Index9 MCP Server
The Index9 MCP Server provides up-to-date information and live testing capabilities for 300+ AI models from OpenRouter, helping you discover, compare, and evaluate models with current pricing, specifications, and performance data.
Key Capabilities:
Search and Filter Models: Use natural language queries or specific filters (provider, context window, price, capabilities) to discover relevant models from 300+ options
Get Detailed Specifications: Retrieve comprehensive technical details including pricing (input/output per million tokens), context window limits, capabilities (vision, audio, tool_calling, JSON mode, video), architecture, and per-request limits
Live Model Testing: Execute actual API calls to 1-5 models simultaneously using preset scenarios (quick math, code generation, reasoning, instruction following, tool calling) or custom prompts, measuring output quality, latency, token usage, and costs
Semantic Search: Find models using natural language descriptions with relevance scoring that combines semantic similarity, capability matching, and quality signals
Cost Analysis: Access current pricing and estimate costs for model usage, including extended pricing for image processing, audio, web search, and caching
Compare Models Side-by-Side: View pricing, release dates, architecture details (tokenizer, instruct type), moderation status, and performance metrics
Capability Filtering: Filter models by specific capabilities using AND logic to find models meeting multiple requirements
Pagination and Sorting: Browse results with pagination support and sort by relevance, price, release date, or context window size
Stay Current: Access regularly updated model information, solving the problem of outdated AI assistant knowledge
Note: Live testing requires an OpenRouter API key for billing purposes.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Index9 MCP Serverfind models with 128k context under $0.50 per million tokens"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
@index9/mcp
Discover, shortlist, compare, cost-model, and live-test 300+ AI models from your editor
Install
npx -y @index9/mcp@latestOpenRouter API key
Optional: set OPENROUTER_API_KEY in your MCP client config for live test_model calls. dryRun=true works without a key.
Add the key as OPENROUTER_API_KEY in the MCP server environment for your client. Example:
{
"mcpServers": {
"index9": {
"command": "npx",
"args": ["-y", "@index9/mcp@latest"],
"env": {
"OPENROUTER_API_KEY": "sk-or-..."
}
}
}
}Claude Code: Run claude mcp add --transport stdio index9 -- npx -y @index9/mcp or add the same config to .mcp.json / ~/.claude.json.
Tools
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)
compare_models — Diff 2-10 models across pricing, context, capabilities, and tokenizer
list_facets — Enumerate available providers, capabilities, modalities, and tokenizers
test_model — Run live inference or dry-run cost estimation across up to 10 models (requires OpenRouter API key)
Response Metadata
All tool responses include an _index9 object with at least:
apiBaseUrl— The API base URL used for the request
Error responses also include:
status— Upstream HTTP status code_index9.retryAfterSeconds— Present whenRetry-Afteris returned_index9.rateLimit— Present when rate-limit headers are returned (x-ratelimit-limit,x-ratelimit-remaining,x-ratelimit-reset)
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Tools
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/index9-org/mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server