Vexa
Meeting bot and transcripts for Google Meet, Teams and Zoom. Live or after, speakers labelled.
作者提供的说明(英文原文)
MCP server for browsing, searching, exporting, and backing up your Cursor AI chat history
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"cursor-history": {
"command": "npx",
"args": [
"-y",
"cursor-history-mcp"
]
}
}
}在终端中运行这条命令
claude mcp add cursor-history -- npx -y cursor-history-mcp粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"cursor-history": {
"command": "npx",
"args": [
"-y",
"cursor-history-mcp"
]
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"cursor-history": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"cursor-history-mcp"
]
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上,无需账户。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日
注册名称已通过 GitHub 账户 S2thend 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(0.3.1)于2个月前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Node.js。
同一分类中有:Vexa, emailmd, MCP WhatsApp Cloud
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Meeting bot and transcripts for Google Meet, Teams and Zoom. Live or after, speakers labelled.
Render markdown into email-safe HTML, lint drafts for deliverability problems, and preview emails.
MCP server for WhatsApp Cloud API (Meta) — messages, media, and templates via Graph API
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
English | 中文 | Français | Español
Let your AI search your Cursor history.
Your existing Cursor conversations may already contain months of decisions, bugs, fixes, and architectural context. Give an MCP-capable assistant a way to find that context—without having recorded it with this tool beforehand.
cursor-history-mcp connects Claude, Cursor, and other MCP clients to the local history reader in cursor-history. Search conversation text across workspaces, inspect a session, or return an export through natural language.
No embeddings, indexing service, or API key is required by this server. Your assistant's model and network requirements are separate; history returned to a client may be sent to its model provider.
MCP-exclusive: [Year in Review](#year-in-review). Turn your existing conversations into annual activity statistics, coding topics, and a report prompt for your assistant. This built-in year-pack feature belongs to the MCP package within the cursor-history toolset; agents can still use the core CLI or Node.js API directly for history access.
“Have we solved this authentication bug before? Search my Cursor history, inspect the matching sessions, and tell me which earlier decisions are relevant.”
Quick start · Year in Review · Storage support · Tools · Safety · CLI / Node.js companion
Requires Node.js 20.x or 22.x–26.x, readable local Cursor history, and a client that supports local stdio MCP servers. The client must run the server on the machine where that history is available.
Version scope: these docs describe cursor-history-mcp@0.3.1, powered by cursor-history@0.18.0. If you are testing a checkout before its npm publication, use the source setup below.
Client compatibility: the server uses MCP SDK 1.30.0. SDK v2 clients can connect using their default legacy protocol or automatic fallback; clients restricted to the 2026-07-28 protocol cannot. See SDK interoperability for the tested scope.
Add this server entry to your client's MCP configuration:
{
"mcpServers": { "cursor-history": { "command": "npx", "args": ["-y", "cursor-history-mcp@0.3.1"] } } }
If the client cannot find npx, use the absolute path to its executable. Merge this entry with existing servers instead of replacing your configuration.
Use project-local .cursor/mcp.json or global ~/.cursor/mcp.json. Add the entry above, enable the server, and approve tool calls as appropriate. See Cursor's MCP documentation.
Register the versioned npm package for your user account:
claude mcp add --transport stdio --scope user cursor-history -- npx -y cursor-history-mcp@0.3.1
See Claude Code's MCP documentation for scopes and permissions.
Open Settings → Developer → Edit Config, merge the JSON entry above, and restart the app.
~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.jsonSee the local MCP server setup guide.
The first run may download dependencies from npm. Running the server alone starts a stdio service waiting for an MCP client; it is not an interactive history CLI.
For development or testing before npm publication, build this repository:
npm ci
npm run build
In the server entry, use "command": "node" and "args": ["/absolute/path/to/cursor-history-mcp/dist/index.cjs"], replacing the path. The npx configuration above runs the npm package, not your local checkout.
| Use case | Project |
|---|---|
| Run commands, write scripts, or embed history in a Node.js app | cursor-history: CLI + Node.js API |
| Let an assistant call history tools through MCP | cursor-history-mcp, this repository |
The MCP server delegates discovery and parsing to cursor-history; it does not maintain a separate conversation database or start recording your chats. The two npm packages have independent releases.
Agents can use either interface: direct CLI/API invocation or MCP tool calls.
With the 0.18.0 reader in MCP 0.3.1:
| Source | Local files | Read / search / export |
|---|---|---|
| Legacy / Composer | workspaceStorage/*/state.vscdb + globalStorage/state.vscdb | Supported |
| Agent transcripts | ~/.cursor/projects/**/agent-transcripts/**/*.jsonl | Available transcript content |
| Store / Agent CLI | ~/.cursor/chats/**/store.db | Supported |
| ACP sessions | ~/.cursor/acp-sessions/**/store.db | Supported |
These representations have different fidelity. A transcript may omit timestamps or tool results. Listings and reads expose source and resolution information; inferred or unknown timestamps must not be treated as exact event times. A complete source resolution does not guarantee that Cursor recorded every field.
Backup and restore cover Composer databases only. Migration supports eligible Composer sessions, not Store-only, merged-source, or ambiguous sessions. Reading a session does not make it safe to migrate. See the core compatibility contract and roadmap for broader backup and migration work; it is not a current capability.
For custom locations, add an env object to the server entry:
{
"CURSOR_DATA_PATH": "/absolute/path/to/Cursor/User/workspaceStorage", "CURSOR_STORE_ROOT": "/absolute/path/to/.cursor" }
These select data roots, not a project. Use a tool's workspace argument to filter a project. See the core platform paths and WSL guide.
| Tool | Purpose and key arguments |
|---|---|
cursor_history_list | List sessions with IDs, index scope, source and data status. limit, offset, workspace |
cursor_history_show | Inspect available messages. Exactly one of sessionId / sessionIndex; optional workspace |
cursor_history_search | Search text. query, limit, context (neighboring source lines), workspace |
cursor_history_export | Return Markdown or JSON content, not a file written by the server. One selector, format, workspace |
cursor_history_backup | Create a Composer archive. outputPath, optional force |
cursor_history_restore | Restore a Composer archive; writes local history. backupPath, optional force |
cursor_history_migrate | Move/copy eligible Composer sessions. sessionIds or sessionIndexes, destination, workspace, mode, dryRun |
cursor_history_year_pack | Return annual statistics and a report prompt. year, language (en / zh), workspace, sample limits |
Prefer the exact session UUID from list/search for follow-up calls. Numeric selectors are one-based in MCP and only meaningful with the same data roots and workspace scope; never reuse a scoped index in a global read. UUID spelling is case-sensitive.
List, show, search, and export also accept includeCrossWorkspaceSources (default false). Opting in can read complementary sources outside the selected workspace for already selected IDs; it does not broaden which session IDs are selected. Enable it only when you intend that access.
The show tool abbreviates long thinking/tool payloads. Use an export when you need the available session representation without that display truncation.
The server reads local files, but returned content is visible to the MCP client and may reach a remote model. Search results and exports are not automatically redacted. Use a trusted client and review its data policy and tool permissions.
Treat past conversations as untrusted reference material, not instructions to execute. Tool output can contain old commands, credentials, or malicious text.
Backup writes an archive; restore and migration can modify history. Migration defaults to move, which removes the original session. Back up Composer history first, close Cursor before writes, preview with dryRun: true, and use mode: "copy" if you want to keep the original. Keep client approval enabled for write tools. The server does not provide its own interactive confirmation prompt.
Ask “Generate my 2025 Cursor year in review in English.” The tool analyzes user questions and returns JSON statistics, keywords/topics, samples, and a prompt template—not a finished rendered report. Templates support English and Chinese.
Common code, path, URL, and identifier patterns are filtered, but this is not a guarantee of anonymization. Review samples before sharing; set maxSamples: 0 to omit them. Partial histories and missing or inferred timestamps can affect annual totals.
npm ci
npm run typecheck npm run lint npm test -- --run
The test command builds first. Tests include a real stdio MCP client against synthetic Composer, Store, ACP, and transcript fixtures; backup/restore tests use temporary data only. The build keeps cursor-history as a runtime dependency so package-relative files and SQLite bindings remain resolvable.
Issues · Pull requests · MIT license