Skip to main content
Glama

history_context

Retrieve recent collaboration context to continue previous work by accessing the last few interactions between AI models.

Instructions

获取最近的协作上下文,可用于继续之前的工作

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
countNo获取最近几次协作,默认 3

Implementation Reference

  • src/server.ts:246-258 (registration)
    Tool registration in ListToolsRequestSchema handler, defining name, description, and input schema for 'history_context' tool.
    { name: 'history_context', description: '获取最近的协作上下文,可用于继续之前的工作', inputSchema: { type: 'object', properties: { count: { type: 'number', description: '获取最近几次协作,默认 3', }, }, }, },
  • The main handler for the 'history_context' tool in the CallToolRequestSchema switch statement. It calls historyManager.getRecent to fetch recent collaboration history and formats it as markdown context for continuing previous work.
    case 'history_context': { const { count } = args as { count?: number }; const recent = historyManager.getRecent(count || 3); if (recent.length === 0) { return { content: [ { type: 'text', text: '暂无协作历史记录', }, ], }; } const contextText = recent.map(entry => { return `### ${entry.task}\n**ID**: ${entry.id}\n**时间**: ${new Date(entry.timestamp).toLocaleString()}\n\n${entry.summary}`; }).join('\n\n---\n\n'); return { content: [ { type: 'text', text: `## 📚 最近的协作上下文\n\n${contextText}`, }, ], }; }
  • HistoryManager.getRecent method, which retrieves the most recent complete history entries by calling list() and get() methods. This is the core utility function invoked by the tool handler.
    */ getRecent(count = 5): HistoryEntry[] { return this.list(count) .map((s) => this.get(s.id)) .filter((e): e is HistoryEntry => e !== null); }

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