Schema | ModelRouter MCP

ModelRouter MCP

Describes the environment variables required to run the server.

Name	Required	Description	Default
No arguments

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.

Features and capabilities supported by this server

Protocol revision2025-11-25

Capability	Details
`tools`	{ "listChanged": true }

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.

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/MrSolution07/ModelRouter_MCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server