Skip to main content
Glama
Cappybara12

OpenXAI MCP Server

by Cappybara12

get_leaderboard

Retrieve ranked performance results for AI explanation methods on specified datasets and metrics to compare evaluation outcomes.

Instructions

Get leaderboard results for explanation methods

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
datasetNoDataset name to get leaderboard for
metricNoMetric to sort leaderboard by

Implementation Reference

  • The main handler function for the 'get_leaderboard' tool. It returns a hardcoded sample leaderboard with rankings of various explanation methods based on the provided dataset and metric parameters.
    async getLeaderboard(dataset, metric) { const sampleLeaderboard = { dataset: dataset || 'german', metric: metric || 'PGI', rankings: [ { rank: 1, method: 'SHAP', score: 0.87, model: 'XGBoost' }, { rank: 2, method: 'LIME', score: 0.82, model: 'XGBoost' }, { rank: 3, method: 'Integrated Gradients', score: 0.78, model: 'Neural Network' }, { rank: 4, method: 'Gradient × Input', score: 0.75, model: 'Neural Network' }, { rank: 5, method: 'Guided Backprop', score: 0.71, model: 'Neural Network' } ], updated: new Date().toISOString() }; return { content: [ { type: 'text', text: `OpenXAI Leaderboard\n\n` + `Dataset: ${sampleLeaderboard.dataset}\n` + `Metric: ${sampleLeaderboard.metric}\n` + `Last Updated: ${sampleLeaderboard.updated}\n\n` + `Rankings:\n` + JSON.stringify(sampleLeaderboard.rankings, null, 2) + `\n\nNote: This is a sample leaderboard. Visit https://open-xai.github.io/ for actual leaderboard data.` } ] }; }
  • Input schema definition for the get_leaderboard tool, specifying optional dataset and metric parameters.
    inputSchema: { type: 'object', properties: { dataset: { type: 'string', description: 'Dataset name to get leaderboard for' }, metric: { type: 'string', description: 'Metric to sort leaderboard by' } }, required: [] }
  • index.js:279-280 (registration)
    Registration of the get_leaderboard tool handler in the CallToolRequestSchema switch statement, dispatching calls to the getLeaderboard method.
    case 'get_leaderboard': return await this.getLeaderboard(args.dataset, args.metric);
  • index.js:199-216 (registration)
    Tool registration in the ListToolsRequestSchema response, including name, description, and input schema.
    { name: 'get_leaderboard', description: 'Get leaderboard results for explanation methods', inputSchema: { type: 'object', properties: { dataset: { type: 'string', description: 'Dataset name to get leaderboard for' }, metric: { type: 'string', description: 'Metric to sort leaderboard by' } }, required: [] } },

Latest Blog Posts

MCP directory API

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

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Cappybara12/mcpopenxAI'

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