Skip to main content
Glama

history_list

Retrieve team collaboration history records to track project progress and review past interactions between AI models.

Instructions

查看团队协作历史记录列表

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNo返回记录数量,默认 10

Implementation Reference

  • MCP CallToolRequestSchema handler for 'history_list' tool. Extracts optional 'limit' parameter, calls historyManager.list(), formats with formatList(), and returns text content.
    case 'history_list': { const { limit } = args as { limit?: number }; const summaries = historyManager.list(limit || 10); return { content: [ { type: 'text', text: historyManager.formatList(summaries), }, ], }; }
  • Tool schema definition including name, description, and inputSchema for 'history_list' in ListTools response.
    { name: 'history_list', description: '查看团队协作历史记录列表', inputSchema: { type: 'object', properties: { limit: { type: 'number', description: '返回记录数量,默认 10', }, }, }, },
  • HistoryManager.list(limit) reads JSON history files from storage directory, parses them into summaries, sorts by recency, limits count, core logic for retrieving history list.
    list(limit = 20): HistorySummary[] { if (!existsSync(this.historyDir)) { return []; } // 获取并排序文件 const files = readdirSync(this.historyDir) .filter((f) => f.endsWith('.json')) .sort() .reverse() .slice(0, limit); // 读取并解析 return files .map((file) => { try { const content = readFileSync(join(this.historyDir, file), 'utf-8'); const entry = JSON.parse(content) as HistoryEntry; return { id: entry.id, timestamp: entry.timestamp, task: entry.task, summary: entry.summary, experts: entry.experts, }; } catch { return null; } }) .filter((e): e is HistorySummary => e !== null); }
  • HistoryManager.formatList(summaries) generates Markdown-formatted list of history summaries with previews, dates, tasks, and experts.
    formatList(summaries: readonly HistorySummary[]): string { if (summaries.length === 0) { return '暂无协作历史记录'; } const lines = ['## 📚 协作历史记录\n']; for (const entry of summaries) { const date = new Date(entry.timestamp).toLocaleString(); const taskPreview = entry.task.length > TASK_PREVIEW_MAX_LENGTH ? `${entry.task.slice(0, TASK_PREVIEW_MAX_LENGTH)}...` : entry.task; lines.push( `- **${entry.id}** (${date})`, ` 任务: ${taskPreview}`, ` 专家: ${entry.experts.join(', ')}`, '' ); } lines.push('\n使用 `history_get` 工具查看详情,传入 ID 即可。'); return lines.join('\n'); }

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/7836246/claude-team-mcp'

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