"Developing agents with expertise in the latest documentation" matching MCP servers:

Enables AI agents to inspect UI screen recordings as token-efficient image sheets with changed regions boxed, single-frame flicker flagged, and speech aligned to frames. Exposes watch_video and zoom_video tools so agents can pull dense keyframes across any time range or one sharp full-resolution frame, all processed locally.

Enables Codex to delegate code reviews, coding tasks, image/video generation, and background investigations to Grok via MCP tools.

Enables an AI assistant to convert images among HEIC, JPEG, PNG, WebP, and AVIF entirely on the local machine, including converting a folder of files into a single zip. Access is confined to a user-specified root directory, metadata is stripped by default, existing files are never overwritten, and no network requests or telemetry are used.

Enables AI agents to create and edit pixel art in a live Aseprite window, with tools for drawing, selection, transformation, and animation.

TCG oracle as an MCP server: 22 focused tools. Search 455K+ trading cards, live market snapshots, AI grading and grade-or-not decisions, conformal-calibrated price forecasts with a public accuracy scorecard, card-collateral loan terms, fantasy and sports souls leagues. Every root proven on-chain. Same tools as the hosted endpoint at mcp.the-undesirables.com, over stdio; no keys.

Enables account-less access to all 45 Google Gemini models and autonomous agents for text generation, multi-step reasoning, deep research, image/video/audio generation, grounded search, and embeddings via L402, x402, and MPP.

MCP server that exposes Google's Veo2 video generation capabilities, allowing clients to generate videos from text prompts or images.

Connects an MCP assistant to the PicPrep desktop app, letting it open and inspect photo projects, view slides and tabs, ask the user questions, and propose changes that the user alone keeps or rejects. It runs locally over 127.0.0.1 and starts the app on demand, so nothing leaves the computer.

Serves read-only tools that let an agent inspect PDFs step by step: outline a document, search for text or figure values, read pages and tables in order, describe figures and chart data, and render page or block images, with every block cited to its page and bounding box. It also lists the PDFs available under a configured root folder, which it never reads outside of.

Lets AI assistants render HTML animations to MP4 or GIF in 16:9, 9:16 and 1:1, preview single frames to check their own work, and finish videos with royalty-free music, AI voiceover, burned-in captions, titles and logos. It renders code frame by frame in a real browser rather than generating video from a text prompt.

MCP server that gives AI coding agents a paintbrush for image generation via ChatGPT in the browser, requiring no OpenAI API key.

An MCP server that scores, enhances, and analyzes prompts for AI video and image generation models to prevent token waste on poor prompts.

MCP server that lets AI assistants control Adobe After Effects via natural language, enabling composition and layer creation, animation, effects, presets, rendering, and arbitrary ExtendScript execution with Arabic/RTL support.

MCP server for the Crowe Logic platform, enabling mycology expertise chat, cultivation photo analysis, grow log management, and SOP generation.

Enables Claude to analyze reference videos (download, transcripts, frames) and generate new branded Instagram Reels/YouTube Shorts as React/TSX compositions, rendered to MP4 via Remotion.

Define one master style once (lighting, mood, composition, colour) and generate unlimited matching images with different subjects. Hosted remote MCP at https://imag8.art/api/v1/mcp with tools imag8_generate_image, imag8_suggest_variations, imag8_get_account_status. Works with Claude, Cursor, ChatGPT and custom agents. Free tier: 10 credits/month.

fixRAgent triages one photo of a building problem: what it is, how urgent (EMERGENCY, TODAY, THIS WEEK or WHENEVER), which trade to call, and what to tell the resident. Remote server at https://fixragent.com/mcp with three tools: try_sample, assess_property_photo, get_triage_profile. No key needed to start.

Deterministic file operations for AI agents: 40 operations over plain HTTPS. PDF merge, split, redact, sanitize, OCR, Office and PDF to Markdown, RAG chunking, charts, QR codes, C2PA AI labelling. find_tool suggests the right one. $0.01 per operation, 100 free, no signup, credits never expire.

Converts video into timestamped contact sheets, enabling AI agents to navigate and retrieve visual evidence from specific timecodes rather than watching entire clips.

Enables AI agents to lip-sync video to a different audio track via LipDub 2, including creating renders, checking statuses, and retrieving results.