# SoftPerceptron (remote · softperceptron.com)

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

- Trust score: 65/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-23

## Components

- remote · `softperceptron.com`: 65/100 (this document), [markdown](https://verifymcp.io/servers/com-softperceptron-mcp/softperceptron.md), [page](https://verifymcp.io/servers/com-softperceptron-mcp/softperceptron)

## Channel facts

- Endpoint: `https://softperceptron.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.1`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-23.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 6 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 74/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 552 tokens (~92/item across 6 items; 6 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 3/100
  - Stability observed for 1 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the SoftPerceptron MCP server?

SoftPerceptron is a hosted endpoint at https://softperceptron.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

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

### Cursor

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

### VS Code

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

### Codex

```toml
[mcp_servers.com-softperceptron-mcp]
url = "https://softperceptron.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-softperceptron-mcp": {
      "type": "remote",
      "url": "https://softperceptron.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-softperceptron-mcp --url 'https://softperceptron.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-softperceptron-mcp:
    url: "https://softperceptron.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-softperceptron-mcp": {
      "Transport": "http",
      "Url": "https://softperceptron.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-softperceptron-mcp -t streamable-http -u 'https://softperceptron.com/mcp'
```

### Other

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

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-23 (score 65, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-22 (score 64)

First indexed and scored.

## MCP tools (6)

### `search_ai_models` (~119 tokens)

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'.

Input parameters:

- `kind` (string): Restrict to one product kind.
- `limit` (integer): Max results (default 10).
- `query` (string): Free-text match against name, tagline, provider and tags. Omit to list everything.

### `get_ai_model` (~72 tokens)

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

Input parameters:

- `id` (string, required): Listing id or alias, e.g. 'anthropic-claude' or 'claude'.

### `compare_ai_models` (~69 tokens)

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).

Input parameters:

- `a` (string, required): First listing id or alias.
- `b` (string, required): Second listing id or alias.

### `can_i_run_model` (~174 tokens)

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'.

Input parameters:

- `context` (integer): Context length in tokens (default 8192).
- `gpu` (string, required): GPU id or name, e.g. 'rtx4090'. Call list_gpus to see options.
- `model` (string, required): Local model id or name, e.g. 'llama33-70b'. Call list_local_models to see options.
- `quant` (string): Quantization id (default 'q4'), e.g. q4, q5, q8, fp16.

### `list_local_models` (~35 tokens)

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

### `list_gpus` (~29 tokens)

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

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-softperceptron-mcp/softperceptron#diagnostics

## Score history

- 2026-10-23: 65
- 2026-10-22: 64

## Common questions

### What is the SoftPerceptron MCP server?

SoftPerceptron is an MCP server listed in the public MCP registry as com.softperceptron/mcp. AI model/agent directory with pricing and comparisons, plus GPU VRAM fit and tokens/sec estimates. This page covers its hosted endpoint (https://softperceptron.com/mcp).

### Is the SoftPerceptron MCP server safe to use?

SoftPerceptron scores 65 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the SoftPerceptron MCP server expose?

SoftPerceptron exposes 6 tools: search_ai_models, get_ai_model, compare_ai_models, can_i_run_model, list_local_models, list_gpus. Their descriptions and schemas cost roughly 498 tokens of context every time the server is loaded.

### Does the SoftPerceptron MCP server require authentication?

No. We connected to SoftPerceptron without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the SoftPerceptron MCP server still maintained?

SoftPerceptron is still listed as active in the MCP registry. We last reached this channel on 23 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://softperceptron.com/mcp
- Website: https://softperceptron.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-softperceptron-mcp/softperceptron.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-softperceptron-mcp/softperceptron.json
- HTML version of this page: https://verifymcp.io/servers/com-softperceptron-mcp/softperceptron