SoftPerceptron MCP

An MCP server that allows AI agents to query the SoftPerceptron directory of AI models, agents, and tokens directly. It provides tools to search for models, retrieve specific model details, compare models side-by-side, and estimate hardware requirements such as GPU VRAM fit and decode speed for running models locally.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Vendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-01Operated by SoftPerceptron

MCP endpoint (Streamable HTTP)

https://softperceptron.com/mcp

Vendor documentation

What you can do with it

Search for AI models and agents by name or category
Retrieve detailed specifications and pricing for specific AI models
Compare capabilities and costs between different AI models
Estimate GPU VRAM requirements and tokens/sec for local model inference

Source and maintenance

Vendor evidenceRegistry 1.0.1

mcp-registry: com.softperceptron/mcp@1.0.1 Project website

Protocol and capabilities

Server: softperceptron 1.0.1
MCP protocol: 2025-06-18
Tools: 6 advertised
Resources: Not advertised
Resource templates: Not advertised
Prompts: Not advertised

Server-advertised capabilities

{
  "tools": {
    "listChanged": false
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

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.

Tools

6 advertised

search_ai_models

Advertised by the server during the last successful anonymous check.

Search the SoftPerceptron directory of AI models, autonomous agents and token/credit products. Returns pricing, specs and provider for each match. Use this to answer questions like 'what AI models are available', 'cheapest model with a big context window', or 'which coding agents exist'.

search_ai_models input schema

{
  "type": "object",
  "properties": {
    "kind": {
      "enum": [
        "model",
        "agent",
        "token"
      ],
      "type": "string",
      "description": "Restrict to one product kind."
    },
    "limit": {
      "type": "integer",
      "maximum": 50,
      "minimum": 1,
      "description": "Max results (default 10)."
    },
    "query": {
      "type": "string",
      "description": "Free-text match against name, tagline, provider and tags. Omit to list everything."
    }
  }
}

get_ai_model

Advertised by the server during the last successful anonymous check.

Get full details for one directory entry by id or common alias (e.g. 'claude', 'gpt', 'gemini'). Returns pricing, specs, provider and links.

get_ai_model input schema

{
  "type": "object",
  "required": [
    "id"
  ],
  "properties": {
    "id": {
      "type": "string",
      "description": "Listing id or alias, e.g. 'anthropic-claude' or 'claude'."
    }
  }
}

compare_ai_models

Advertised by the server during the last successful anonymous check.

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 agent).

compare_ai_models input schema

{
  "type": "object",
  "required": [
    "a",
    "b"
  ],
  "properties": {
    "a": {
      "type": "string",
      "description": "First listing id or alias."
    },
    "b": {
      "type": "string",
      "description": "Second listing id or alias."
    }
  }
}

can_i_run_model

Advertised by the server during the last successful anonymous check.

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. Use for questions like 'can an RTX 4090 run Llama 70B'.

can_i_run_model input schema

{
  "type": "object",
  "required": [
    "model",
    "gpu"
  ],
  "properties": {
    "gpu": {
      "type": "string",
      "description": "GPU id or name, e.g. 'rtx4090'. Call list_gpus to see options."
    },
    "model": {
      "type": "string",
      "description": "Local model id or name, e.g. 'llama33-70b'. Call list_local_models to see options."
    },
    "quant": {
      "type": "string",
      "description": "Quantization id (default 'q4'), e.g. q4, q5, q8, fp16."
    },
    "context": {
      "type": "integer",
      "maximum": 200000,
      "minimum": 512,
      "description": "Context length in tokens (default 8192)."
    }
  }
}

list_local_models

Advertised by the server during the last successful anonymous check.

List the open-weight models supported by the VRAM/can-i-run calculator, with parameter counts and what each is good for.

list_local_models input schema

{
  "type": "object",
  "properties": {}
}

list_gpus

Advertised by the server during the last successful anonymous check.

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

list_gpus input schema

{
  "type": "object",
  "properties": {}
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks: 1 of 1 (100%)
Average latency: 1398 ms
95th percentile latency: 1398 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

Nov 1, 2026, 8:55 AM UTC · probe · passed · 1398 ms · metadata changed · 6 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.

Claude Code configuration

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

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).

Codex configuration

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

Cursor

Merge this server into .cursor/mcp.json in your project, then enable softperceptron-mcp in your MCP settings.

Cursor configuration

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

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).

Cline configuration

{
  "mcpServers": {
    "softperceptron-mcp": {
      "type": "streamableHttp",
      "url": "https://softperceptron.com/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start softperceptron-mcp and inspect its tools.

VS Code configuration

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

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.

Gemini CLI configuration

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

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.

Claude Desktop configuration

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

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

{
  "mcpServers": {
    "softperceptron-mcp": {
      "serverUrl": "https://softperceptron.com/mcp"
    }
  }
}

Let your agent find its tools

Find servers like SoftPerceptron MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows

Do you run SoftPerceptron MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing