ModelRouter MCP
Advisory MCP server for intelligent LLM model recommendations in Cursor. Provides tools for task analysis, repository analysis, and model selection guidance.
README
ModelRouter MCP
Advisory MCP server for intelligent LLM model recommendations in Cursor.
v1 Capability Statement
Ships:
- Advisory
recommend_modelwith schema-validated JSON - Heuristic task analysis (Layer A) + metadata scoring (Layer B)
- Static seed registry (
registrySnapshot.mode: static_seed) - Benchmark ingest metadata (fixture-based until live sync)
- Guidance snippets for Cursor — user manually picks model
Does NOT ship:
- Force Composer/Auto model selection
- Continuous validation against engineering tasks (Phase 8 opt-in only)
Cursor.models.list()or any IDE runtime model API
Quick Start
npm install
npm run build
npm test
npm run validate-schemas
npm run smoke
Cursor MCP Configuration
{
"mcpServers": {
"modelrouter": {
"command": "node",
"args": ["/absolute/path/to/ModelRouter_MCP/dist/index.js"]
}
}
}
Tools
| Tool | Description |
|---|---|
recommend_model |
Advisory recommendation from plan + repo metadata |
analyze_task |
Task type, complexity, requirement vector |
analyze_repository |
File counts, languages, frameworks, diff stats |
list_models |
Registry model list |
get_model_profile |
Full profile with provenance |
sync_metadata |
Sync from external sources (blocked in privacy mode) |
generate_cursor_guidance |
Advisory snippets — does not apply model |
get_telemetry_summary |
Local telemetry only |
estimate_cost |
Cost estimate for a specific model |
Privacy
See PRIVACY.md. User data never leaves the machine via outbound HTTP.
Maintainer Scripts
# Optional — requires CURSOR_API_KEY
npm run verify-cursor-ids
# CI denylist check
npm run lint:cursor-denylist
Registry
Seed models live in data/models/. Run sync_metadata to refresh from fixture-based adapters (OpenRouter, SWE-bench, Anthropic docs, Ollama). Registry uses static seeds until first successful sync.
Implementation status
| Phase | Status |
|---|---|
| 0 Contracts | Complete |
| 1 MCP transport | Complete |
| 2 Registry | Complete (8 seeds) |
| 3 Analysis + golden set | Complete (30 fixtures) |
| 4 Scoring | Complete |
| 5 E2E static_seed | Complete |
| 6 Sync | Complete (fixture-based) |
| 7 Benchmark ingest | Complete |
| 8 Internal validation | Complete (opt-in) |
| 9 Telemetry + guidance | Complete |
See CONTRIBUTING.md for maintainer workflows.
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.