---
title: "Deploy sokosumi-mcp"
description: "Deploy and Host sokosumi-mcp with Railway"
category: "AI/ML"
url: https://railway.com/deploy/sokosumi-mcp
---

# Deploy sokosumi-mcp

Deploy and Host sokosumi-mcp with Railway

**[Deploy sokosumi-mcp on Railway](https://railway.com/template/sokosumi-mcp)**

- **Creator:** Albina Nikiforova's Projects
- **Category:** AI/ML
- **Total deploys:** 1

## Template content

### Sokosumi-MCP

- **Source:** masumi-network/Sokosumi-MCP
- **Public domain:** Yes

## Documentation

# Deploy and Host sokosumi-mcp on Railway

Sokosumi-MCP is a Model Context Protocol (MCP) server that provides AI agents access to the Sokosumi platform. It enables remote interaction with AI agents, job creation, monitoring, and management through a standardized MCP interface with dual transport support.

## About Hosting sokosumi-mcp

Hosting sokosumi-mcp involves deploying a FastMCP server that bridges MCP clients (like Claude Desktop) with the Sokosumi AI agent platform. The server automatically handles API authentication via URL parameters, supports both mainnet and preprod environments, and provides six core tools for agent interaction. Railway deployment enables remote MCP access through HTTP transport, making it accessible to any MCP-compatible client without local configuration. The server includes middleware for parameter extraction, comprehensive error handling, and built-in logging for monitoring API interactions.

## Common Use Cases

- Connect Claude Desktop or other MCP clients to Sokosumi AI agents remotely
- Automate AI agent job creation and monitoring through standardized MCP tools
- Build custom applications that interact with Sokosumi agents via MCP protocol
- Provide team access to Sokosumi platform through a centralized MCP endpoint
- Integrate Sokosumi AI capabilities into existing MCP-compatible workflows

## Dependencies for sokosumi-mcp Hosting

- Python 3.8+ runtime environment
- Sokosumi platform API key (from [Account Settings](https://app.sokosumi.com/account))
- Public HTTP access for MCP client connections

### Deployment Dependencies

- [Sokosumi Platform Account](https://app.sokosumi.com) - Required for API access
- [Model Context Protocol Specification](https://modelcontextprotocol.io) - Protocol documentation
- [FastMCP Framework](https://github.com/jlowin/fastmcp) - Underlying MCP server framework

### Implementation Details

The server uses FastMCP with dual transport support:

```python
# Automatic transport selection based on PORT environment variable
port = os.environ.get("PORT")
if port:
    # HTTP transport for Railway deployment
    app = mcp.streamable_http_app()
    app.add_middleware(APIKeyExtractorMiddleware)
    uvicorn.run(app, host="0.0.0.0", port=int(port))
else:
    # STDIO transport for local development
    mcp.run()
```

API key extraction from URL parameters:
```python
# Middleware automatically extracts credentials
# Example: ?api_key=xxx&network=mainnet
api_key = request.query_params.get('api_key')
network = request.query_params.get('network', 'mainnet')
```

## Why Deploy sokosumi-mcp on Railway?


Railway is a singular platform to deploy your infrastructure stack. Railway will host your infrastructure so you don't have to deal with configuration, while allowing you to vertically and horizontally scale it.

By deploying sokosumi-mcp on Railway, you are one step closer to supporting a complete full-stack application with minimal burden. Host your servers, databases, AI agents, and more on Railway.


## Similar templates

- [Chat Chat](https://railway.com/deploy/-WWW5r) — Chat Chat, your own unified chat and search to AI platform.
- [stella](https://railway.com/deploy/stella) — Self-host stella with web, API, Postgres, Redis, and object storage.
- [Hermes Agent | OpenClaw Alternative with Dashboard](https://railway.com/deploy/hermes-agent-or-openclaw-alternative-wit) — Self-Hosted Hermes AI Agent for Telegram, Discord & Slack

Open this page in a browser: https://railway.com/deploy/sokosumi-mcp