Skip to main content
Glama
sophiemiddleton

MCP Refana Server

by sophiemiddleton
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Hybrid

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": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
healthcheck

Return server readiness.

count_signal_background

Extract signal and background event counts in defined kinematic regions.

    Args:
        mom_list: Reconstructed momentum values
        time_list: Reconstructed time values
        mc_list: MC truth labels
        mom_range: [min, max] momentum window for signal region
        time_range: [min, max] time window for signal region
        sign: Particle sign ("minus" for electrons, "plus" for positrons)
        
    Returns:
        Dictionary with signal count, background count, and event statistics
analyze_cuts

Initialize and configure analysis cuts for event selection.

    Args:
        cut_definitions: Dictionary defining cut criteria
        sign: Particle sign ("minus" or "plus")
        
    Returns:
        Dictionary with cut configuration and status
compute_sensitivity

Compute physics sensitivity metrics (significance, limits, intervals).

    Args:
        s_expected: Expected signal events
        b_expected: Expected background events
        b_sys_uncertainty: Systematic uncertainty on background
        exposure: Detector exposure (for normalization)
        efficiency: Signal detection efficiency
        
    Returns:
        Dictionary with significance, CLs limits, and Feldman-Cousins intervals
initialize_ml_selector

Initialize the machine learning selector for BDT-based event selection.

    Returns:
        Dictionary with initialization status and available features
get_cut_efficiency

Calculate efficiency metrics for applied cuts.

    Args:
        cuts_applied: Dictionary describing cuts applied
        n_total: Number of events before cuts
        n_surviving: Number of events after cuts
        
    Returns:
        Dictionary with efficiency and related metrics
summarize_analysisA

Generate a summary of analysis results for a dataset.

    Args:
        dataset_name: Name of the dataset analyzed
        sign: Particle sign
        n_events_processed: Total events processed
        signal_count: Reconstructed signal events
        background_count: Reconstructed background events
        ml_score_mean: Mean ML BDT score (if available)
        
    Returns:
        Dictionary with analysis summary
list_available_datasetsA

List available SAM dataset definitions for Mu2e analysis.

    Returns:
        Dictionary with available datasets and their descriptions
get_dataset_infoA

Get information about a specific SAM dataset definition.

    Args:
        defname: SAM definition name (e.g., 'ensembleMDS3c')
        location: File location ('disk', 'tape', 'scratch', 'nersc')
        
    Returns:
        Dictionary with dataset information: file count, size, availability
create_dataset_filelistA

Create a filelist for analysis from a SAM dataset definition.

    This tool prepares a dataset for use with refana analysis tools.
    
    Args:
        defname: SAM definition name (e.g., 'ensembleMDS3c')
        location: File location ('disk', 'tape', 'scratch', 'nersc')
        max_files: Limit to first N files (useful for testing)
        output_path: Path to save filelist (if None, generates temp path)
        
    Returns:
        Dictionary with filelist path and dataset information

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4/5.0

Scored across 4 tools

Disambiguation5/5

Each tool has a distinct purpose: listing datasets, retrieving dataset info, creating filelists, and summarizing analysis results. No overlap.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern in snake_case, making them predictable and easy to navigate.

Tool Count5/5

Four tools is appropriate for a specialized analysis server, covering key steps without being excessive or insufficient.

Completeness4/5

The set covers dataset discovery, preparation, and result summarization, but lacks a tool to trigger or configure an actual analysis run, which is a minor gap.

Maintenance

ActivitySlowing
ResponsivenessNo issues

Resources