"A server for finding creative writing resources and content" matching MCP connectors:

The agent-native cloud: database, functions, AI, storage, auth and more. 50 tools, one API key.

Build personal interactive apps with real URLs and persistent storage, using any AI.

Live GPU compute & inference token price indices for AI agents — 591 reference indices across H100/A100/B200/B300 spot+on-demand, Claude/GPT/Llama token pricing, and more. Every value is methodology-versioned and citable via the /v1/verify handshake.

AI infrastructure design agent. Describe your app in plain English; Riley designs, prices, and deploys AWS or GCP infrastructure with generated Terraform.

MCP server aggregating developer infrastructure deals, free tiers, and startup programs

Compare LLM inference costs vs OpenAI/Anthropic/DeepSeek. Gonka is up to 6800x cheaper.

Video generation cost estimates across providers, with provenance, freshness, and confidence.

Custom domains API for SaaS: connect, verify, and manage customer domains, SSL, and DNS

Build, deploy, and operate hosted web apps on VibeKit (vibekit.bot) from any MCP client.

MCP server for DNSimple — domains, DNS zone records, availability, pricing and contacts.

Manage Scalingo PaaS apps, deployments, containers, logs and env vars from your AI assistant.

Inspect and control your Northflank projects, services, jobs, and builds from your AI assistant.

Manage Laravel Forge servers, sites, and deployments from your AI assistant.

Remote MCP server for RunComfy Serverless API (ComfyUI): deployments and async inference.

Massed Compute MCP — browse GPU inventory, launch and manage VMs, audit billing.

LLM and GPU rental prices: model price lookup, GPU listings, cheapest-GPU search, price history

Deploy a GitHub repo to a live HTTPS URL from your AI tool; read logs, set variables, resize apps.

Lowers your AWS bill by helping you clean up and optimize your setup

Publish the website you built with AI to a live public URL — straight from chat, no setup.

JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion.