Jotsu MCP

Name: Jotsu MCP
Author: getjotsu

@getjotsu

About Jotsu MCP

Workflow engine for executing Model Context Protocol (MCP) workflows. It provides a lightweight runtime for running AI-powered tasks across MCP-compatible servers with built-in support for authentication, resources, and tools. This package powers the Jotsu platform but can also b

#mcp #mcp-server #mcp-client

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "jotsu-mcp": {
      "command": "uv",
      "args": [
        "venv"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Jotsu MCP?

Jotsu MCP is a general‑purpose Python library for implementing the Model Context Protocol (MCP) and creating workflows that use MCP tools, resources, and prompts. It is intended for developers who want to build and run MCP‑based workflows, especially with models that do not natively support MCP.

How to use Jotsu MCP?

Install the package with pip install jotsu-mcp[cli]. Use the CLI command jotsu-mcp workflow init to create a workflow.json file, then run it with jotsu-mcp workflow run ./workflow.json. Workflows are defined as JSON and can connect to MCP servers to call tools.

Key features of Jotsu MCP

Implement MCP and create MCP workflows.
Call tools from MCP servers in workflows.
Use MCP with models other than Claude.
CLI for init and run commands.
Workflows defined in portable JSON format.
Support for generic, application‑specific nodes.

Use cases of Jotsu MCP

Build and run a workflow that calls a tool from a public MCP server.
Integrate MCP tools into applications that do not yet support MCP natively.
Debug or inspect MCP workflow outputs using generic output nodes.
Chain multiple MCP server calls in a single workflow.

FAQ from Jotsu MCP

How do I install Jotsu MCP?

Run pip install jotsu-mcp[cli] to install the package including the CLI.

What file format does the workflow use?

Workflows are defined in a JSON file, by default named workflow.json.

Are there constraints on server IDs?

Yes, server IDs may only contain lowercase letters, numbers, :, _, or -.

Does the example Hello World server require authentication?

No, the publicly available Hello World server has no authentication.

Where does the workflow output appear?

When running a workflow, output consists of three messages: workflow start, node message, and workflow end. The final result appears in the result field of the workflow‑end node.