> ## Documentation Index > Fetch the complete documentation index at: https://docs.yambr.com/llms.txt > Use this file to discover all available pages before exploring further. # API reference > MCP over Streamable HTTP — endpoints, headers, tools, and dynamic configuration endpoints. The Computer Use Server speaks standard [MCP (Model Context Protocol)](https://modelcontextprotocol.io/) over **Streamable HTTP**. Any MCP-compatible client can connect. Registered in the [MCP Registry](https://github.com/modelcontextprotocol/registry) as `io.github.yambr/open-computer-use`. ## Endpoint **Managed Yambr:** `https://api.yambr.com/mcp/computer_use` — auth with your Yambr API key as `Authorization: Bearer sk-yambr-...`. Get keys at [app.yambr.com](https://app.yambr.com/). Yambr exposes MCP only; your LLM traffic goes to your own provider — see [Access model](/platform/access-model). **Self-hosted:** `http://localhost:8081/mcp` ## Authentication Set the `MCP_API_KEY` environment variable on the server and pass as a Bearer token: ``` Authorization: Bearer ``` Leave `MCP_API_KEY` empty for local dev (no auth). ## Required headers **`X-Chat-Id` is mandatory.** Without it (and with `SINGLE_USER_MODE=false`), the server returns an error. Every request must include a unique session identifier. | Header | Purpose | Required | | ---------------- | ------------------------------------------------------------------ | ----------------------- | | `X-Chat-Id` | Session identifier — one sandbox container per id | Yes | | `Authorization` | `Bearer ` | If `MCP_API_KEY` is set | | `X-User-Email` | User email (per-user skills, PAT lookup, logging) | No | | `X-User-Name` | Display name (URL-encoded) | No | | `X-MCP-Servers` | Comma-separated MCP server names for the Claude Code sub-agent | No | | `Mcp-Session-Id` | Session id from `initialize` response; include on subsequent calls | After initialize | ## Session isolation modes Controlled by `SINGLE_USER_MODE`: | Mode | `X-Chat-Id` | Behavior | | ------- | ----------- | -------------------------------------------------------------------- | | *unset* | Yes | Isolated container per chat id | | *unset* | No | Shared `default` container + warning appended to every tool response | | `true` | *any* | Always one `default` container; header ignored | | `false` | Yes | Strict: isolated container per chat id | | `false` | No | **Rejected** with error | See [MCP methods](/api-reference/mcp/initialize) for request examples. ## Available tools | Tool | Description | | ------------- | ---------------------------------------------------------- | | `bash_tool` | Execute bash commands in the sandbox with streaming output | | `view` | View files and directories with line numbers | | `create_file` | Create files (auto-creates parent directories) | | `str_replace` | Edit files via find-and-replace with uniqueness validation | | `sub_agent` | Delegate to an autonomous Claude Code agent | Full signatures: [tools/list](/api-reference/mcp/tools-list) · [tools/call](/api-reference/mcp/tools-call). ## Native MCP primitives beyond tools Three more native primitives, all scoped by `X-Chat-Id`: | Primitive | What you get | How | | ----------------------------------- | ------------------------------------------------------------------ | -------------------------------------------------------------------------------------- | | `InitializeResult.instructions` | The per-chat system prompt as a string, delivered in the handshake | Dynamic — re-rendered each stateless request from `X-Chat-Id` / `X-User-Email` headers | | `resources/list` + `resources/read` | Uploaded files as `file://uploads/{chat_id}/{encoded-rel-path}` | Auto-registered on container create + on every `POST /api/uploads` | In addition, `/home/assistant/README.md` inside the sandbox carries the same prompt text — any model that runs `view` can recover its environment even if the client stripped every MCP handshake field. Full map: [system prompt reference](/reference/system-prompt). The server intentionally does **not** expose the system prompt via `prompts/get`. MCP `prompts/*` is user-controlled (slash commands) and `PromptMessage.role` is restricted to `user | assistant` — duplicating `InitializeResult.instructions` there would be off-spec. ## Dynamic configuration endpoints Non-MCP HTTP endpoints that MCP clients should use instead of hardcoding: | Endpoint | Returns | | ----------------------------------------------- | ------------------------------------------------------ | | `GET /system-prompt?chat_id=...&user_email=...` | Full per-session system prompt (plain text) | | `GET /skill-list?user_email=...` | Skills list for sub-agent prompts | | `GET /mcp-info` | Available tools, required headers, endpoint URL (JSON) | ## Browser endpoint (CDP) ``` GET /browser/{chat_id}/status GET /browser/{chat_id}/json WS /browser/{chat_id}/devtools/page/{page_id} ``` See [Live browser](/features/browser). ## Terminal endpoint ``` GET /terminal/{chat_id}/status POST /terminal/{chat_id}/start-ttyd WS /terminal/{chat_id}/ws ``` See [Terminal tab](/features/terminal). ## File endpoint ``` GET /files/{chat_id}/{path} GET /preview/{chat_id}/{path} GET /files/{chat_id}/archive # zip of everything in this chat ``` See [File preview](/features/file-preview) and [cu.yambr.com](/platform/cu-endpoint). ## Per-method details Open a session and get `Mcp-Session-Id`. Enumerate available tools. Invoke a tool. Browse uploaded files.