Aichat MCP server
{
"mcpServers": {
"acedatacloud-aichat": {
"command": "uvx",
"args": [
"mcp-aichat"
],
"env": {
"ACEDATACLOUD_API_TOKEN": "<acedatacloud_api_token>"
}
}
}
}{
"mcpServers": {
"acedatacloud-aichat": {
"command": "uvx",
"args": [
"mcp-aichat"
],
"env": {
"ACEDATACLOUD_API_TOKEN": "<acedatacloud_api_token>"
}
}
}
}{
"mcpServers": {
"acedatacloud-aichat": {
"command": "uvx",
"args": [
"mcp-aichat"
],
"env": {
"ACEDATACLOUD_API_TOKEN": "<acedatacloud_api_token>"
}
}
}
}{
"servers": {
"acedatacloud-aichat": {
"command": "uvx",
"args": [
"mcp-aichat"
],
"env": {
"ACEDATACLOUD_API_TOKEN": "${input:acedatacloud_api_token}"
}
}
},
"inputs": [
{
"id": "acedatacloud_api_token",
"type": "promptString",
"description": "Acedatacloud api token",
"password": true
}
]
}{
"mcpServers": {
"acedatacloud-aichat": {
"command": "uvx",
"args": [
"mcp-aichat"
],
"env": {
"ACEDATACLOUD_API_TOKEN": "<acedatacloud_api_token>"
}
}
}
}file .mcp.json (in your project root)file claude_desktop_config.jsonfile ~/.cursor/mcp.jsonfile .vscode/mcp.jsonfile ~/.codeium/windsurf/mcp_config.jsoninstall uvx mcp-aichatversion 2026.9.6.1
What it does
MCP server that enables AI dialogue through the AceDataCloud platform, supporting multiple LLM models including GPT-4/5, o-series, DeepSeek, Grok, and GLM. Designed for developers who need to integrate diverse language models into their applications.
- Create and manage multi-turn conversations with different AI models by selecting from a supported model list.
- Query an external LLM service without hosting your own models, using your AceDataCloud API token.
- Include external references in AI requests to get context-aware responses from various language model providers.
Tools this server exposes
| Tool | Does |
|---|---|
| aichat_create_conversation | Create an AI conversation with any supported model. |
| aichat_create_conversation_v2 | Create and manage conversations via the v2 API endpoint. |
| aichat_list_models | List all available AI models accessible through AceDataCloud. |
| aichat_get_usage_guide | Get the API usage guide for the AiChat service. |
Before you enable it
An MCP server runs with whatever access you give it. Start with a development account rather than production, and check which tools the server exposes before you let an agent call them unattended.