@index9/mcp 1.0.30 → 4.0.0

package/README.md

@@ -1,80 +1,32 @@
 # @index9/mcp
 
-[![npm version](https://badge.fury.io/js/@index9%2Fmcp.svg)](https://badge.fury.io/js/@index9%2Fmcp)
-[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+Search, inspect, and benchmark 300+ AI models from your editor
 
-Your AI assistant’s model knowledge is outdated. **index9 fixes that.**
+## Install
 
-MCP server providing up-to-date pricing, context limits, and capabilities for 300+ models from [OpenRouter](https://openrouter.ai).
-
-## Installation
-
-Add to your MCP client configuration:
-
-```json
-{
-  "mcpServers": {
-    "index9": {
-      "command": "npx",
-      "args": ["-y", "@index9/mcp"]
-    }
-  }
-}
+```bash
+npx -y @index9/mcp@latest
 ```
 
-**Where to add this:**
+Optional: `OPENROUTER_API_KEY` for live test_model calls.
 
-| Client         | Location                                                                  |
-| -------------- | ------------------------------------------------------------------------- |
-| Cursor         | Settings → MCP → Add new global MCP server                                |
-| VS Code        | Settings → MCP Servers (use `"type": "stdio"`)                            |
-| Claude Desktop | `~/Library/Application Support/Claude/claude_desktop_config.json` (macOS) |
-| Claude Code    | `claude mcp add index9 -- npx -y @index9/mcp`                             |
-
-See [index9.dev](https://index9.dev/#installation) for all supported clients.
+**Claude Code:** Run `claude mcp add --transport stdio index9 -- npx -y @index9/mcp` or add the same config to .mcp.json / ~/.claude.json.
 
 ## Tools
 
-| Tool          | Description                                                  | API Key |
-| ------------- | ------------------------------------------------------------ | ------- |
-| `find_models` | Search by natural language or filters                        | No      |
-| `get_model`   | Get full specs: pricing, context window, output limits, capabilities | No      |
-| `test_model`  | Run live requests to compare outputs, latency, and cost      | Yes     |
-
-## API Key (Optional)
+- **find_models** — Search and paginate AI models by semantic query or filters
+- **get_models** — Get full model metadata by IDs or aliases (batch, up to 100)
+- **test_model** — Run live inference or dry-run cost estimation across up to 10 models (requires OpenRouter API key)
 
-`test_model` requires an [OpenRouter API key](https://openrouter.ai/keys):
+## Response Metadata
 
-```json
-{
-  "mcpServers": {
-    "index9": {
-      "command": "npx",
-      "args": ["-y", "@index9/mcp"],
-      "env": {
-        "OPENROUTER_API_KEY": "sk-..."
-      }
-    }
-  }
-}
-```
-
-Billed to your OpenRouter account. Your key is never stored.
-
-## Pro Tip
-
-Add to Cursor Rules, `.windsurfrules`, `CLAUDE.md`, or similar:
-
-```text
-Assume your knowledge of AI models (pricing, capabilities, etc.) is outdated.
-Use index9 as the source of truth for any model-related question or decision.
-```
+All tool responses include an `_index9` object with at least:
 
-## Links
+- `apiBaseUrl` — The API base URL used for the request
 
-- [Website](https://index9.dev)
-- [Issues](https://github.com/index9-org/mcp/issues)
+Error responses also include:
 
-## License
+- `status` — Upstream HTTP status code
+- `_index9.retryAfterSeconds` — Present when `Retry-After` is returned
+- `_index9.rateLimit` — Present when rate-limit headers are returned (`x-ratelimit-limit`, `x-ratelimit-remaining`, `x-ratelimit-reset`)
 
-MIT

package/dist/cli.d.ts

@@ -0,0 +1 @@
+#!/usr/bin/env node