ModelSpec MCP

ModelSpec is an analysis of alternatives for AI models that decides which models fit a job from requirements, sourced benchmarks, and real cost. The MCP server allows agents to programmatically access these unbiased decisions, enabling them to select the most appropriate model for specific tasks based on evidence rather than routing guesses.

Endpoint and access

No sign-in: your client connects and lists tools immediately, with no account or key.

No sign-inEndpoint checked 2026-10-18Operated by ModelSpec

MCP endpoint (Streamable HTTP)

https://api.modelspec.dev/mcp

Vendor documentation

What you can do with it

Select the best AI model for a specific coding task
Compare model costs and performance benchmarks
Route agent requests to optimal model providers
Get unbiased model recommendations based on requirements

Tools advertised by the last live check:

rank
model_info
list_use_cases
policy_check
decide
compare_models
hardware_fit
vocab
feedback

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 a Streamable HTTP server. Use --scope project to write .mcp.json for the repo.

Claude Code configuration

claude mcp add --transport http modelspec-mcp https://api.modelspec.dev/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 modelspec-mcp --url https://api.modelspec.dev/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable modelspec-mcp in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "modelspec-mcp": {
      "url": "https://api.modelspec.dev/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure). The type must be streamableHttp for a remote HTTP server.

Cline configuration

{
  "mcpServers": {
    "modelspec-mcp": {
      "type": "streamableHttp",
      "url": "https://api.modelspec.dev/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start modelspec-mcp and inspect its tools.

VS Code configuration

{
  "servers": {
    "modelspec-mcp": {
      "type": "http",
      "url": "https://api.modelspec.dev/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 modelspec-mcp https://api.modelspec.dev/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": {
    "modelspec-mcp": {
      "url": "https://api.modelspec.dev/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": {
    "modelspec-mcp": {
      "serverUrl": "https://api.modelspec.dev/mcp"
    }
  }
}

See all 1,015

Do you run ModelSpec 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