Zed

Editor

Zed Industries

A high-performance, open source code editor with a built-in Agent Panel, MCP support, and ACP-based external agents.

MCP

Supported

Configure MCP servers (context servers) in settings.json under the context_servers key, or install them as Zed extensions. Supports local stdio and remote servers with OAuth.

Verified 2026-07-12Docs

Transportsstdiohttp

Authoauthheaders

Config files

Path	Scope	Format	Key
`~/.config/zed/settings.json` macOS/Linux. On Windows: %APPDATA%/Zed/settings.json.	Global	json	context_servers
`.zed/settings.json`	Project	json	context_servers

Fields

Field	Type	Description
`source`	"custom" \| "extension"	How the server is provided. Entries added via the UI set 'custom'; extension-provided servers use 'extension'.
`command`	string	Command to start a local (stdio) server.
`args`	string[]	Arguments passed to the command.
`env`	record<string, string>	Environment variables for a local server.
`url`	string	Endpoint URL for a remote server.
`headers`	record<string, string>	HTTP headers for a remote server (e.g. Authorization: Bearer <token>).

Capabilities

ToolsSupported

PromptsSupported

ResourcesNot supported

RootsNot supported

ElicitationNot supported

SamplingNot supported

Examples

Local and remote context servers

{
  "context_servers": {
    "local-mcp-server": {
      "command": "some-command",
      "args": ["arg-1", "arg-2"],
      "env": {}
    },
    "remote-mcp-server": {
      "url": "https://example.com/mcp",
      "headers": { "Authorization": "Bearer <token>" }
    },
    "remote-mcp-server-with-oauth": {
      "url": "https://mcp.example.com/mcp"
    }
  }
}

•MCP servers can also be installed as Zed extensions from the extension registry (Settings > AI > MCP Servers > Install from Extensions).
•Remote servers without an Authorization header trigger the standard MCP OAuth flow.
•Zed handles notifications/tools/list_changed and reloads a server's tool list at runtime without a restart.
•Servers configured in Zed are forwarded to External Agents over the Agent Client Protocol (ACP).
•Per-tool approval uses agent.tool_permissions with the key format mcp:<server>:<tool>; agent.tool_permissions.default is one of confirm, allow, or deny.
•Custom agent profiles can scope which context servers and tools are enabled via enable_all_context_servers and per-server tool toggles.

Skills

Supported

SKILL.md skill folders following the open Agent Skills standard, loaded autonomously from a catalog or invoked manually via slash command or @-mention.

Verified 2026-07-12Docs

Invoke/skill-name@skillautomatic

Config files

Path	Scope	Format	Key
`.agents/skills/<name>/SKILL.md` Project-local skills, only loaded from trusted worktrees.	Project	markdown	—
`~/.agents/skills/<name>/SKILL.md` Global skills, available in every project.	Global	markdown	—

Fields

Field	Type	Description
`name`*	string	Lowercase letters, numbers, and hyphens only; 1-64 chars; no leading/trailing/consecutive hyphens. Should match the folder name.
`description`*	string	What the skill does and when to use it. Keep under 1024 bytes; longer descriptions load with a warning.
`disable-model-invocation`	boolean	When true, hides the skill from the agent's catalog; it remains invocable via slash command or @-mention.

Examples

Manual-only deploy skill

---
name: deploy
description: Deploy the current branch to production.
disable-model-invocation: true
---

## Instructions

Step-by-step instructions for the agent...

•Skills replaced Zed's reusable Rules Library.
•Flat layout only: skills must be direct children of the skills root; nested folders are not discovered.
•Project-local skills only load from trusted worktrees; a project-local skill overrides a global skill with the same name.
•Live reload: SKILL.md edits take effect immediately without restarting the session.
•The total size of all skill names and descriptions is capped at 50KB for the catalog.
•Skills can bundle scripts/, references/, and assets/ that the agent loads on demand.
•Skills can be shared via self-contained zed://skill links and imported from GitHub .md URLs; a built-in /create-skill skill scaffolds new skills.
•Invoking a user-created skill prompts for permission (same flow as tool permissions); built-in skills do not prompt.

Rules

Supported

Always-on instructions via AGENTS.md: a personal global file plus one project instruction file, with compatibility for .rules, .cursorrules, CLAUDE.md, and similar.

Verified 2026-07-12Docs

Config files

Path	Scope	Format	Key
`~/.config/zed/AGENTS.md` Personal instructions for every project. On Windows: %APPDATA%/Zed/AGENTS.md.	Global	markdown	—
`AGENTS.md` Project instructions at the worktree root. First matching compatibility file wins (see notes).	Project	markdown	—
`.rules` Zed-native compatibility instruction file; highest priority in the match order.	Project	text	—

Examples

Project AGENTS.md

# Project instructions

- Run `cargo test` before committing.
- Follow the repository's error-handling conventions in src/errors.rs.

•Zed's Rules Library was replaced: reusable rules became Skills, always-on rules became Instructions (AGENTS.md).
•For project instructions Zed uses the first matching file in this order: .rules, .cursorrules, .windsurfrules, .clinerules, .github/copilot-instructions.md, AGENT.md, AGENTS.md, CLAUDE.md, GEMINI.md.
•Project instructions override personal AGENTS.md when they conflict.
•Instructions apply to the Zed Agent; External Agents and Terminal Threads read their own native instruction files.

Hooks

Not supported

Zed has no lifecycle hook system for the Agent Panel: no user-configurable scripts fire on agent events such as tool use, prompt submit, or session start/end.

Verified 2026-07-12

•Agent lifecycle hooks (custom commands, pre/post tool-use scripts) are open feature requests on the Zed GitHub repo (e.g. issues #57890, #52688) but are not shipped.
•The unrelated create_worktree Task hook runs when Zed creates a linked git worktree for parallel agents; it is a workspace task hook, not an agent lifecycle hook.

Commands

Partial

Slash commands in the Agent Panel invoke skills by name, plus the built-in /compact. There is no separate custom prompt-template command format; custom commands are authored as skills.

Verified 2026-07-12Docs

Invoke/skill-name/compact/create-skill

Config files

Path	Scope	Format	Key
`.agents/skills/<name>/SKILL.md` Skills double as slash commands; see the skills surface for the full format.	Project	markdown	—
`~/.agents/skills/<name>/SKILL.md` Global skills are also available as slash commands in every project.	Global	markdown	—

•Typing / in the Agent Panel message editor lists installed skills; selecting one injects the skill's instructions as context.
•/compact manually compacts the current Zed Agent thread.
•/create-skill invokes the built-in skill-creation skill.
•Legacy Text Threads have their own built-in context slash commands (/file, /fetch, /prompt, /now, /diagnostics, /symbols, /tab, /selection, /terminal, /default); these do not work in the modern Agent Panel. See https://zed.dev/docs/ai/text-threads.
•User-defined prompt-template command files (e.g. a .zed/commands/ directory) are an open feature request, not a shipped feature.

Settings

Supported

Agent behavior is configured in settings.json under the agent key: tool permissions, profiles, auto-compaction, feature-specific models, and model parameters.

Verified 2026-07-12Docs

Config files

Path	Scope	Format	Key
`~/.config/zed/settings.json` macOS/Linux. On Windows: %APPDATA%/Zed/settings.json.	Global	json	agent
`.zed/settings.json` Project settings override user settings for this worktree.	Project	json	agent

Fields

Field	Type	Description
`tool_permissions.default`	"confirm" \| "allow" \| "deny"	Default tool-approval behavior for the Zed Agent. confirm (default) prompts before every tool action.
`profiles`	object	Named agent profiles that toggle built-in tools and context servers (e.g. enable_all_context_servers, per-server tools).
`auto_compact`	{ enabled: boolean, threshold: string \| number }	Automatic thread compaction. Threshold is a percentage string ("90%"), a token count, or a negative remaining-token count.
`model_parameters`	array	Temperature overrides per provider, model, or provider/model pair; matching entries are checked last to first.
`inline_assistant_model`	object	Model override for the Inline Assistant.
`commit_message_model`	object	Model override for Git commit message generation.
`thread_summary_model`	object	Model override for thread summaries.
`subagent_model`	object	Model override for subagents.
`commit_message_instructions`	string	Instructions applied only to generated Git commit messages.

Examples

Auto-compaction and commit message instructions

{
  "agent": {
    "auto_compact": {
      "enabled": true,
      "threshold": "90%"
    },
    "commit_message_instructions": "Use the Conventional Commits format: <type>(<scope>): <description>."
  }
}

•The Settings Editor (agent: open settings) exposes LLM providers, External Agents, and MCP servers; zed: open settings file opens the raw JSON.
•MCP servers live in the same settings.json under the context_servers key (see the mcp surface).
•In Zed v0.224.0+ tool approval is controlled by agent.tool_permissions.default; earlier versions used the agent.always_allow_tool_actions boolean (default false).
•Per-tool permission rules support MCP tools with the key format mcp:<server>:<tool>.