Spark Terminal MCP
Provides Git integration with tools for cloning repositories, checking status, committing, pushing, and pulling changes.
Provides compatibility with Google's Gemini Spark, allowing Spark to use the server's terminal tools such as command execution, file management, web requests, and system operations.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Spark Terminal MCPCheck disk space and show me the results"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Spark Terminal MCP
A Gemini Spark-compatible MCP server with 30+ terminal tools — deployed on Render.
What this is
Gemini Spark requires custom Connected Apps to expose a full OAuth 2.1 discovery chain before it will call any tools:
Spec | Endpoint | Purpose |
RFC 9728 |
| Discover which auth server protects the tools |
RFC 8414 |
| Find token/registration/authorize endpoints |
RFC 7591 |
| Dynamic Client Registration (auto-register) |
RFC 7636 |
| PKCE authorization-code flow |
This server implements all four, plus the Streamable HTTP MCP transport that Spark uses.
Related MCP server: cloudflare-mcp-dcr-bridge
Tools (30+)
Group | Tools |
Command Execution |
|
File Management |
|
Web & Internet |
|
Package & System |
|
Text Processing |
|
Git |
|
Archive |
|
Network |
|
System |
|
Downloads |
|
Deploy to Render
Fork / clone this repo
Go to render.com → New → Web Service
Connect this repo, select Docker runtime
Set env var
JWT_SIGNING_KEYto a random 64-char hex stringDeploy — get your
https://spark-terminal-mcp.onrender.comURL
Connect to Gemini Spark
Go to gemini.google.com
Switch to Spark mode
Settings & help → Connected Apps → Add a custom app
Enter your Render URL:
https://spark-terminal-mcp.onrender.comFollow OAuth flow — click Connect
Local dev
pip install -r requirements.txt
AUTH_BYPASS=true python3 server.py
# Server on http://localhost:8080
# MCP endpoint: http://localhost:8080/mcpEnvironment variables
Variable | Default | Description |
|
| HTTP port |
|
| Set |
| auto-generated | Secret for signing JWT tokens |
This server cannot be deployed
Maintenance
Related MCP Connectors
MCP server connecting AI agents to 100+ apps (Gmail, Slack, Notion, GitHub) via one-click OAuth.
Connect AI agents to Filepad workspaces through OAuth MCP.
Zero-setup MCP gateway securely connecting AI to your tools with authentication and workflows
Unified MCP Server is a remote MCP connector for AI agents and vertical AI products that provides access to 22,000+ authorized SaaS tools across 400+ integrations and 24 categories directly inside LLMs (Claude, GPT, Gemini, Cohere). Tools operate only on explicitly authorized customer connections, enabling agents to safely read and write against live third-party systems.
Related MCP Servers
- FlicenseNot gradedqualityAmaintenanceA local MCP server that enables Gemini Spark to safely access and work with files in a user-selected workspace via authenticated HTTPS tunnel, with sandboxing, policy enforcement, and audit logging.3-
- AlicenseNot gradedqualityCmaintenanceEnables Gemini Enterprise to connect to Cloudflare Zero Trust MCP server portals via Dynamic Client Registration (DCR) and OAuth 2.0 proxying. It proxies MCP JSON-RPC/SSE traffic with Cloudflare Access service token authentication.MIT
- AlicenseAqualityBmaintenanceEnables AI assistants to access and manage Google Drive, Sheets, Docs, Calendar, and Gmail through OAuth2-authenticated MCP tools.271MIT
- AlicenseNot gradedqualityBmaintenanceEnables remote MCP connections with Google OAuth authentication, allowing secure access to MCP tools and resources.1MIT