Createya MCP & APIofficial
A
licenseNot graded
qualityD
maintenanceEnables AI agents and developers to generate images, videos, audio, and text using 100+ models via MCP or REST with a single API key.
4
MIT
relaygpu-mcp
OfficialRelated Servers
Alternatives to relaygpu-mcp
No user-submitted related servers found.
Related Servers
- AlicenseBqualityAmaintenanceEnables AI agents to consume 50+ NVIDIA NIM models including LLMs, image generation, and vision through 10 MCP tools with rich metadata and advanced filtering.11329 npm1MIT
ModelsLab MCP Serverofficial
AlicenseNot gradedqualityCmaintenanceEnables users to generate images, video, speech, music and sound effects, and run LLM chat across 10,000+ AI models from any MCP client through a hosted remote server with OAuth or API-key authentication.MIT- AlicenseAqualityDmaintenanceHosted multi-model AI media + chat MCP server. Generates images, video, audio, face-swaps and talking-avatars, and chats across 300+ models (Claude, GPT, Gemini, DeepSeek…) - all from one balance and one API key.16MIT
- AlicenseAqualityDmaintenanceEnables AI agents to discover, compare, and select the best AI models across multiple providers based on pricing, performance, and capabilities, with real-time cost estimation and benchmarking.93,909 npm1MIT
- FlicenseNot gradedqualityCmaintenanceProvides a live, audited catalog of AI models from NVIDIA NIM, OpenRouter, Nous Portal, and other providers, enabling search, retrieval, and usage examples via MCP tools and resources.-
TDQS
A4.3/5.0
Scored across 14 tools
Disambiguation4/5
Tools are largely distinct and the descriptions explicitly cross-reference their partners (run_model → check_task, run_workflow → check_workflow_run), which resolves most ambiguity. The only soft overlaps are the account/money trio get_pricing, estimate_cost, get_usage and get_credits, which an agent could momentarily confuse, plus the parallel check_task/check_workflow_run pair that requires reading descriptions to separate.
Naming Consistency5/5
Every tool follows a strict snake_case verb_noun pattern (list_workflows, search_models, get_model, run_model, check_task, cancel_workflow_run, upload_file, estimate_cost). The run/check/cancel triplet for workflows and the run/check pair for tasks are named symmetrically, reinforcing the pattern.
Tool Count5/5
14 tools sit squarely in the well-scoped range for an inference/media platform. Each tool maps to a distinct stage: discovery, schema lookup, pricing, execution, polling, cancellation, upload, and account state, with no obviously redundant entries.
Completeness4/5
The surface covers the full lifecycle for models and workflows: discover → inspect schema → estimate cost → run → poll → cancel → store outputs, plus upload, usage, credits, and docs. The notable gap is asymmetry in cancellation: workflow runs can be cancelled but async model tasks (check_task) have no cancel or list/history operation, which could strand long-running or unwanted tasks.
Maintenance
ActivityMaintained
ResponsivenessSyncing