"Actual Budget" matching MCP servers:

Enables AI assistants to drive a Google Flow web workspace through local login-session reuse: inspecting the account's actual models and parameters, submitting image and video generation jobs, tracking each job by persistent ID, and downloading the matching media to a specified local path with file and parameter records. Supports repeatable, multi-shot video production workflows where tracked assets are handed off to editing tools like FFmpeg.

Connects a text-only coding agent to an OpenAI-compatible vision model so it can analyze images, screenshots, and UI mockups. Provides tools for general image understanding, OCR and code transcription, error-screenshot diagnosis, technical diagram and chart interpretation, UI-to-code/spec generation, and expected-versus-actual UI comparison.

Local MCP server that plans, generates, and assembles production assets (images, audio, video) through multi-agent personas and official APIs, with free-tier budget guard.

Enables AI agents and Claude Code to generate Midjourney images, wait for jobs to finish, download the actual image files, and create reusable moodboards through a signed-in Chrome session without API keys.

Enables Claude to generate ByteDance Seedance videos and Seedream images through a BytePlus key, pricing every request in dollars before it is sent. It adds budget limits, ask-first approvals and whole-key spend tracking so costly generations cannot happen without consent.

Enables any MCP client to turn layered PSD artwork into game-ready Spine packages by inspecting and classifying layers, rigging with meshes, bones, weights, IK, physics and animation, applying procedural or After Effects-driven FX, and running runtime and mobile-budget validation with preview output. It finishes by exporting the final .spine, JSON and atlas assets so a model can drive a full art pipeline without hand-authoring rig data.

Enables users to generate and edit images and videos through their own KIE account, with live model/parameter/price comparison, immutable request approval, and safe local saving of results. Budget reservations, spending limits, and guarded upload/download roots keep paid submissions controlled and never automatically retried.

An agentic AI video editor for Claude. It enables editing real video through MCP: cutting, captioning, reframing, scoring, and exporting finished MP4s from actual footage.

Opens, inspects, and renders DXF/CAD drawings for AI agents: describe_dxf returns structured facts (layers with actual drawn colors, units, bounds, text content) and render_dxf returns PNG images. On MCP Apps hosts like ChatGPT and Claude, view_dxf opens an interactive in-chat viewer with pan, zoom, and layer toggles.

An MCP server for image generation across Google, OpenAI, and Reve providers with budget control, cost reporting, and URL-based output instead of base64.

Enables AI clients to look up real Danbooru tags — exact names, aliases, categories, post counts, co-occurrence, wiki text, and the tag lists of actual posts — before composing image prompts. This tag verification noticeably improves prompt accuracy for local AI image generation.

Enables coding agents to watch and analyze videos by extracting scene-aware frames, transcribing speech, and generating shot timelines, all constrained by a token budget to fit LLM context limits.

Enables AI clients to turn text prompts and 2D photos into watertight 3D-printable figurines, keyed multi-part assemblies, and game-ready PBR assets entirely on local consumer hardware within a 16 GB RAM/VRAM budget. It exposes 16 native tools covering image-to-3D generation, pose canonicalization, auto-split assembly, retopology, texture baking, and hardware tier detection over stdio.

Enables AI agents to drive a desktop video editor through MCP, providing the same editing operations as the user — placing, trimming, rippling, grading, captioning, and exporting — on the actual project with local rendering.

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 AI models to decode QR codes from images by providing tools that scan and enhance QR codes, returning content and image quality diagnostics. It bridges the gap between visual recognition and actual decoding, allowing models to read QR codes directly from screenshots or photos.

Enables AI agents to browse video production packages, obtain free quotes, start and track productions with budget safeguards, and download finished videos, thumbnails and subtitles from vidia.kr. It also supports account balance checks and asset library lookups through MCP clients such as Claude, Cursor and Codex.

Read any PDF or image into agent context as markdown (tables preserved) or plain text. Every call returns its exact cost_usd, a free estimate_cost tool quotes documents before you commit, and max_pages / max_cost_usd caps refuse before any spend — OCR agents can budget. $0.75 per 1,000 pages, first 100/month free.

An MCP server for Claude Code that provides web search via Perplexity Sonar and image generation through OpenRouter, with cost-aware tool design and budget controls.