SeaShell plugins extend the agent in 2 ways. They contribute tools, new capabilities the model can call alongside the built-in ones, and they hook into lifecycle events, running your code at defined points as a session proceeds. Together that covers both what the agent can do and what happens around it, without modifying SeaShell itself.
Two extension points, not one
Most tools offer 1 extension point and force everything through it. SeaShell separates contributing a tool, which changes what the agent is able to do, from hooking a lifecycle event, which changes what happens around what it does.
The split matters because the two have different shapes. Adding a deployment command is a tool: the model decides when to call it. Recording every session to an internal audit system is a hook: nobody wants the model deciding whether auditing happens. Collapsing both into one mechanism means one of them ends up modeled badly.
Plugin tools are still permission-gated
A tool contributed by a plugin passes through the same allow, ask, or deny check as the 1st-party ones. Installing a plugin does not create a path around the permission system, and unmatched actions still default to ask.
This is what makes third-party extension safe to adopt. The safety properties of SeaShell are enforced at the tool-call boundary rather than inside each tool, so they apply uniformly to code the SeaShell team did not write. A plugin can add capability; it cannot quietly add authority.
Plugins or MCP servers
The 2 mechanisms answer different questions. Write a plugin when you want to change how SeaShell itself behaves. Use a Model Context Protocol server when you want to connect SeaShell to a system that already exists and may serve other clients too.
MCP is the better choice for anything with an existing API surface, because the server you write is reusable beyond SeaShell. Plugins are the better choice for behavior that is specific to how your team runs the agent, since that logic has no meaning outside the tool it customizes.
Frequently asked questions
- Can I extend SeaShell with my own tools?
- Yes. SeaShell plugins contribute tools the agent can call and hook into agent lifecycle events.
- Are plugin tools subject to permissions?
- Yes. A plugin-contributed tool passes the same allow, ask, or deny check as a built-in tool.
- What is the difference between a plugin and an MCP server?
- A plugin changes how SeaShell itself behaves. An MCP server connects SeaShell to an existing system and is reusable by other MCP clients.
- Can a plugin run code during a session?
- Yes. Lifecycle hooks let a plugin run at defined points as a session proceeds, independently of what the model chooses to call.
Try SeaShell in your terminal
The terminal-native AI coding agent. Free core, single binary.
Install SeaShellRelated guides
Atlas with GPT-5.5 Pro in 2026
Explore Atlas with OpenAI's GPT-5.5 Pro, the maximum-effort reasoning model for 2026. Ideal for complex planning with its 1.05M token context window, but consider its $180/Mtok output cost.
Atlas with Snowflake Cortex in 2026
Explore Atlas with Snowflake Cortex in 2026. Access frontier models like Claude Opus 4.8 and GPT-5.5 within your Snowflake security boundary, billed in credits.
Atlas with Claude Opus 4.7 (2026)
Explore Claude Opus 4.7 in Atlas, the terminal-native AI coding agent. Leverage its 1M token context window and 128K max output for complex refactors at $5/$25 per Mtok.
Atlas with Amazon Nova Lite in 2026
Explore Atlas with Amazon Nova Lite, Amazon's low-cost multimodal model. Leverage its 300K token context for efficient coding tasks and direct AWS IAM billing in 2026.
Atlas with Claude Opus 4.6 in 2026
Explore Atlas with Claude Opus 4.6 in 2026. This model offers a 1M token context window and 128K output, ideal for large codebases at $5/$25 per Mtok.
Atlas with Google Vertex AI (gateway) in 2026
Atlas integrates with Google Vertex AI (gateway), providing a secure enterprise path to Gemini and Claude models in 2026. Leverage service-account authentication and a 1M context window for Gemini 3.1 Pro.
Atlas for Scala in 2026
Atlas is a terminal-native AI coding agent for Scala in 2026. Run it in a project with a build.sbt, let it read your traits and implicits, and approve every diff.
Atlas for Dart in 2026
Adopt Atlas, the terminal-native AI coding agent, for Dart development in 2026. Enhance productivity with intelligent code search, refactoring, and robust safety features across your Dart projects.