ModelRouter MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| analyze_taskB | Analyze a plan document for task type, complexity, and requirement vector. Advisory analysis only — does not select a model. |
| analyze_repositoryA | Analyze repository metadata (file counts, languages, frameworks, diff stats). No source file contents are read. |
| recommend_modelC | Advisory model recommendation based on plan analysis and registry metadata. User must manually select model in Cursor picker. |
| estimate_costC | Estimate token usage and cost for a specific model given a plan. |
| list_modelsA | List all models in the registry with basic metadata. |
| get_model_profileC | Get full model profile with provenance for a specific model ID. |
| sync_metadataC | Sync model metadata from external sources. Blocked in privacy mode. |
| get_telemetry_summaryA | Get local telemetry summary. Data never leaves the machine. |
| generate_cursor_guidanceC | Generate advisory Cursor guidance snippets. Does not apply or enforce model selection. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
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.