A free, hosted MCP server for local-LLM hardware decisions. Ask whether a model fits your GPU, Mac, or mini-PC, which GGUF quant to download, the cheapest machine that runs it, and the buy-vs-rent-vs-API cost, from a maintained catalog of models and machines plus a monthly used-GPU price feed. No install, no API key. Tools: can_i_run_it, recommend_quant, cheapest_hardware_for_model, recommend_hardware, compare_hardware, cost_compare, get_used_gpu_prices, list_models, list_hardware. Works with Claude, Cursor, Cline, and any MCP client.
hiroshic9-png/edition-api
holco-apps/pennypilot
iamjamb/shipscreens
imviky-zzzr/tickerr-live-status
in.creo-memories/mcp-server
ing.conjure/conjure
CodeRabbit
CodeScene MCP Server
belt - the only tool your agent needs
MCP-ready Email Sending
Capacitor - Shared memory for your team’s coding agents.
Give your AI the whole web as clean markdown
inference shell
Make your agent a DeFi expert
