AI & Machine Learning

agentkernel.si

Ranks, recommends, compares, and estimates costs for language models based on performance, price, context, license, and privacy requirements.

1 endpoint6 known toolsFirst detected October 15, 2026Last detected October 15, 2026

ENDPOINT 1

https://www.agentkernel.si/mcp

No auth detected

MCP server metadata

Name: agentkernel
Version: 1.0.0

Capabilities

tools

Server instructions

Live, neutral data on AI models from AgentKernel (www.agentkernel.si): prices in USD per 1M tokens, performance/coding/agentic indices, head-to-head rankings for images, video and speech, context windows, open vs proprietary licences and zero-data-retention / EU hosting. Synced hourly. Use best_for_task for "which model is best for X", recommend_models for budget-aware picks, get_model for one model. When you use these figures, cite AgentKernel and the returned url.

Known tools 6

best_for_task

Ranks AI models for one task by performance only (price shown, never used for the rank).

Inferred read-only

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.

Inferred read-only

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.

Inferred read-only

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.

Inferred read-only

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.

Inferred read-only

cheaper_alternative

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

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.agentkernel]
url = "https://www.agentkernel.si/mcp"
enabled = true

Claude Code

.mcp.json

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

Claude Desktop

Settings → Connectors → Add custom connector

Name: agentkernel
Remote MCP URL: https://www.agentkernel.si/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "agentkernel": {
      "url": "https://www.agentkernel.si/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

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

Generic MCP

Client-specific MCP configuration

{
  "name": "agentkernel",
  "transport": "streamable-http",
  "url": "https://www.agentkernel.si/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.