Skip to content

SoftPerceptron MCP server

com.softperceptron/mcpsoftperceptron.comstreamable-httpv1.0.2Scanned

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

6 tools: 1 change things and 5 only read.

Tools: 0 delete, 0 irreversible, 1 write, 5 read.
  • Reads private data · 3
  • Reads text others write · 0
  • Can send data out · 0
  • 1 finding

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here changes things. Govern it.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the SoftPerceptron MCP server can do

The SoftPerceptron MCP server is published by softperceptron.com, a domain the MCP Registry verified. It has 6 tools. It can create or change data (1 tool: can_i_run_model), but cannot delete data. 5 tools only read.

3 tools read private data (search_ai_models, get_ai_model and compare_ai_models).

The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.

Last scanned Nov 12, 2026, version 1.0.2.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

6 tools

Changes things 1Claude Code: ask
  • can_i_run_modelCheck 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 to…1 finding

    Why it is in this group

    • The name "can_i_run_model" says "run": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "can_i_run_model" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "can_i_run_model" says "run": a word for a change.

      What this check looks for
    Description, as the server wrote it
    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'.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
Only reads 5Show 5 read-only tools
  • compare_ai_modelsCompare two directory entries side by side — pricing, context window, modality and what each is best for.Reads private dataNo findings

    Why it is in this group

    • The name "compare_ai_models" says "compare": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "compare" and "directory": it reads files.
    Description, as the server wrote it
    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).

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_ai_modelGet full details for one directory entry by id or common alias (e.g.Reads private dataNo findings

    Why it is in this group

    • The name "get_ai_model" says "get": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "get" and "directory": it reads files.
    Description, as the server wrote it
    Get full details for one directory entry by id or common alias (e.g. 'claude', 'gpt', 'gemini'). Returns pricing, specs, provider and links.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_gpusList the GPUs supported by the VRAM calculator, with VRAM, memory bandwidth and power draw.No findings

    Why it is in this group

    • The name "list_gpus" says "list": a word for reading.
    Description, as the server wrote it
    List the GPUs supported by the VRAM calculator, with VRAM, memory bandwidth and power draw.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_local_modelsList the open-weight models supported by the VRAM/can-i-run calculator, with parameter counts and what each is good for.No findings

    Why it is in this group

    • The name "list_local_models" says "list": a word for reading.
    Description, as the server wrote it
    List the open-weight models supported by the VRAM/can-i-run calculator, with parameter counts and what each is good for.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • search_ai_modelsSearch the SoftPerceptron directory of AI models, autonomous agents and token/credit products.Reads private dataNo findings

    Why it is in this group

    • The name "search_ai_models" says "search": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "search" and "directory": it reads files.
    Description, as the server wrote it
    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'.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged untrusted-input or outbound.

Reads private data3
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:47 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
1
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://softperceptron.com/mcp: tools/list returned 6 tools to an anonymous client, including can_i_run_model (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

1 warn
  • The server marks "can_i_run_model" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "can_i_run_model" says "run": a word for a change.

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools6 changed.~6 changedView diff

Install

Pinned to version 1.0.2. Values in angle brackets are yours to fill in.

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

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__softperceptron__search_ai_models",
      "mcp__softperceptron__get_ai_model",
      "mcp__softperceptron__compare_ai_models",
      "mcp__softperceptron__list_local_models",
      "mcp__softperceptron__list_gpus"
    ],
    "ask": [
      "mcp__softperceptron__can_i_run_model"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as softperceptron. Review it before you use it.

Capability tags behind 3 rules
  • mcp__softperceptron__search_ai_models private-data
  • mcp__softperceptron__get_ai_model private-data
  • mcp__softperceptron__compare_ai_models private-data

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/com.softperceptron/mcp/verify?hash=854fb640d61709c91104a3a259a56b1d82e4e8bc97317d94c41d583089adb772" | jq -e '.changed == false'

Pinned hash 854fb640d617, from Nov 12, 2026, 01:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/com.softperceptron/mcp/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for com.softperceptron/mcp
[![Anlyon Radar](https://radar.anlyon.com/badge/com.softperceptron/mcp.svg)](https://radar.anlyon.com/servers/com.softperceptron/mcp)

Source: MCP Registry. Synced Nov 12, 2026, 01:17 UTC.

SoftPerceptron MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the SoftPerceptron MCP server safe?

No scan can promise that. What its definitions show: 6 tools, 1 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the SoftPerceptron MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the SoftPerceptron MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the SoftPerceptron MCP server have?

6 tools: 1 write, 5 read. can_i_run_model, search_ai_models, get_ai_model, compare_ai_models, list_local_models and list_gpus.

Does the SoftPerceptron MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the SoftPerceptron MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the SoftPerceptron MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 12, 2026. Every change is on this page and in its Atom feed.