve LinkedIn-style news digests, GitHub repository hygiene, and daily operations briefs generated via Amazon Bedrock, through natural language over Streamable HTTP.

Enables AI assistants to query Hong Kong horse racing data such as race cards, AI win probabilities, odds, results, form, jockey/trainer statistics, and draw statistics in English or Traditional Chinese.

Enables creation of professional PowerPoint presentations with AI-generated content and images, supporting multiple LLMs and image services via MCP protocol.

Enables MCP-compatible agents to generate, edit, export, and preview AI slide decks through tool calls. Supports deck generation from topics or reference material, per-slide and deck-wide edits, and HTML export.

Enables an AI assistant to build an editable slide deck from a brief and local source documents over MCP — creating decks, adding sources, generating outlines and slides, reviewing and approving slides, checking figures against sources, and exporting to PPTX, PDF, HTML or Markdown. Everything stays local, with the same tools backing the bundled UI.

Enables IBM Bob to directly invoke semiconductor fab analytics tools via MCP, including lot analysis, root-cause findings, batch risk prediction, and copilot queries grounded in statistical process control and domain evidence.

Provides policy-grounded triage of Trust & Safety reports via MCP, with tools for triage, policy search, and operational telemetry.

MCP server for AI-native editable presentations: surgically edit slide components by stable ID, with local rendering and self-checking overflow.

A hosted remote MCP server for OpenAI Codex memory MCP, providing structured JSON tools to store, recall, and manage memory with token-based access and audit receipts.

Enables deployment of MCP servers over HTTP, providing ready-to-use tools for text processing, math calculations, and social media content generation, accessible to AI assistants like GitHub Copilot and Claude.

MCP server for bottle-cap CAD workflow, providing tools for generating precise caps, filling holes, repairing meshes, and generating visual meshes via CadQuery, PyMeshLab, and the Meshy API.

Enables MCP clients to consult Google Gemini through a single tool that returns text answers, with automatic retries, exponential backoff, and fallback across models for rate limits or outages.

An MCP server that bridges multiple LLMs (OpenAI-compatible APIs and CLI coding agents) for collaborative debugging and diverse AI perspectives.

Enables MCP clients such as Claude Code, Cursor, and Claude Desktop to generate UGC video ads, avatar ads, image ads, and brand-grounded videos across multiple models, plus manage jobs, brands, reusable skill templates, and scheduled agent workflows through a secure API-key-authenticated wrapper.

AI-powered IT support server that understands issues in Turkish and English, suggests fixes, and routes to the right experts via Django DB.

An MCP server that lets agents act as the person who added them, giving them identity, shared context (data, documents, goals, calendar, skills), and a place to publish apps and pages behind sign-in. It also brokers access to models, data APIs and other tools' MCP servers through one key, with consent prompts, per-person access checks and encrypted credentials as guardrails.

MCP server for fal model discovery, execution, pricing, and local media processing, enabling AI model workflows via natural language.

MCP serverr for Lastest to manage your tests, AI create them, run them, and speed up AI-development.

Unifies MiniMax's multimodal generation, web search, image understanding, audio, video, and music tools into a single MCP server for use with Claude and other clients.