Unichat MCP Server

Unichat MCP Server

Local serverstdioPython

What is the Unichat MCP server?

Most developer tooling work still happens through a UI a human drives. Unichat MCP server moves it into the conversation instead. Unichat MCP Server.

The short version

Send requests to OpenAI, MistralAI, Anthropic, xAI, Google AI or DeepSeek using MCP protocol via tool or predefined prompts. Vendor API key required.

Getting it running

@smithery/cli on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

The tools it exposes

The server publishes 4 tools. What each one is for:

  • unichat — Send a request to unichat
  • Tools — The server implements one tool: - unichat: Send a request to unichat - Takes "messages" as required string arguments - Returns a response
  • Prompts — The Prompts tool exposed by this server
  • Debugging — Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the [MCP

What it needs from you

Configuration is passed through the environment: UNICHAT_MODEL, UNICHAT_API_KEY, YOUR_VENDOR_API_KEY, YOUR_OPENAI_API_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

How it compares

Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Unichat's toolset — unichat, Tools, Prompts and 1 more — is a fair guide to whether it matches your workflow. It is maintained by GitHub Actions; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Available tools

ToolWhat it does
unichatSend a request to unichat
ToolsThe server implements one tool: - unichat: Send a request to unichat - Takes "messages" as required string arguments - Returns a response
PromptsThe Prompts tool exposed by this server.
DebuggingSince MCP servers communicate over stdio, debugging can be challenging. We recommend using the [MCP Inspector](https://github.com/modelcontextprotocol/inspector), which is available as a package script:

How to install the Unichat MCP server

Run published:
```json
{
  "mcpServers": {
    "unichat-ts-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "unichat-ts-mcp-server"
      ],
      "env": {
        "UNICHAT_MODEL": "YOUR_PREFERRED_MODEL_NAME",
        "UNICHAT_API_KEY": "YOUR_VENDOR_API_KEY"
      }
    }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
UNICHAT_MODELConfiguration value read at startup.Optional
UNICHAT_API_KEYCredential the server authenticates with.Yes
YOUR_VENDOR_API_KEYCredential the server authenticates with.Yes
YOUR_OPENAI_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Unichat to unichat.
  • Use Unichat to Tools.
  • Use Unichat to Prompts.

Frequently asked questions

It connects Unichat to MCP-compatible AI assistants such as Claude and Cursor, exposing 4 tools (unichat, Tools, Prompts, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Unichat directly.