Skip to content

AgentKernel AI model data MCP server

si.agentkernel/modelsagentkernel.sistreamable-httpv1.0.0Scanned

Live prices, rankings, licences and privacy of AI models: best model per task, costs, alternatives.

6 tools: 3 change things and 3 only read.

Tools: 0 delete, 0 irreversible, 3 write, 3 read.
  • Reads private data · 0
  • Reads text others write · 0
  • Can send data out · 0
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

3 tools here change things. Govern them.

  • 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 AgentKernel AI model data MCP server can do

The AgentKernel AI model data MCP server is published by agentkernel.si, a domain the MCP Registry verified. It has 6 tools. It can create or change data (3 tools: best_for_task, estimate_cost and cheaper_alternative), but cannot delete data. 3 tools only read.

None of its tools reads private data, brings in text other people write, or sends data out.

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 19, 2026, version 1.0.0.

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 3Claude Code: ask
  • best_for_taskRanks AI models for one task by performance only (price shown, never used for the rank).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Ranks AI models for one task by performance only (price shown, never used for the rank). Tasks cover text, coding, agents, websites/UI/games/data viz, image generation and editing, video from text or image, video editing, text to speech, transcription, music and embeddings.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
    • idempotentHint: true
  • cheaper_alternativeFor a model you use today, finds a cheaper model at most five performance-index points lower for the same usage.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    For a model you use today, finds a cheaper model at most five performance-index points lower for the same usage.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
    • idempotentHint: true
  • estimate_costMonthly API cost at base rates for up to five models and a token volume, with the volume translated into words and pages.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Monthly API cost at base rates for up to five models and a token volume, with the volume translated into words and pages.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
    • idempotentHint: true
Only reads 3Show 3 read-only tools
  • find_modelsSearches and filters the catalog of language models by name, provider, licence and privacy, sorted by performance, coding, agentic index, price or context.No findings

    Why it is in this group

    • The name "find_models" says "find": a word for reading.
    Description, as the server wrote it
    Searches and filters the catalog of language models by name, provider, licence and privacy, sorted by performance, coding, agentic index, price or context.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
    • idempotentHint: true
  • get_modelPrice, context window, performance/coding/agentic index with rank, licence, privacy, cost for a usage volume and cheaper or open alternatives for one language model.No findings

    Why it is in this group

    • The name "get_model" says "get": a word for reading.
    Description, as the server wrote it
    Price, context window, performance/coding/agentic index with rank, licence, privacy, cost for a usage volume and cheaper or open alternatives for one language model.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
    • idempotentHint: true
  • recommend_modelsReturns the best-fitting language models for a use case and monthly API budget using the published AgentKernel Fit Score (performance, cost, context, features), with optional priva…No findings

    Why it is in this group

    • The description's first verb is "return": a word for reading.
    Description, as the server wrote it
    Returns the best-fitting language models for a use case and monthly API budget using the published AgentKernel Fit Score (performance, cost, context, features), with optional privacy and licence requirements.

    Annotations the server declares

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

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 private-data or untrusted-input or outbound.

Reads private data0
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, 19:18 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
3
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 3 tools that change things (3 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://www.agentkernel.si/mcp: tools/list returned 6 tools to an anonymous client, including best_for_task (write), estimate_cost (write), cheaper_alternative (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

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

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http models https://www.agentkernel.si/mcp
claude mcp add --transport http models https://www.agentkernel.si/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__models__recommend_models",
      "mcp__models__get_model",
      "mcp__models__find_models"
    ],
    "ask": [
      "mcp__models__best_for_task",
      "mcp__models__estimate_cost",
      "mcp__models__cheaper_alternative"
    ],
    "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 models. Review it before you use it.

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/si.agentkernel/models/verify?hash=be49de063e32f2a2890efdb8d41ded718c02a9c7a0b5c08c61e541e3f545d54b" | jq -e '.changed == false'

Pinned hash be49de063e32, from Nov 19, 2026, 04:18 UTC.

Watch

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

https://radar.anlyon.com/servers/si.agentkernel/models/changes.xml

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

Badge

Anlyon Radar badge for si.agentkernel/models
[![Anlyon Radar](https://radar.anlyon.com/badge/si.agentkernel/models.svg)](https://radar.anlyon.com/servers/si.agentkernel/models)

Source: MCP Registry. Synced Oct 21, 2026, 18:54 UTC.

AgentKernel AI model data MCP server: questions and answers

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

Is the AgentKernel AI model data MCP server safe?

No scan can promise that. What its definitions show: 6 tools, 3 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the AgentKernel AI model data MCP server delete data?

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

Can the AgentKernel AI model data 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 AgentKernel AI model data MCP server have?

6 tools: 3 write, 3 read. best_for_task, estimate_cost, cheaper_alternative, recommend_models, get_model and find_models.

Does the AgentKernel AI model data MCP server need sign-in or OAuth?

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

Does the AgentKernel AI model data MCP server send data to outside services?

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

Has the AgentKernel AI model data MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 19, 2026.