# MCP AiChat Server

<!-- mcp-name: io.github.AceDataCloud/mcp-aichat -->

A Model Context Protocol (MCP) server for AI dialogue via the AceDataCloud platform.
Supports a wide range of models including GPT-4/5, o-series, DeepSeek, Grok, and GLM.

## Ace Data Cloud in goose

[Named provider preset and upstream acceptance status](goose/README.md). This independently installed preset is not an official built-in provider.

## Features

- **Multi-model support**: GPT-4.1, GPT-4o, GPT-5, o1, o3, o4-mini, DeepSeek, Grok, GLM, and more
- **Multi-turn conversations**: Continue conversations using conversation IDs
- **Stateful mode**: Optional server-side conversation state management
- **Reference sources**: Include external references for context-aware responses

## Connect: hosted OAuth, API token, or local stdio

The hosted endpoint is `https://aichat.mcp.acedata.cloud/mcp`. Choose one route for the MCP client:

| Route | When to use it | Credential setup |
|---|---|---|
| Hosted OAuth | The client supports remote MCP OAuth | Add only the URL, then sign in to AceDataCloud and approve access. No token needs to be pasted into client configuration. |
| Hosted API token | The client cannot finish OAuth, or you need an explicit integration credential | Send an AceDataCloud API token in the `Authorization: Bearer …` header. Keep it in a local secret store or environment variable. |
| Local stdio | The client runs a local MCP process | Install `mcp-aichat` and pass `ACEDATACLOUD_API_TOKEN` to that process. It still calls the AceDataCloud API. |

The hosted service advertises OAuth metadata and Dynamic Client Registration (DCR). **DCR registers the client application; it is not an API key.** OAuth signs you in and the client sends the resulting Bearer token; it may reuse or create an API credential for the account. Browser sign-in still requires an AceDataCloud account. The hosted service can be metered: review [current service documentation](https://platform.acedata.cloud/documents/aichat?utm_source=github&utm_medium=referral&utm_campaign=evergreen&utm_content=aichat_mcp_readme_quick_start) and displayed pricing before a real operation. Do not configure both an OAuth login and a fixed `Authorization` header for the same server.

### Hosted OAuth examples

- **Claude and Claude Desktop chat:** Add a remote custom connector in `Customize → Connectors → Add custom connector`, enter `https://aichat.mcp.acedata.cloud/mcp`, select sign-in, and choose **Register automatically** if Claude asks how to register its OAuth client. Complete consent. Claude Desktop's local `claude_desktop_config.json` is a separate setup. [Claude connector guide](https://support.claude.com/en/articles/11175166-get-started-with-custom-connectors-using-remote-mcp).
- **Claude Code:** `claude mcp add --transport http --scope user aichat https://aichat.mcp.acedata.cloud/mcp`, then `claude mcp login aichat`. Check `/mcp`. [Claude Code MCP guide](https://code.claude.com/docs/en/mcp).
- **Cursor:** Add a remote server with only `https://aichat.mcp.acedata.cloud/mcp`. For a project, merge the entry below into `<project>/.cursor/mcp.json`; for personal use, use `~/.cursor/mcp.json`. [Cursor MCP guide](https://cursor.com/docs/mcp).
- **VS Code / Copilot:** Run **MCP: Add Server**, select HTTP, enter `https://aichat.mcp.acedata.cloud/mcp`, then finish the browser sign-in. New portable workspace configs use `<project>/.mcp.json`; the VS Code-specific format below uses `<project>/.vscode/mcp.json` or the user profile. Check **MCP: List Servers**. [VS Code MCP setup](https://code.visualstudio.com/docs/agent-customization/mcp-servers).
- **Codex:** `codex mcp add aichat --url https://aichat.mcp.acedata.cloud/mcp`, then `codex mcp login aichat`. Its user settings are in `~/.codex/config.toml`. [Official Codex MCP guide](https://developers.openai.com/codex/mcp/).

Cursor project config (OAuth):

```json
{
  "mcpServers": {
    "aichat": {"url": "https://aichat.mcp.acedata.cloud/mcp"}
  }
}
```

VS Code-specific workspace config (OAuth):

```json
{
  "servers": {
    "aichat": {"type": "http", "url": "https://aichat.mcp.acedata.cloud/mcp"}
  }
}
```

### Hosted API token

<!-- BEGIN TOKEN ONBOARDING -->
1. Open [Ace Data Cloud → Applications](https://platform.acedata.cloud/console/applications?utm_source=github&utm_medium=referral&utm_campaign=evergreen&utm_content=aichat_mcp_readme_api_key). Sign in, or register an account first.
2. Find **General application**. If it has not been created, choose **Initialize General Application**. A general key can use the services available to your account; a dedicated application's key is limited to its service. Check the required service/model access and [current pricing](https://platform.acedata.cloud/models?utm_source=github&utm_medium=referral&utm_campaign=evergreen&utm_content=aichat_mcp_readme_models).
3. Copy the **API Key** from the application card, or open **Keys / Manage Keys → Create** to create a separate key for this integration. Give it a recognizable name so you can revoke or rotate it independently.
4. When creating a key, review **Expiration Time**, **Set Usage Limitation**, and **Allowed APIs**. Enable only the restrictions you need, allow the operations you will call, then click **Create** and copy the token from the key list. Task lookup does not grant permission to submit a generation. Confirm the application's balance can cover your first request; any trial allowance is whatever your account currently displays.
5. Copy only the token value, without quotation marks, spaces, or `Bearer `. An API Key / API Token field expects this raw value; only a manually configured HTTP `Authorization` header needs the `Bearer ` prefix. A `platform-...` account-management token cannot replace a generation API key.

![Copy an application API key or open Manage Keys](https://raw.githubusercontent.com/AceDataCloud/NanoBananaDify/2522b2f57210597af2db866445319334a1677a23/_assets/tutorial/get-api-key-en.png)

![Create a separately named key with optional restrictions](https://raw.githubusercontent.com/AceDataCloud/NanoBananaDify/2522b2f57210597af2db866445319334a1677a23/_assets/tutorial/create-api-key-en.png)

Save the key in the client's credential store or the environment variable shown below. Never put it in a prompt, shared workflow, screenshot, or Git commit. If authentication fails, check the full copied value, application/service access, expiration, usage limit, and balance before creating another key.
<!-- END TOKEN ONBOARDING -->

A fixed Bearer header bypasses OAuth. If the header is invalid, remove it before trying browser sign-in; keep the saved credential private.

For Claude Code, the shell expands the token when you add the server; treat the saved user MCP config as a secret:

```bash
export ACEDATACLOUD_API_TOKEN='YOUR_API_TOKEN'
claude mcp add --transport http --scope user aichat https://aichat.mcp.acedata.cloud/mcp \
  --header "Authorization: Bearer $ACEDATACLOUD_API_TOKEN"
```

For a Claude Code project config, put a variable reference in `<project>/.mcp.json` and set that variable in the environment that launches Claude Code:

```json
{
  "mcpServers": {
    "aichat": {
      "type": "http",
      "url": "https://aichat.mcp.acedata.cloud/mcp",
      "headers": {"Authorization": "Bearer ${ACEDATACLOUD_API_TOKEN}"}
    }
  }
}
```

Cursor uses a different environment-variable syntax in `~/.cursor/mcp.json` or an uncommitted project config:

```json
{
  "mcpServers": {
    "aichat": {
      "url": "https://aichat.mcp.acedata.cloud/mcp",
      "headers": {"Authorization": "Bearer ${env:ACEDATACLOUD_API_TOKEN}"}
    }
  }
}
```

In VS Code, run **MCP: Open User Configuration** and merge this server plus its masked input; `${input:...}` is for VS Code's user/workspace format and is not portable to the Agent Host `.mcp.json` format:

```json
{
  "inputs": [
    {"id": "acedata-aichat-token", "type": "promptString", "description": "AceDataCloud API token", "password": true}
  ],
  "servers": {
    "aichat": {
      "type": "http",
      "url": "https://aichat.mcp.acedata.cloud/mcp",
      "headers": {"Authorization": "Bearer ${input:acedata-aichat-token}"}
    }
  }
}
```

For **Cline**, use its MCP configuration UI or CLI file `~/.cline/data/settings/cline_mcp_settings.json`; its remote transport value is `streamableHttp`. For **JetBrains AI Assistant**, add a remote URL from **Settings → Tools → AI Assistant → Model Context Protocol (MCP)**. For **Zed**, use a `context_servers` entry with the URL only for OAuth or add a local Bearer header. These clients have different configuration schemas; follow their current UI rather than copying another client's JSON. [Cline](https://docs.cline.bot/mcp/mcp-overview) · [JetBrains](https://www.jetbrains.com/help/ai-assistant/mcp.html) · [Zed](https://zed.dev/docs/ai/mcp).

### Local stdio

Install the package and give the local process an API token:

```bash
python -m pip install mcp-aichat
export ACEDATACLOUD_API_TOKEN='YOUR_API_TOKEN'
mcp-aichat
```

For Claude Desktop local MCP, merge this entry into the file opened by its developer settings (`~/Library/Application Support/Claude/claude_desktop_config.json` on macOS). `uvx` requires [uv](https://docs.astral.sh/uv/) on `PATH`:

```json
{
  "mcpServers": {
    "aichat": {
      "command": "uvx",
      "args": ["mcp-aichat"],
      "env": {"ACEDATACLOUD_API_TOKEN": "YOUR_API_TOKEN"}
    }
  }
}
```

Keep this user-level file private. Self-hosted HTTP uses `mcp-aichat --transport http --port 8000`; expose it only with suitable network and TLS controls. Local execution still calls the AceDataCloud API.

### Check before using the service

1. `https://aichat.mcp.acedata.cloud/health` returning `{"status":"ok"}` checks endpoint reachability only.
2. Confirm that the MCP client loads tools. `aichat_list_models` is a reference tool; it does not verify downstream API access or balance.
3. If you need a full API check, call `aichat_create_conversation` with your own valid input after reviewing [current service documentation](https://platform.acedata.cloud/documents/aichat?utm_source=github&utm_medium=referral&utm_campaign=evergreen&utm_content=aichat_mcp_readme_quick_start) and displayed pricing.

For **401**, check which auth route the client used and whether the token or OAuth session is valid. A **403** may mean an account permission or content moderation failure; read the returned error. Insufficient balance and downstream service failures need their own diagnosis. A listed tool or submitted task does not prove a successful result.

## Available Tools

| Tool | Description |
|------|-------------|
| `aichat_create_conversation` | Create an AI conversation with any supported model |
| `aichat_create_conversation_v2` | Create/manage conversations via `/aichat2/conversations` |
| `aichat_list_models` | List all available AI models |
| `aichat_get_usage_guide` | Get API usage guide |

### AiChat v2 agent iterations

`aichat_create_conversation_v2` accepts `max_turns` from 1 to 500. Omit it to use
the Backend default of 500. This limits agent iterations for one request, not
conversation-history length; `max_turns=1` prevents tool calls. Each model call
is billed by actual usage, and execution may end earlier due to timeouts,
authorization or other execution conditions.

## Supported Models

### OpenAI
- GPT-5.6 Sol Fast: `gpt-5.6-sol-fast`, supported by both `aichat_create_conversation` and `aichat_create_conversation_v2`. Existing defaults are unchanged.
- GPT-5 series: gpt-5.5, gpt-5.4, gpt-5.2, gpt-5.1, gpt-5, gpt-5-mini, gpt-5-nano
- GPT-4.1 series: gpt-4.1, gpt-4.1-mini, gpt-4.1-nano
- GPT-4o series: gpt-4o, gpt-4o-mini, gpt-4o-all, gpt-4o-image
- GPT-4 series: gpt-4, gpt-4-turbo, gpt-4-vision-preview
- o-series: o1, o1-mini, o1-pro, o3, o3-mini, o3-pro, o4-mini

### DeepSeek
- deepseek-r1, deepseek-r1-0528, deepseek-v3, deepseek-v3-250324, deepseek-v4-flash, deepseek-v4-pro

### xAI
- grok-3

### Zhipu AI
- glm-5.1, glm-4.7, glm-4.6, glm-3-turbo

### Google Gemini (AiChat v2 only)

Use `aichat_create_conversation_v2` with `model="gemini-4-argon"` for Gemini 4
Argon. It is not available through the v1 tool; the default remains `gpt-4.1`.

```json
{"model":"gemini-4-argon","question":"Review this code and identify its key risks."}
```

Pass these arguments to `aichat_create_conversation_v2`. This uses
`/aichat2/conversations`, not native Gemini Generate Content or Google
Interactions. The MCP tool does not expose `max_tokens`, thinking-level or
explicit-cache controls; native endpoint capabilities do not imply those controls
are available through this conversation wrapper.

### Kimi (AiChat v2 only)

Use `aichat_create_conversation_v2` with `model="kimi-k3.1-pro"` to use Kimi
K3.1 Pro. `kimi-k3` and existing v2 Kimi aliases remain supported; the default
model is still `gpt-4.1`. These models are not available through the v1 tool.

```json
{"model":"kimi-k3.1-pro","question":"Review this code and identify its key risks."}
```

Pass these arguments to `aichat_create_conversation_v2`. The tool calls
`/aichat2/conversations`, not `/kimi/chat/completions`, and does not expose the
latter endpoint's `reasoning_effort` control.

## Documentation

<!-- canonical-documentation -->
[Documentation](https://platform.acedata.cloud/documents/aichat?utm_source=github&utm_medium=referral&utm_campaign=evergreen&utm_content=aichat_mcp_readme_quick_start)

## License

MIT