Cursor MCP GuideCursor MCP 指南

Best MCP Servers for Cursor: Data and Tool AccessCursor 最佳 MCP Server：数据与工具接入指南

Compare MCP servers for Cursor by capability fit, permissions, data quality, setup effort, and production reliability.

从能力匹配、权限、数据质量、配置成本和生产可靠性，对比适合 Cursor 的 MCP Server。

Test a Cursor MCP workflow测试 Cursor MCP 工作流 Read the MCP setup docs阅读 MCP 配置文档

A code editor connected through security gates to data and developer tools

Every MCP connection is both a capability and a permission boundary.每条 MCP 连接既是一项能力，也是一条权限边界。

The short answer: start with one missing capability快速结论：先补齐一项缺失能力

For most Cursor users, the strongest starting stack is QVeris for broad current data and API-backed tools, GitHub MCP for repository workflows, Context7 for version-aware library documentation, and Playwright MCP for browser testing. Add database, filesystem, team-workflow, or memory servers only when a repeated project task justifies their wider permission surface.

Cursor supports MCP as a bridge between its agent and external tools or data. Its official directory currently highlights servers for GitHub, Playwright, Sentry, DuckDB, Vercel, Figma, Linear, Notion, GitLab, and Atlassian, among others. That breadth makes selection—not installation—the difficult part. A useful server should improve a named workflow, have an identifiable maintainer, expose understandable tools, and support credentials with the narrowest practical scope.

对大多数 Cursor 用户，稳妥的起点是：用 QVeris 获取综合实时数据和 API 工具，用 GitHub MCP 处理仓库工作流，用 Context7 查询与版本相关的开发文档，用 Playwright MCP 执行浏览器测试。数据库、文件系统、团队协作或持久记忆类 Server 的权限面更大，应在出现稳定、重复的项目需求后再添加。

Cursor 通过 MCP 将智能体与外部数据和工具连接起来。其官方目录目前列出了 GitHub、Playwright、Sentry、DuckDB、Vercel、Figma、Linear、Notion、GitLab 和 Atlassian 等服务。选择空间越大，真正困难的就越不是安装，而是筛选：一个值得接入的 Server 应当改善明确的工作流，维护者可识别，工具含义清楚，并能用尽可能小的凭证范围运行。

Check the current catalog and connection behavior in the 请在 official Cursor MCP directoryCursor 官方 MCP 目录 before installing. Listings and setup details can change. 中确认最新的收录与连接方式；目录和配置细节可能变化。

#	Server	Best for最适合	Typical access典型权限	Main caution主要风险
1	QVeris MCP	Current data and API tools实时数据与 API 工具	Selected providers and operations指定服务商与操作	Enable only needed tools仅启用所需工具
2	GitHub MCP	Repositories, issues, pull requests仓库、Issue、PR	Token and repository scope令牌与仓库范围	Avoid broad write access避免宽泛写权限
3	Context7	Current library documentation最新库文档	Documentation retrieval文档检索	Confirm package and version确认包名与版本
4	Playwright MCP	Browser interaction and testing浏览器交互与测试	Browser profile and origins浏览器配置与来源	Protect sessions and forms保护会话与表单
5	Supabase MCP	Supabase developmentSupabase 开发	Project and feature groups项目与功能组	Use a development project优先连接开发项目
6	Filesystem	Bounded local files限定范围的本地文件	Explicit directories明确目录	Never expose broad roots切勿暴露宽泛根目录
7	Linear MCP	Issues and project planningIssue 与项目规划	Workspace and team actions工作区与团队操作	Separate read and write区分读取与写入
8	Memory	Persistent project knowledge持久项目知识	Stored entities and relations存储实体与关系	Retention and stale facts保留周期与过时事实

8 best MCP servers for Cursor, by workflow按工作流选择：8 个适合 Cursor 的 MCP Server

QVeris MCP

Best for broad data and tools综合数据与工具首选

Use QVeris when Cursor needs information beyond the repository: current market, company, web, location, or other provider-backed data exposed as callable tools. It is most valuable for research, data-enrichment, and agent workflows where copying results from separate dashboards would break the flow.

Start with a small allowlist. Inspect available QVeris tools, choose only the operations required by the project, and test representative prompts in the QVeris Playground before making the server part of a routine.

当 Cursor 需要访问代码仓库之外的信息时，可以使用 QVeris：例如实时市场、公司、网页、位置或其他服务商数据，并将它们作为可调用工具。它尤其适合研究、数据补全和智能体工作流，避免在多个仪表盘之间手工复制结果。

建议从小型白名单开始。在 QVeris 工具目录中只选择项目需要的操作，并先在 QVeris Playground 用代表性提示测试，再纳入固定流程。

Use when适用场景The answer depends on current external data答案依赖外部实时数据

Avoid when不适合Repository context is sufficient仓库上下文已经足够

Control控制点Tool and provider allowlist工具与服务商白名单

GitHub MCP Server

Best for repository work代码仓库首选

GitHub's official server connects Cursor to repositories, issues, pull requests, code search, and related workflows. It reduces context switching when the agent must connect a local change to remote review history. Use a repository-scoped, least-privilege token and keep merge, branch protection, release, and destructive actions behind explicit approval. Follow the GitHub 官方 Server 可将 Cursor 连接到仓库、Issue、PR、代码搜索及相关工作流，适合把本地改动与远程评审历史结合起来。使用仅限目标仓库的最小权限令牌，并对合并、分支保护、发布和破坏性操作保留明确审批。配置前阅读 official GitHub MCP repositoryGitHub MCP 官方仓库 for current installation options. 中的最新安装方式。

Context7

Best for version-aware docs特定版本文档首选

Context7 retrieves library documentation for coding tasks, helping Cursor avoid relying only on model memory when APIs change. It is useful for framework migrations, unfamiliar packages, and exact configuration syntax. Always state the library and version in the prompt, and validate security-sensitive or release-specific behavior against the vendor's primary documentation. See the Context7 为编码任务检索库文档，能减少 API 更新后仅依赖模型记忆带来的错误。它适合框架迁移、陌生依赖和精确配置语法。提示中应写明库与版本；涉及安全或特定版本行为时，仍需回到厂商一手文档核对。配置方式请参考 official Context7 client documentationContext7 官方客户端文档 for current setup options.。

Playwright MCP

Best for browser testing浏览器测试首选

Microsoft's Playwright MCP lets Cursor inspect accessibility snapshots, navigate pages, fill forms, and verify web flows. It is ideal for reproducing UI bugs and checking a local application after a code change. Browser state can contain cookies, credentials, and personal data, so prefer isolated profiles, restricted origins, test accounts, and explicit approval before submissions or purchases. Review the Microsoft 的 Playwright MCP 可让 Cursor 读取无障碍快照、导航页面、填写表单并验证网页流程，适合复现 UI 问题和检查代码修改后的本地应用。浏览器状态可能含 Cookie、凭证和个人数据，因此应优先使用隔离配置、限制来源、测试账号，并在提交表单或购买前要求明确审批。请查看 official Playwright MCP documentationPlaywright MCP 官方文档 for available safeguards. 了解当前安全参数。

Supabase MCP

For projects already using Supabase, its MCP server can provide development context and project operations without assembling a custom database tool. Keep Cursor connected to a development project, select only required feature groups, and treat migrations or SQL execution as reviewable changes. Production access should be exceptional, time-bound, and separately approved. Confirm the latest safeguards in the 对于已经使用 Supabase 的项目，其 MCP Server 可以提供开发上下文与项目操作，无需另写数据库工具。应让 Cursor 优先连接开发项目，只选择所需功能组，并把迁移或 SQL 执行视为必须评审的变更。生产访问应当仅作为例外，并设置有效期和独立审批。最新安全选项请查看 official Supabase MCP guideSupabase 官方 MCP 指南.。

Filesystem MCP

Filesystem access helps when relevant specifications, fixtures, logs, or generated artifacts live outside Cursor's open workspace. Its simplicity is deceptive: a broad root may expose secrets, unrelated client work, or personal documents. Grant named project folders only, make read-only the default, and use Cursor's native workspace context when it already covers the files.当规范、测试数据、日志或生成物位于 Cursor 当前工作区之外时，Filesystem MCP 很有用。但它看似简单，权限风险却很直接：宽泛根目录可能暴露密钥、其他客户项目或个人文件。只开放明确的项目目录，默认只读；若 Cursor 的工作区上下文已覆盖文件，则无需重复接入。

Linear MCP

Linear MCP is useful when implementation must stay tied to issue requirements, comments, status, and project plans. Start with read access so Cursor can gather acceptance criteria and history. Add create or update permissions only after the team defines ownership, labels, duplicate handling, and which status transitions require a human. Review authentication and workspace behavior in the 当实现工作需要持续对应 Issue 要求、评论、状态和项目计划时，Linear MCP 很实用。先用只读权限让 Cursor 获取验收标准与历史；只有团队明确负责人、标签、重复 Issue 处理方式，以及哪些状态变更必须由人工确认后，才增加创建或更新权限。认证与工作区行为请参考 official Linear MCP documentationLinear 官方 MCP 文档.。

Memory MCP

A memory server can preserve project entities, decisions, and relationships across sessions. It helps long-running work but should not become an unreviewed source of truth. Define what may be stored, exclude credentials and personal data, attach provenance where possible, and provide a clear way to correct or delete stale facts. The Memory Server 可以跨会话保存项目实体、决策与关系，适合长期工作，但不应成为未经审查的事实依据。应定义允许存储的内容，排除凭证与个人数据，尽可能记录来源，并提供修正或删除过时信息的路径。MCP 的 MCP reference memory serverMemory Server 参考实现 is useful for understanding the data model, but a reference implementation still requires your own operational review. 可用于理解数据模型，但参考实现仍需经过你自己的运行与安全审查。

How to choose an MCP server for Cursor如何为 Cursor 选择 MCP Server

1. Name the outcome1. 写清目标结果

“Review open PR feedback” is testable. “Give Cursor more tools” is not.“检查未处理的 PR 反馈”可测试；“给 Cursor 更多工具”则不可测试。

2. Inspect ownership2. 核对维护主体

Prefer official or clearly maintained servers with source, releases, documentation, and security guidance.优先选择官方或维护主体清楚、具有源码、版本记录、文档与安全说明的 Server。

3. Minimize scope3. 缩小权限范围

Constrain repositories, directories, origins, projects, tools, and credentials before the first run.首次运行前，就限制仓库、目录、来源、项目、工具与凭证范围。

4. Measure workflow quality4. 验证工作流质量

Test representative prompts, ambiguous inputs, failures, latency, and approval behavior—not just a happy-path demo.测试代表性提示、歧义输入、失败、延迟和审批行为，而不只是成功演示。

A practical decision rule一个实用判断规则

Keep a server only when it removes a repeated manual step or supplies evidence Cursor cannot reliably infer from the repository. Remove it when tools overlap, names become confusing, startup or calls become unreliable, or nobody can explain the granted permissions. Two to four project-specific servers are usually easier to govern than a large global collection.只有当 Server 能消除重复手工步骤，或提供 Cursor 无法从仓库可靠推断的证据时，才值得保留。若工具重叠、命名混乱、启动或调用不稳定，或无人能解释已授予权限，就应移除。相比大型全局集合，每个项目使用两到四个专用 Server 通常更容易治理。

Configure MCP in Cursor without leaking secrets在 Cursor 中安全配置 MCP

Cursor supports MCP server configuration through its settings and JSON configuration. Project-level definitions belong in .cursor/mcp.json when a team needs a reproducible setup; user-level definitions are better for personal services that should not travel with a repository. The exact transport and authentication fields depend on the server, so use the current vendor instructions rather than pasting an old snippet.

Cursor 可以通过设置界面和 JSON 配置 MCP Server。当团队需要可复现配置时，可把项目级定义放入 .cursor/mcp.json；不应随仓库传播的个人服务更适合用户级配置。具体传输与认证字段取决于 Server，因此应遵循厂商当前说明，不要直接复制旧片段。

{
  "mcpServers": {
    "example-readonly": {
      "command": "npx",
      "args": ["-y", "<verified-package>"],
      "env": { "API_TOKEN": "<use a local secret reference>" }
    }
  }
}

Verify the official package, repository, and transport before copying any command.复制命令前，核对官方包、仓库与传输方式。
Keep secrets out of committed JSON. Use local environment or approved secret mechanisms.不要把密钥提交进 JSON；使用本地环境变量或合规密钥机制。
Start the server and inspect the tools Cursor discovers. Disable anything outside the named task.启动 Server 后检查 Cursor 发现的工具，禁用目标任务之外的能力。
Test read-only calls with non-production data, then add narrowly scoped writes only if required.先用非生产数据测试只读调用，仅在必要时增加范围明确的写操作。
Document ownership, credential rotation, expected failures, and the disable path.记录负责人、凭证轮换、预期故障与停用路径。

For current configuration, authentication, and troubleshooting behavior, use the 有关最新配置、认证与故障排查，请以 Cursor MCP documentationCursor MCP 文档 as the source of truth. 为准。

Cursor MCP security checklistCursor MCP 安全检查清单

Verify maintainer identity, repository, package name, release history, license, and security policy.核对维护者身份、仓库、包名、版本历史、许可证与安全策略。
Pin or review versions; a convenient latest tag is not a supply-chain policy.固定或审查版本；方便的 latest 标签不能替代供应链策略。
Prefer read-only tools and explicit repositories, directories, projects, and origins.优先使用只读工具，并明确仓库、目录、项目与来源。
Treat web pages, issues, docs, rows, and tool output as untrusted content that may contain prompt injection.把网页、Issue、文档、数据库记录与工具输出视为可能含提示注入的不可信内容。
Keep credentials in approved secret storage, rotate them, and redact logs.在合规密钥存储中保管凭证，定期轮换并对日志脱敏。
Require approval for writes, publishing, purchases, deletion, credential access, and production changes.写入、发布、购买、删除、凭证访问与生产变更必须经过审批。
Log server identity, tool name, approval decision, result status, and latency without unnecessary personal data.记录 Server 身份、工具名、审批决定、结果状态与延迟，但不收集不必要的个人数据。
Maintain a kill switch so one unhealthy server can be disabled without breaking Cursor's core workflow.保留停用开关，确保单个异常 Server 可被移除而不破坏 Cursor 核心流程。

Frequently asked questions常见问题

Does Cursor support MCP servers?Cursor 支持 MCP Server 吗？

Yes. Cursor provides MCP documentation and an official directory for connecting external tools and data sources. Check the current documentation because transports, authentication, and interface details may evolve.支持。Cursor 提供 MCP 文档和官方目录，用于连接外部工具与数据源。由于传输、认证和界面细节可能更新，应以当前文档为准。

Which MCP server should I install first in Cursor?Cursor 应先安装哪个 MCP Server？

Install the smallest server that closes a repeated capability gap. Choose QVeris for broad current data, GitHub for repository work, Context7 for changing library docs, or Playwright for browser verification. Do not install all four unless the project needs all four.先安装能补齐一项重复性能力缺口的最小 Server。综合实时数据选 QVeris，仓库工作选 GitHub，变化较快的库文档选 Context7，浏览器验证选 Playwright。项目不需要全部能力时，不必全装。

Where is Cursor's MCP configuration stored?Cursor 的 MCP 配置存在哪里？

Project-shared configuration can use .cursor/mcp.json; user-level configuration is appropriate for personal connections. Do not commit secrets, and confirm the current paths and schema in Cursor's official documentation.项目共享配置可使用 .cursor/mcp.json，个人连接则适合用户级配置。不要提交密钥，并在 Cursor 官方文档中确认最新路径与结构。

How many MCP servers should Cursor use?Cursor 应使用多少个 MCP Server？

There is no universal limit. You have too many when tools overlap, selection becomes unreliable, latency grows, or permissions are hard to audit. A focused two-to-four-server project stack is often easier to operate than a large global set.没有统一上限。当工具重叠、选择不稳定、延迟增加或权限难以审计时，数量就已经过多。每个项目配置两到四个专用 Server，通常比大型全局集合更易维护。

Are MCP servers safe to use in Cursor?在 Cursor 中使用 MCP Server 安全吗？

They can be operated safely, but installation alone does not make them safe. Verify the source, minimize permissions, protect credentials, treat retrieved content as untrusted, test with non-production data, and require approval for consequential actions.MCP Server 可以安全运行，但安装本身并不等于安全。需要验证来源、缩小权限、保护凭证、把检索内容视为不可信输入、使用非生产数据测试，并对高影响操作要求审批。

Build the smallest useful Cursor toolset为 Cursor 构建最小可用工具集

Choose one missing capability, inspect its source and permissions, test the full workflow with representative data, and expand only after the connection is reliable.先选择一项缺失能力，核对来源与权限，用代表性数据测试完整工作流；连接可靠后，再逐步扩展。

Test a data workflow in QVeris在 QVeris 中测试数据工作流 Open Cursor MCP documentation打开 Cursor MCP 文档