Document new CLI commands: eval runs, chatboxes, chat-sessions

docs/cli/overview.mdx

@@ -41,7 +41,7 @@ npx -y @mcpjam/cli@latest --help
 | [`apps`](/cli/apps-conformance) | Validate MCP Apps metadata and resource wiring | `conformance`, `conformance-suite` |
 | [`compat`](/cli/reference#compat-command) | Check whether a server's tools and widgets work on each AI host | `compat` |
 | [`inspector`](/cli/reference#inspector-commands) | Start, open, or stop the local Inspector from the CLI | `open`, `start`, `stop` |
-| [`eval`](/cli/reference#eval-commands) | Author and run eval suites in your hosted MCPJam projects | `create`, `list`, `run`, `status` |
+| [`eval`](/cli/reference#eval-commands) | Author and run eval suites in your hosted MCPJam projects | `create`, `list`, `run`, `runs`, `status` |
 | [`tunnel`](/cli/reference#tunnel) | Expose a local MCP server through a public MCPJam tunnel URL, registered as a server in your project | `tunnel <url>`, `tunnel -- <command>` |
 | [`tools`](/cli/tools-resources-prompts) | Exercise the tool surface | `list`, `call` |
 | [`resources`](/cli/tools-resources-prompts) | Read resources and templates | `list`, `read`, `templates` |
@@ -50,6 +50,8 @@ npx -y @mcpjam/cli@latest --help
 | [`hosts`](/cli/reference#hosts-commands) | Manage hosts in your hosted MCPJam projects | `list`, `get`, `create`, `update`, `delete`, `templates` |
 | [`environments`](/cli/reference#environments-commands) | Manage project environments — the host + servers + pinned skills/plugins bundles eval suites and journeys run against | `list`, `get`, `resolve`, `create`, `update`, `archive`, `restore` |
 | [`images`](/cli/reference#images-commands) | Manage custom Computer sandbox images (blueprints) | `list`, `get`, `create`, `validate`, `edit`, `build`, `logs`, `use`, `reset`, `promote`, `delete` |
+| [`chatboxes`](/cli/reference#chatboxes-commands) | Inspect published chatboxes (read-only) | `list`, `get` |
+| [`chat-sessions`](/cli/reference#chat-sessions-commands) | Inspect saved chat sessions (read-only) | `list` |
 | [`mcp`](/cli/mcp-server) | Run MCPJam as a stdio MCP server for agents (Claude Desktop, Claude Code, Cursor, ...) | `mcp` |
 | [`telemetry`](/cli/telemetry) | Inspect and configure anonymous CLI telemetry | `status`, `disable`, `enable` |
 

docs/cli/reference.mdx

@@ -753,6 +753,59 @@ Permanently delete a sandbox image from a project.
 
 ---
 
+## `chatboxes` commands
+
+Inspect the chatboxes published from a hosted project. All `chatboxes` commands require an `sk_` API key (via `--api-key` or the `MCPJAM_API_KEY` environment variable) or a prior `mcpjam login`. Publishing, rotating a share link, and managing members are done in the app.
+
+### Shared platform flags
+
+| Flag | Description |
+|------|-------------|
+| `--api-key <key>` | MCPJam `sk_` API key (overrides `MCPJAM_API_KEY`) |
+| `--api-url <url>` | MCPJam API base URL (defaults to `https://app.mcpjam.com/api/v1`) |
+
+### `chatboxes list`
+
+List the chatboxes published from a project.
+
+| Flag | Required | Description |
+|------|----------|-------------|
+| `--project <id-or-name>` | No | Project name or ID (defaults to the most recently updated project) |
+
+### `chatboxes get`
+
+Show one chatbox: access mode, attached servers, share link.
+
+| Flag | Required | Description |
+|------|----------|-------------|
+| `--chatbox <id-or-name>` | Yes | Chatbox name or ID |
+| `--project <id-or-name>` | No | Project name or ID (defaults to the most recently updated project) |
+
+---
+
+## `chat-sessions` commands
+
+Inspect saved chat sessions. All `chat-sessions` commands require an `sk_` API key (via `--api-key` or the `MCPJAM_API_KEY` environment variable) or a prior `mcpjam login`.
+
+### Shared platform flags
+
+| Flag | Description |
+|------|-------------|
+| `--api-key <key>` | MCPJam `sk_` API key (overrides `MCPJAM_API_KEY`) |
+| `--api-url <url>` | MCPJam API base URL (defaults to `https://app.mcpjam.com/api/v1`) |
+
+### `chat-sessions list`
+
+List chat sessions, newest first.
+
+| Flag | Required | Description |
+|------|----------|-------------|
+| `--project <id-or-name>` | No | Restrict to one project |
+| `--status <status>` | No | Filter by session status |
+| `--limit <n>` | No | Maximum sessions to return (1–200) |
+
+---
+
 ## `inspector` commands
 
 ### `inspector open`
@@ -942,6 +995,16 @@ Get the status and summary of an eval run.
 | `--run <id>` | Yes | Eval run ID (from `eval run`) |
 | `--project <id-or-name>` | Yes | Project name or ID |
 
+### `eval runs`
+
+List a suite's run history, newest first.
+
+| Flag | Required | Description |
+|------|----------|-------------|
+| `--suite <id-or-name>` | Yes | Eval suite name or ID |
+| `--project <id-or-name>` | No | Project name or ID (defaults to the most recently updated project) |
+| `--limit <n>` | No | Maximum number of runs to return (1–100) |
+
 ### `eval iterations`
 
 List per-iteration results for an eval run (pass/fail, tool calls, tokens, latency). Results are paginated.