---
summary: "Install and use Codex, Claude, and Cursor bundles as Klaw plugins"
read_when:
  - You want to install a Codex, Claude, or Cursor-compatible bundle
  - You need to understand how Klaw maps bundle content into native features
  - You are debugging bundle detection or missing capabilities
title: "Plugin bundles"
---

Klaw can install plugins from three external ecosystems: **Codex**, **Claude**,
and **Cursor**. These are called **bundles** — content and metadata packs that
Klaw maps into native features like skills, hooks, and MCP tools.

<Info>
  Bundles are **not** the same as native Klaw plugins. Native plugins run
  in-process and can register any capability. Bundles are content packs with
  selective feature mapping and a narrower trust boundary.
</Info>

## Why bundles exist

Many useful plugins are published in Codex, Claude, or Cursor format. Instead
of requiring authors to rewrite them as native Klaw plugins, Klaw
detects these formats and maps their supported content into the native feature
set. This means you can install a Claude command pack or a Codex skill bundle
and use it immediately.

## Install a bundle

<Steps>
  <Step title="Install from a directory, archive, or marketplace">
    ```bash
    # Local directory
    klaw plugins install ./my-bundle

    # Archive
    klaw plugins install ./my-bundle.tgz

    # Claude marketplace
    klaw plugins marketplace list <marketplace-name>
    klaw plugins install <plugin-name>@<marketplace-name>
    ```

  </Step>

  <Step title="Verify detection">
    ```bash
    klaw plugins list
    klaw plugins inspect <id>
    ```

    Bundles show as `Format: bundle` with a subtype of `codex`, `claude`, or `cursor`.

  </Step>

  <Step title="Restart and use">
    ```bash
    klaw gateway restart
    ```

    Mapped features (skills, hooks, MCP tools, LSP defaults) are available in the next session.

  </Step>
</Steps>

## What Klaw maps from bundles

Not every bundle feature runs in Klaw today. Here is what works and what
is detected but not yet wired.

### Supported now

| Feature       | How it maps                                                                                 | Applies to     |
| ------------- | ------------------------------------------------------------------------------------------- | -------------- |
| Skill content | Bundle skill roots load as normal Klaw skills                                               | All formats    |
| Commands      | `commands/` and `.cursor/commands/` treated as skill roots                                  | Claude, Cursor |
| Hook packs    | Klaw-style `HOOK.md` + `handler.ts` layouts                                                 | Codex          |
| MCP tools     | Bundle MCP config merged into embedded Pi settings; supported stdio and HTTP servers loaded | All formats    |
| LSP servers   | Claude `.lsp.json` and manifest-declared `lspServers` merged into embedded Pi LSP defaults  | Claude         |
| Settings      | Claude `settings.json` imported as embedded Pi defaults                                     | Claude         |

#### Skill content

- bundle skill roots load as normal Klaw skill roots
- Claude `commands` roots are treated as additional skill roots
- Cursor `.cursor/commands` roots are treated as additional skill roots

This means Claude markdown command files work through the normal Klaw skill
loader. Cursor command markdown works through the same path.

#### Hook packs

- bundle hook roots work **only** when they use the normal Klaw hook-pack
  layout. Today this is primarily the Codex-compatible case:
  - `HOOK.md`
  - `handler.ts` or `handler.js`

#### MCP for Pi

- enabled bundles can contribute MCP server config
- Klaw merges bundle MCP config into the effective embedded Pi settings as
  `mcpServers`
- Klaw exposes supported bundle MCP tools during embedded Pi agent turns by
  launching stdio servers or connecting to HTTP servers
- the `coding` and `messaging` tool profiles include bundle MCP tools by
  default; use `tools.deny: ["bundle-mcp"]` to opt out for an agent or gateway
- project-local Pi settings still apply after bundle defaults, so workspace
  settings can override bundle MCP entries when needed
- bundle MCP tool catalogs are sorted deterministically before registration, so
  upstream `listTools()` order changes do not thrash prompt-cache tool blocks

##### Transports

MCP servers can use stdio or HTTP transport:

**Stdio** launches a child process:

```json
{
  "mcp": {
    "servers": {
      "my-server": {
        "command": "node",
        "args": ["server.js"],
        "env": { "PORT": "3000" }
      }
    }
  }
}
```

**HTTP** connects to a running MCP server over `sse` by default, or `streamable-http` when requested:

```json
{
  "mcp": {
    "servers": {
      "my-server": {
        "url": "http://localhost:3100/mcp",
        "transport": "streamable-http",
        "headers": {
          "Authorization": "Bearer ${MY_SECRET_TOKEN}"
        },
        "connectionTimeoutMs": 30000
      }
    }
  }
}
```

- `transport` may be set to `"streamable-http"` or `"sse"`; when omitted, Klaw uses `sse`
- `type: "http"` is a CLI-native downstream shape; use `transport: "streamable-http"` in Klaw config. `klaw mcp set` and `klaw doctor --fix` normalize the common alias.
- only `http:` and `https:` URL schemes are allowed
- `headers` values support `${ENV_VAR}` interpolation
- a server entry with both `command` and `url` is rejected
- URL credentials (userinfo and query params) are redacted from tool
  descriptions and logs
- `connectionTimeoutMs` overrides the default 30-second connection timeout for
  both stdio and HTTP transports

##### Tool naming

Klaw registers bundle MCP tools with provider-safe names in the form
`serverName__toolName`. For example, a server keyed `"vigil-harbor"` exposing a
`memory_search` tool registers as `vigil-harbor__memory_search`.

- characters outside `A-Za-z0-9_-` are replaced with `-`
- fragments that would start with a non-letter get a letter prefix, so numeric
  server keys such as `12306` become provider-safe tool prefixes
- server prefixes are capped at 30 characters
- full tool names are capped at 64 characters
- empty server names fall back to `mcp`
- colliding sanitized names are disambiguated with numeric suffixes
- final exposed tool order is deterministic by safe name to keep repeated Pi
  turns cache-stable
- profile filtering treats all tools from one bundle MCP server as plugin-owned
  by `bundle-mcp`, so profile allowlists and deny lists can include either
  individual exposed tool names or the `bundle-mcp` plugin key

#### Embedded Pi settings

- Claude `settings.json` is imported as default embedded Pi settings when the
  bundle is enabled
- Klaw sanitizes shell override keys before applying them

Sanitized keys:

- `shellPath`
- `shellCommandPrefix`

#### Embedded Pi LSP

- enabled Claude bundles can contribute LSP server config
- Klaw loads `.lsp.json` plus any manifest-declared `lspServers` paths
- bundle LSP config is merged into the effective embedded Pi LSP defaults
- only supported stdio-backed LSP servers are runnable today; unsupported
  transports still show up in `klaw plugins inspect <id>`

### Detected but not executed

These are recognized and shown in diagnostics, but Klaw does not run them:

- Claude `agents`, `hooks.json` automation, `outputStyles`
- Cursor `.cursor/agents`, `.cursor/hooks.json`, `.cursor/rules`
- Codex inline/app metadata beyond capability reporting

## Bundle formats

<AccordionGroup>
  <Accordion title="Codex bundles">
    Markers: `.codex-plugin/plugin.json`

    Optional content: `skills/`, `hooks/`, `.mcp.json`, `.app.json`

    Codex bundles fit Klaw best when they use skill roots and Klaw-style
    hook-pack directories (`HOOK.md` + `handler.ts`).

  </Accordion>

  <Accordion title="Claude bundles">
    Two detection modes:

    - **Manifest-based:** `.claude-plugin/plugin.json`
    - **Manifestless:** default Claude layout (`skills/`, `commands/`, `agents/`, `hooks/`, `.mcp.json`, `.lsp.json`, `settings.json`)

    Claude-specific behavior:

    - `commands/` is treated as skill content
    - `settings.json` is imported into embedded Pi settings (shell override keys are sanitized)
    - `.mcp.json` exposes supported stdio tools to embedded Pi
    - `.lsp.json` plus manifest-declared `lspServers` paths load into embedded Pi LSP defaults
    - `hooks/hooks.json` is detected but not executed
    - Custom component paths in the manifest are additive (they extend defaults, not replace them)

  </Accordion>

  <Accordion title="Cursor bundles">
    Markers: `.cursor-plugin/plugin.json`

    Optional content: `skills/`, `.cursor/commands/`, `.cursor/agents/`, `.cursor/rules/`, `.cursor/hooks.json`, `.mcp.json`

    - `.cursor/commands/` is treated as skill content
    - `.cursor/rules/`, `.cursor/agents/`, and `.cursor/hooks.json` are detect-only

  </Accordion>
</AccordionGroup>

## Detection precedence

Klaw checks for native plugin format first:

1. `klaw.plugin.json` or valid `package.json` with `klaw.extensions` — treated as **native plugin**
2. Bundle markers (`.codex-plugin/`, `.claude-plugin/`, or default Claude/Cursor layout) — treated as **bundle**

If a directory contains both, Klaw uses the native path. This prevents
dual-format packages from being partially installed as bundles.

## Runtime dependencies and cleanup

- Third-party compatible bundles do not get startup `npm install` repair. They
  should be installed through `klaw plugins install` and ship everything
  they need in the installed plugin directory.
- Klaw-owned bundled plugins are either shipped lightweight in core or
  downloadable through the plugin installer. Gateway startup never runs a
  package manager for them.
- `klaw doctor --fix` removes legacy staged dependency directories and can
  recover downloadable plugins that are missing from the local plugin index when
  config references them.

## Security

Bundles have a narrower trust boundary than native plugins:

- Klaw does **not** load arbitrary bundle runtime modules in-process
- Skills and hook-pack paths must stay inside the plugin root (boundary-checked)
- Settings files are read with the same boundary checks
- Supported stdio MCP servers may be launched as subprocesses

This makes bundles safer by default, but you should still treat third-party
bundles as trusted content for the features they do expose.

## Troubleshooting

<AccordionGroup>
  <Accordion title="Bundle is detected but capabilities do not run">
    Run `klaw plugins inspect <id>`. If a capability is listed but marked as
    not wired, that is a product limit — not a broken install.
  </Accordion>

  <Accordion title="Claude command files do not appear">
    Make sure the bundle is enabled and the markdown files are inside a detected
    `commands/` or `skills/` root.
  </Accordion>

  <Accordion title="Claude settings do not apply">
    Only embedded Pi settings from `settings.json` are supported. Klaw does
    not treat bundle settings as raw config patches.
  </Accordion>

  <Accordion title="Claude hooks do not execute">
    `hooks/hooks.json` is detect-only. If you need runnable hooks, use the
    Klaw hook-pack layout or ship a native plugin.
  </Accordion>
</AccordionGroup>

## Related

- [Install and Configure Plugins](/tools/plugin)
- [Building Plugins](/plugins/building-plugins) — create a native plugin
- [Plugin Manifest](/plugins/manifest) — native manifest schema