Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

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

CapabilityDetails
tools
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
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

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

B3.4/5.0

Scored across 9 tools

Disambiguation5/5

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.

Naming Consistency5/5

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.

Tool Count5/5

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.

Completeness4/5

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.

Maintenance

ActivitySlowing
ResponsivenessNo issues