ModelRouter MCP
Related Servers
Alternatives to ModelRouter MCP
No user-submitted related servers found.
Related Servers
- AlicenseAqualityBmaintenanceMCP server that lets any agent or MCP host delegate tasks to the Cursor CLI agent for fast, headless execution. Supports task delegation, project discovery, file analysis, and follow-up sessions.314 npm3MIT
- AlicenseCqualityDmaintenanceMCP server for sharing source-backed engineering memory across AI coding clients like Cursor and VS Code.301MIT
- AlicenseCqualityDmaintenanceCentralized MCP server that provides standardized development workflow commands to Cursor AI, auto-detecting project type (Laravel, Next.js, Flutter, Architecture) and offering relevant commands for implementation, testing, and commits.236 npmMIT
- AlicenseNot gradedqualityCmaintenanceMCP server that enables intent search over Python call graphs inside Cursor, returning cite spans and call chains to reduce token usage.MIT
- AlicenseAqualityDmaintenanceUniversal MCP server that analyzes any codebase and provides structured context to AI assistants. Dynamic, accurate, and token-efficient.187 npmMIT
- FlicenseNot gradedqualityDmaintenanceLocal MCP server for Cursor that analyzes code, finds bugs, generates tests and documentation via OpenRouter.-
TDQS
Scored across 9 tools
Each tool targets a distinct aspect of model routing: repository analysis, task analysis, cost estimation, guidance generation, profile retrieval, telemetry, listing, recommendation, and metadata sync. No two tools have overlapping purposes.
All tool names follow a consistent verb_noun pattern in snake_case, such as analyze_repository, estimate_cost, and list_models. This makes the tool set predictable and easy to navigate.
With 9 tools, the server provides a comprehensive yet concise set of capabilities for an advisory model router. Each tool has a clear role, and the count is well within the optimal 3-15 range.
The tool surface covers the core workflow of analyzing tasks, recommending models, estimating costs, and retrieving metadata. Minor gaps exist, such as no tool for direct model selection or comparison, but these are intentional given the advisory nature.