MCP Server Support
Ability to connect to and interact with an MCP (Model Context Protocol) server, including task delegation and external tool access.
Overview
The Model Context Protocol (MCP) is an open protocol that enables AI coding agents to safely connect to external data sources and tools. MCP servers act as bridges between AI agents and various systems, providing structured access to databases, APIs, file systems, and development tools while maintaining security boundaries.
Why It Matters
MCP support dramatically expands what AI coding agents can do by allowing them to interact with your specific tools and data sources. This means agents can query your databases, interact with your APIs, use specialized tools, and access project-specific context that would otherwise be unavailable.
Common Use Cases
- ▸Connecting to company databases to query schemas and data for code generation
- ▸Integrating with project management tools like Jira or Linear
- ▸Accessing specialized development tools and build systems
- ▸Connecting to documentation systems and knowledge bases
- ▸Interacting with cloud services and deployment pipelines
Agent Support
| Agent | Support Level | Notes | Actions |
|---|---|---|---|
| Claude Code | ✅ Full Support | Supports MCP servers for connecting custom tools and services, enhancing AI workflows. | |
| Cline | ✅ Full Support | MCP lets Cline use external tools and data sources through MCP servers. | |
| Cursor | ✅ Full Support | Supports one-click MCP server setup for external tool integration, enhanced with OAuth authentication. | |
| Devin Desktop | ✅ Full Support | MCP servers can be configured for the Cascade agent in mcp_config.json (for tools such as GitHub and databases), with admin controls for Teams. | |
| Gemini CLI | ✅ Full Support | Supports MCP servers for custom integrations, configured in ~/.gemini/settings.json. | |
| GitHub Copilot | ✅ Full Support | GitHub Copilot supports MCP (Model Context Protocol) servers in VS Code, JetBrains, and Xcode, available in Agent Mode. Users can connect MCP tools directly from the Copilot panel. | |
| Google Antigravity | ✅ Full Support | Antigravity supports MCP servers, configured in Settings (Antigravity 2.0), the MCP Store (IDE), or mcp_config.json at global (~/.gemini/config/) or workspace (.agents/) level for the CLI. | |
| Google Jules | ✅ Full Support | Since February 2, 2026, Jules supports Model Context Protocol integrations for Linear, Stitch, Neon, Tinybird, Context7, and Supabase, authenticated with API keys. | |
| Kiro | ✅ Full Support | MCP servers can be configured in workspace or user MCP configuration files and are supported across the IDE, CLI, and web. | |
| OpenAI Codex | ✅ Full Support | The ChatGPT desktop app, Codex CLI, and IDE extension support MCP servers and share MCP configuration for the same Codex host. | |
| OpenCode | ✅ Full Support | OpenCode supports both local and remote MCP servers. | |
| Replit Agent | ✅ Full Support | Agent can connect to external services through MCP; Replit maintains an MCP directory (for example, Airwallex Developer for building and testing payment integrations). | |
| Zed AI | ✅ Full Support | Zed natively supports MCP (Model Context Protocol) servers via its 'Context Servers' feature. MCP tools are accessible from the assistant panel and in agentic mode, enabling integration with databases, APIs, and custom tooling. | |
| Aider | ❌ No Support | Aider does not natively support MCP (Model Context Protocol) servers. It has its own tool/plugin ecosystem distinct from MCP. Some workarounds exist via shell commands, but native MCP integration is not available as of early 2026. | |
| Devin | ❌ No Support | Devin does not support MCP (Model Context Protocol) servers. It has its own tool ecosystem (shell, browser, editor) within the cloud sandbox but does not use the MCP standard for external tool integration. |
Frequently Asked Questions
What is MCP (Model Context Protocol)?▼
Why is MCP support important for AI coding agents?▼
Is MCP secure to use?▼
Related Features
Automatic Context Awareness
The capability of an AI coding agent to automatically detect and incorporate relevant context, such as open files, project structure, or custom instructions, without manual intervention.
ExecutionFilesystem Access
Ability to autonomously read, write, create, and modify files in the project directory and beyond.
ExecutionBroad IDE Integration
The ability of an AI coding agent to seamlessly integrate with a wide range of Integrated Development Environments (IDEs) such as VS Code, JetBrains, Xcode, and others.
Editor IntegrationReady to Compare Agents?
See how different AI coding agents stack up for MCP Server Support and other features. Make an informed decision based on your specific needs.