com.softperceptron/mcp

up checked 2026-11-11T06:38:55.175Z

Unclaimed · Unverified

Publisher-provided title

SoftPerceptron

Publisher-provided description

AI model/agent directory with pricing and comparisons, plus GPU VRAM fit and tokens/sec estimates.

Summary by lookupd

Searches and compares AI models and agents with pricing and specs, and estimates whether open-weight models fit on specific GPUs.

Install

Claude Code, remote (streamable-http)

claude mcp add --transport http mcp https://softperceptron.com/mcp

Codex, remote (streamable-http)

codex mcp add mcp --url https://softperceptron.com/mcp

Cursor, remote (streamable-http) → .cursor/mcp.json

{
  "mcpServers": {
    "mcp": {
      "url": "https://softperceptron.com/mcp"
    }
  }
}

Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.

Publisher-provided text

search_ai_models Search the SoftPerceptron directory of AI models, autonomous agents and token/credit products. Returns pricing, specs and provider for each match. Use this to a
get_ai_model Get full details for one directory entry by id or common alias (e.g. 'claude', 'gpt', 'gemini'). Returns pricing, specs, provider and links.
compare_ai_models Compare two directory entries side by side — pricing, context window, modality and what each is best for. Both must be the same kind (model vs model, agent vs a
can_i_run_model Check whether a specific open-weight model fits on a specific GPU: VRAM required, whether it fits, how much headroom, which quantization to use, and an estimate
list_local_models List the open-weight models supported by the VRAM/can-i-run calculator, with parameter counts and what each is good for.
list_gpus List the GPUs supported by the VRAM calculator, with VRAM, memory bandwidth and power draw.

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/com.softperceptron/mcp.svg)](https://lookupd.com/servers/com.softperceptron/mcp)