AI & Machine Learning

softperceptron.com

An MCP server that lets you search, compare, and inspect AI models, agents, and token/credit products, and check whether open-weight models fit on specific GPUs.

1 endpoint6 known toolsFirst detected September 21, 2026Last detected September 21, 2026

ENDPOINT 1

https://softperceptron.com/mcp

No auth detected

MCP server metadata

Name: softperceptron
Version: 1.0.0

Capabilities

tools

Server instructions

SoftPerceptron's directory of AI models, agents and token products, plus a GPU VRAM and decode-speed calculator. Use search_ai_models / get_ai_model / compare_ai_models for the directory, and can_i_run_model for GPU fit checks.

Known tools 6

search_ai_models

Search the SoftPerceptron directory of AI models, autonomous agents and token/credit products.

Inferred read-only

get_ai_model

Get full details for one directory entry by id or common alias (e.g.

Inferred read-only

compare_ai_models

Compare two directory entries side by side — pricing, context window, modality and what each is best for.

Inferred read-only

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 estimated decode speed in tokens/sec.

Inferred read-only

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.

Inferred read-only

list_gpus

List the GPUs supported by the VRAM calculator, with VRAM, memory bandwidth and power draw.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.softperceptron]
url = "https://softperceptron.com/mcp"
enabled = true

Claude Code

.mcp.json

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

Claude Desktop

Settings → Connectors → Add custom connector

Name: softperceptron
Remote MCP URL: https://softperceptron.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

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

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "softperceptron": {
      "type": "http",
      "url": "https://softperceptron.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "softperceptron",
  "transport": "streamable-http",
  "url": "https://softperceptron.com/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.