F
licenseNot graded
qualityD
maintenanceAutomatically routes queries to the most suitable AI model based on task type, cost constraints, and performance needs, supporting multiple providers and customizable priorities.
-
ypollak2/llm-router
by ypollak2
Related Servers
Alternatives to ypollak2/llm-router
No user-submitted related servers found.
Related Servers
- AlicenseBqualityDmaintenanceRoute prompts intelligently across Claude, Gemini, and GPT-4o, automatically picking the best model for every task while minimizing token cost.58 npmMIT
- AlicenseAqualityBmaintenanceRoutes tasks to the optimal AI model based on task type and benchmark scores across 25+ platforms. Automatically selects the best model for coding, reasoning, writing, and more using public benchmark data.520 npm1MIT
- -licenseNot gradedqualityNot gradedmaintenanceIntelligent routing service that selects optimal AI models based on capability requirements and normalizes input/output formats across multiple providers like OpenAI, Anthropic, Google, and others.-
- FlicenseNot gradedqualityAmaintenanceIntelligently routes AI tool calls (search, extract, browse) to the cheapest capable provider by default with automatic failover and audit receipts, enabling cost-effective agent workflows.2-
- AlicenseCqualityFmaintenanceAn AI router that connects applications to multiple LLM providers (OpenAI, Anthropic, Google, DeepSeek, Ollama, etc.) with smart model orchestration capabilities, enabling dynamic switching between models for different reasoning tasks.343 npm37MIT
TDQS
A3.5/5.0
Scored across 60 tools
Disambiguation2/5
Many tools have overlapping purposes, e.g., llm_route, llm_auto, llm_query, llm_code, llm_generate, llm_analyze, llm_research all route tasks to LLMs based on complexity or task type. Additionally, multiple savings/usage tools (llm_savings, llm_gain, llm_digest, llm_team_report, llm_team_push, llm_session_spend) create confusion. While descriptions differentiate them, the sheer number of similar tools makes it hard for an agent to select the correct one.
Naming Consistency4/5
The vast majority of tools follow a consistent `llm_<verb>_<noun>` or `llm_<noun>` pattern in snake_case. The five `agoragentic_*` tools are a separate prefix but still consistent within their own domain. Minor inconsistency: some tools use verb+noun (e.g., llm_check_usage, llm_set_profile) while others are just noun (llm_health, llm_budget). Overall, the pattern is clear and predictable.
Tool Count1/5
With 60 tools, the server is severely over-scoped for an MCP server. A typical well-coherent server has 3–15 tools; this has 60, many of which are redundant or could be consolidated (e.g., multiple savings report tools, multiple file system helpers). The high count overwhelms the agent and reduces coherence.
Completeness4/5
The tool set covers an exceptionally broad domain: task routing, classification, evaluation, savings tracking, profile management, file system operations, orchestration, media generation, setup, health checks, and team collaboration. Few obvious gaps exist; almost any operation related to LLM routing is present. The only minor omission is perhaps a direct tool for model comparison or A/B testing, but overall completeness is high.
Maintenance
ActivityActive
ResponsivenessWithin a week