MCP server for LLM/VLM model selection — compare 300+ models with real-time benchmarks, pricing, and personalized recommendations. No API key
MCP server for LLM/VLM model selection — compare 300+ models with real-time benchmarks, pricing, and personalized recommendations. No API key required. That is what the llm advisor mcp mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.
LLMs have knowledge cutoffs. Ask Claude "what's the best coding model right now?" and it cannot answer with current data. This MCP server fixes that by feeding live model intelligence directly into your AI assistant's context window.
The server publishes 7 tools. What each one is for:
get_model_info — Detailed specs for a specific model: pricing, benchmarks, percentile ranks, capabilities, and a ready-to-use API code examplePricing — The Pricing tool exposed by this serverBenchmarks — The Benchmarks tool exposed by this serverlist_top_models — Top-ranked models for a category. Includes release dates for freshness awarenesscompare_models — Side-by-side comparison for 2-5 models. Best values are bolded automatically. Includes a Released row so you can spot outdated models at a glancerecommend_model — Personalized top-3 recommendations. Scores combine weighted benchmarks, pricing, capability bonuses, and a freshness bonus (+3 points for modelsContributing — 1. Fork the repository 2. Create a feature branch 3. Add tests for new functionality 4. Run npm test to verify all 51 tests pass 5. Submit a pullInstallation goes through your MCP client rather than a global install: point it at llm-advisor-mcp on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
Configuration is passed through the environment: OPENROUTER_API_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Llm Advisor MCP's toolset — get_model_info, Pricing, Benchmarks and 4 more — is a fair guide to whether it matches your workflow. It is maintained by daichi-kudo; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| get_model_info | Detailed specs for a specific model: pricing, benchmarks, percentile ranks, capabilities, and a ready-to-use API code example. |
| Pricing | The Pricing tool exposed by this server. |
| Benchmarks | The Benchmarks tool exposed by this server. |
| list_top_models | Top-ranked models for a category. Includes release dates for freshness awareness. |
| compare_models | Side-by-side comparison for 2-5 models. Best values are **bolded** automatically. Includes a Released row so you can spot outdated models at a glance. |
| recommend_model | Personalized top-3 recommendations. Scores combine weighted benchmarks, pricing, capability bonuses, and a freshness bonus (+3 points for models released within 3 months, +1 within 6 months). |
| Contributing | 1. Fork the repository 2. Create a feature branch 3. Add tests for new functionality 4. Run npm test to verify all 51 tests pass 5. Submit a pull request |
{
"mcpServers": {
"llm-advisor": {
"command": "npx",
"args": ["-y", "llm-advisor-mcp"]
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| OPENROUTER_API_KEY | Credential the server authenticates with. | Yes |
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.