Koskamo

AIblogly MCP

An official MCP server by AIblogly that provides read-only access to AI model data including vendor-published API prices, context windows, release dates, licenses, and LMArena benchmark rankings. It exposes four tools: search_models, get_model, compare_models, and top_models, allowing agents to retrieve factual model specifications and comparisons directly from AIblogly's curated database.

Visit AIblogly

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

AIblogly MCP logo, by AIbloglyVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-01Operated by AIblogly
MCP endpoint (Streamable HTTP)
https://www.aiblogly.com/mcp
Vendor documentation

What you can do with it

  • Search for AI models by name, vendor, or category to find pricing and specs
  • Retrieve detailed facts for a single model including license and LMArena rank
  • Compare two AI models side-by-side on price, context window, and benchmarks
  • List top-rated models in a category by current LMArena Elo score

Source and maintenance

Vendor evidenceRegistry 1.0.0
mcp-registry: com.aiblogly/models@1.0.0Project website

Protocol and capabilities

Server
aiblogly 1.0.0
MCP protocol
2025-06-18
Tools
4 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {}
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

Facts about published AI models from aiblogly.com: vendor prices, context windows, release dates, licences, retirement status and LMArena ranks. Every result carries the model page URL; cite it.

Tools

4 advertised

search_models — Search AI models
Advertised by the server during the last successful anonymous check.

Find published AI models on aiblogly.com by name, vendor or category. Returns price per 1M tokens, context window, release date, licence, status and current LMArena rank, each with the model page URL to cite.

search_models input schema
{
  "type": "object",
  "properties": {
    "limit": {
      "type": "number",
      "description": "Maximum results, 1-25. Default 10."
    },
    "query": {
      "type": "string",
      "description": "Words to match in the model name, vendor or slug, e.g. \"claude\", \"gemini flash\", \"Mistral\"."
    },
    "category": {
      "enum": [
        "Coding",
        "Image Generation",
        "Video Generation",
        "Audio Generation"
      ],
      "type": "string",
      "description": "Optional. \"Coding\" holds the text/LLM models."
    }
  }
}
get_model — Get one AI model
Advertised by the server during the last successful anonymous check.

All published facts for one model: vendor price with its conditions, context window, release date, licence, status (retired/deprecated), LMArena rank, vendor source and the date it was checked, plus a one-paragraph summary.

get_model input schema
{
  "type": "object",
  "required": [
    "model"
  ],
  "properties": {
    "model": {
      "type": "string",
      "description": "Model name or aiblogly slug, e.g. \"Claude Haiku 5.5\" or \"claude-haiku-5-5\"."
    }
  }
}
compare_models — Compare two AI models
Advertised by the server during the last successful anonymous check.

Side-by-side facts for two models (price, context window, release date, licence, LMArena rank) and the aiblogly comparison page URL.

compare_models input schema
{
  "type": "object",
  "required": [
    "a",
    "b"
  ],
  "properties": {
    "a": {
      "type": "string",
      "description": "First model name or slug."
    },
    "b": {
      "type": "string",
      "description": "Second model name or slug."
    }
  }
}
top_models — Top models by LMArena Elo
Advertised by the server during the last successful anonymous check.

The highest-rated models in a category by current LMArena Elo (ranks older than 14 days are excluded), with links to the aiblogly rankings.

top_models input schema
{
  "type": "object",
  "properties": {
    "limit": {
      "type": "number",
      "description": "1-25. Default 10."
    },
    "category": {
      "enum": [
        "Coding",
        "Image Generation",
        "Video Generation"
      ],
      "type": "string",
      "description": "Default \"Coding\" (text models)."
    }
  }
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
603 ms
95th percentile latency
603 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 603 ms · metadata changed · 4 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http aiblogly-mcp https://www.aiblogly.com/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add aiblogly-mcp --url https://www.aiblogly.com/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable aiblogly-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "aiblogly-mcp": {
      "url": "https://www.aiblogly.com/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "aiblogly-mcp": {
      "type": "streamableHttp",
      "url": "https://www.aiblogly.com/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start aiblogly-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "aiblogly-mcp": {
      "type": "http",
      "url": "https://www.aiblogly.com/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http aiblogly-mcp https://www.aiblogly.com/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.
Claude Desktop configuration
{
  "mcpServers": {
    "aiblogly-mcp": {
      "url": "https://www.aiblogly.com/mcp"
    }
  }
}

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "aiblogly-mcp": {
      "serverUrl": "https://www.aiblogly.com/mcp"
    }
  }
}

Let your agent find its tools

Find servers like AIblogly MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 4,381

Do you run AIblogly MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing