chat-recall

One searchable history across every AI coding tool, with secret scanning and a shared task board.

这个条目提供什么？

chat-recall 是 ChatHome Skills 收录的 MCP 条目，来源为 Official MCP Registry，质量分 78/100。作为 Model Context Protocol 服务器，它向 Claude、Cursor、Copilot 等兼容 MCP 的 LLM 客户端暴露可直接调用的工具，让 agent 的能力超出模型内置范围。该条目由 ChatHome Skills 的每日抓取从官方 registry 和 GitHub 发现查询中收录，每次运行都会重新核验仓库事实、新鲜度信号和安装元数据。质量分综合了官方 registry 收录情况、可用安装命令、许可证完整性、仓库活跃度和 GitHub star 趋势，完整算法说明见来源页。安装命令已列于上方，可直接复制使用。在将 chat-recall 加入生产 agent 工作流前，请核对上方的最近更新日期和仓库状态——下方事实快照是最近一次抓取的时点值。

事实快照

来源: Official MCP Registry
质量: 78/100
安装方式: streamable-http
仓库: munhq/chat-recall
仓库更新: 2026年10月6日

安装命令

mcp add io.github.munhq/chat-recall https://chatrecall.dev/mcp

安装方式: streamable-http

运行此命令前，请先核对上游源码。

GitHub 项目主页

质量

仓库 Stars

仓库更新

2026年10月6日

质量分如何计算？

由六个维度加权得出，满分 100。
来源可信度（25）：是否收录于官方或精选 registry。
可安装性（25）：可直接运行的命令 > 已声明传输方式 > 仅源码。
维护活跃度（20）：最近推送时间；已归档条目此项为 0。
采用度（20）：仓库 star 数，按对数曲线计分。
文档完整性（10）与描述质量（10）：是否有已解析的 manifest 或 SKILL.md frontmatter，以及是否为真实描述而非占位文本。
某个来源结构上无法提供的维度（registry 不提供 star 和许可证）不计入该条目的平均分，而不是记为 0 分，因此不同来源的条目仍可横向比较。

MCP manifest

{
  "_meta": {
    "io.modelcontextprotocol.registry/official": {
      "status": "active",
      "isLatest": true,
      "updatedAt": "2026-10-06T18:32:22.814951Z",
      "publishedAt": "2026-10-06T18:32:22.814951Z",
      "statusChangedAt": "2026-10-06T18:32:22.814951Z"
    }
  },
  "server": {
    "name": "io.github.munhq/chat-recall",
    "title": "chat-recall",
    "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
    "remotes": [
      {
        "url": "https://chatrecall.dev/mcp",
        "type": "streamable-http"
      }
    ],
    "version": "0.7.19",
    "packages": [
      {
        "version": "0.7.19",
        "transport": {
          "type": "stdio"
        },
        "identifier": "chat-recall",
        "runtimeHint": "npx",
        "registryType": "npm",
        "environmentVariables": [
          {
            "name": "CHAT_RECALL_SERVER",
            "format": "string",
            "description": "Server to sync to. Defaults to the hosted service at https://chatrecall.dev; set it to your own instance to self-host. Self-hosting is free for one person."
          },
          {
            "name": "CHAT_RECALL_MCP_PROFILE",
            "format": "string",
            "choices": [
              "lean",
              "full"
            ],
            "default": "lean",
            "description": "Which tools to register: \"lean\" (default, 28 tools — tool choice degrades as the list grows) or \"full\" (all 63 tools, plus recall_help — a directory of the rest; 4 code-intelligence tools register only with the codeindex companion on PATH). Every tool works when called by name either way."
          },
          {
            "name": "CHAT_RECALL_NO_DAEMON",
            "format": "string",
            "description": "Set to 1 to load the whole server inside each session. By default every session with the same profile and server shares one background daemon, and each session is a thin relay onto it — the engine is loaded once per machine instead of once per session. Turn it off for a sandbox with no writable runtime directory."
          },
          {
            "name": "CHAT_RECALL_DAEMON_IDLE_SECS",
            "format": "string",
            "description": "Seconds with no session attached before the shared daemon exits and returns its memory. Default 900. Set 0 to keep it resident."
          }
        ]
      }
    ],
    "repository": {
      "url": "https://github.com/munhq/chat-recall",
      "source": "github"
    },
    "websiteUrl": "https://chatrecall.dev",
    "description": "One searchable history across every AI coding tool, with secret scanning and a shared task board."
  }
}

报告此条目的问题