Skip to content
AgentKernel logo

AgentKernel MCP server

Which MCP servers are AgentKernel's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-27

← Back to AgentKernel

Whose server it is
  • Registry namesi.agentkernel/modelsverified in the MCP registry

The registry name sits under agentkernel.si. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-27
  • Stateanswerschecked 2026-10-27
  • Tools6
  • Server calls itselfagentkernel
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 102 ms.

Should an agent connect itNot proven either way yet
  • Its tools do every use case we checked: Find a model for a task and budget; Compare model prices and performance across providers; Estimate monthly API cost for a token volume.
  • Checked on 1 of the 7 days it takes to judge reliability.

Once connected

  • For "Find a model for a task and budget", the likely first call is recommend_models.
  • For "Compare model prices and performance across providers", the likely first call is find_models.
  • For "Estimate monthly API cost for a token volume", the likely first call is estimate_cost.
  • Parameters are untyped or undescribed in 6 of 6 tools: check arguments before calling.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 1, the first on 2026-10-27
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
  • What an agent can do with it3 of 3 use cases
  • Answeredmeasuring1 of the 7 daily checks it takes to print a share
  • Median first answer125 ms
  • Space in an agent's context≈ 1,048 tokensthe definitions of all its tools (6), which an agent carries on every turn
  • Tool definitionsB · 83 of 100
  • Typed results0 of 6 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 6 of 6

What an agent can do with it

  • can do · Find a model for a task and budget
  • can do · Compare model prices and performance across providers
  • can do · Estimate monthly API cost for a token volume

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers6 tools · read 2026-10-27
  • best_for_task

    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…

  • recommend_models

    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.

  • get_model

    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.

  • find_models

    Searches and filters the catalog of language models by name, provider, licence and privacy, sorted by performance, coding, agentic index, price or context.

  • estimate_cost

    Monthly API cost at base rates for up to five models and a token volume, with the volume translated into words and pages.

  • cheaper_alternative

    For a model you use today, finds a cheaper model at most five performance-index points lower for the same usage.

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "models": {
      "type": "http",
      "url": "https://www.agentkernel.si/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http agentkernel https://www.agentkernel.si/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://www.agentkernel.si/mcp as a custom connector in the settings.

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.