# MCP Aichat

> MCP Aichat is an MCP server for ai models and llm tooling. Chat with GPT, o-series, DeepSeek, Grok and GLM models through AceDataCloud. It can run locally on your machine or as a hosted remote server.

- **Kind:** MCP server
- **Platforms:** API, CLI
- **Website:** https://platform.acedata.cloud/documents/aichat
- **Repository:** https://github.com/acedatacloud/aichatmcp
- **MCP Registry name:** io.github.AceDataCloud/mcp-aichat
- **Categories:** [AI models and LLM tooling](https://ai-powered.com/categories/ai-and-llm)
- **Listing updated:** 2026-11-18

## About

Rather than wrapping one model, this server routes dialogue requests to a range of LLMs on the AceDataCloud platform. The README lists GPT-4.1, GPT-4o, GPT-5, o1, o3, o4-mini, DeepSeek, Grok and GLM, with multi-turn conversations continued by conversation ID, an optional server-side stateful mode and support for including reference sources.

There are three ways in: hosted OAuth at https://aichat.mcp.acedata.cloud/mcp, the hosted endpoint with an AceDataCloud API token in a Bearer header, or a local stdio install of the `mcp-aichat` PyPI package with ACEDATACLOUD_API_TOKEN set. All routes require an AceDataCloud account, and the README warns the hosted service can be metered.

Setup steps are given for Claude, Claude Code, Cursor, VS Code and Codex, and the README says not to combine an OAuth login with a fixed Authorization header.

## Features

- **Many models:** Reaches GPT, o-series, DeepSeek, Grok and GLM models.
- **Multi-turn chats:** Continue a conversation using its ID.
- **Stateful mode:** Optional server-side conversation state.
- **Reference sources:** Pass external references for context-aware replies.
- **Three connect routes:** Hosted OAuth, hosted API token or local stdio.
- **Wide client setup:** Documented for Claude, Cursor, VS Code and Codex.

## Good for

- Ask a second model for an opinion from inside an assistant
- Compare answers from different LLMs
- Keep a threaded conversation across calls
- Give a model reference text while asking
- Use one account for several model families

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http mcp-aichat https://aichat.mcp.acedata.cloud/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://aichat.mcp.acedata.cloud/mcp
```

### Cursor (~/.cursor/mcp.json)

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

### VS Code (.vscode/mcp.json)

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

### Windsurf (~/.codeium/windsurf/mcp_config.json)

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

### Other clients (your client's MCP settings (most use this shape))

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

## FAQ

### Which models are listed?

GPT-4.1, GPT-4o, GPT-5, o1, o3, o4-mini, DeepSeek, Grok and GLM.

### Do I need an account?

Yes, an AceDataCloud account or API token.

### Is it metered?

The README says the hosted service can be metered; check the displayed pricing.

### How do I install locally?

Install `mcp-aichat` and pass ACEDATACLOUD_API_TOKEN to the process.

### How do I add MCP Aichat to Claude Code?

Run this command in your terminal: claude mcp add --transport http mcp-aichat https://aichat.mcp.acedata.cloud/mcp

### What are the best alternatives to MCP Aichat?

The closest alternatives to MCP Aichat are headroom, omniget, next-ai-draw-io, mcp-for-blender and Claude Code Ultimate Guide.

## Where this comes from

- Description: written from the project's README and the project's website.
- Install steps: from the official MCP Registry entry.

## Alternatives

- [headroom](https://ai-powered.com/mcp/headroom-3): headroom is an open-source MCP server for ai models and llm tooling.
- [omniget](https://ai-powered.com/mcp/omniget): omniget is an open-source MCP server for ai models and llm tooling.
- [next-ai-draw-io](https://ai-powered.com/mcp/next-ai-draw-io-2): next-ai-draw-io is an open-source MCP server for ai models and llm tooling.
- [mcp-for-blender](https://ai-powered.com/mcp/mcp-for-blender): mcp-for-blender is an open-source MCP server for design and media.
- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.
- [unity-mcp](https://ai-powered.com/mcp/unity-mcp-2): unity-mcp is an open-source MCP server for ai models and llm tooling.
- [fastapi_mcp](https://ai-powered.com/mcp/fastapi-mcp): fastapi_mcp is an open-source MCP server for ai models and llm tooling.
- [tyk](https://ai-powered.com/mcp/tyk): tyk is an open-source MCP server for developer tools.

---
Source: https://ai-powered.com/mcp/mcp-aichat
