A
licenseNot graded
qualityA
maintenanceEnables AI agents to manage system updates, application installations, and remote host orchestration through MCP tools.
3
MIT
VLA-Diff-MCP
by zhywwyzh
Provides tools for querying ROS topic status, echoing recent topic messages, and reading ROS-related logs from a Docker container, enabling monitoring of ROS navigation and scene graph operations.
Provides tools for listing tmux sessions, capturing pane output, and sending commands to tmux sessions (creating them if needed), enabling monitoring and control of terminal-based processes.
Click on "Install 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., "@VLA-Diff-MCPWhat's the current frequency and latest message on /agent_prompt?"
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.
VLA-Diff-MCP
VLA-Diff project operations MCP server (Phase 1 read-only + Phase 2 write operations).
Features
Provide stable tools to the Agent via the MCP protocol, replacing ad-hoc bash commands each time:
Phase 1: Read-only tools
Tool | Description | Run location |
| Query ROS topic frequency + latest message | Container |
| Read the latest n messages from a ROS topic | Container |
| Query key service process status | Host |
| List tmux sessions | Host |
| Capture tmux session pane output | Host |
| Read agent_run / scene_graph logs | Container |
Phase 2: Write operation tools
Tool | Description | Safety mechanism |
| Publish fake instructions to /agent_prompt (task_id: 0=VLA/1=TRACKING/2=other) | None (simulates LLM messages) |
| Send commands to a tmux session (auto-create if it does not exist, no kill-session) | None (operates per reuse rules) |
| Restart ego_planner etc. (kill first then start, run in background) | confirm=True explicit confirmation |
| Fallback for arbitrary shell commands in the container | No whitelist, use with caution |
Related MCP server: WEATHGARDS
Environment preparation
# 创建虚拟环境（名称固定为 vla_diff_mcp_venv，已被 .gitignore 忽略）
uv venv vla_diff_mcp_venv
# 安装依赖（mcp SDK）
UV_PROJECT_ENVIRONMENT=vla_diff_mcp_venv uv syncRunning
vla_diff_mcp_venv/bin/python server.pyDefault stdio transport, launched as a subprocess by the MCP client (opencode / Claude Code).
Prerequisites
Docker container
ros_noetic_uss_navalready created (ROS-related tools depend on it)If not started, ROS tools return clear errors; tmux / process tools are unaffected
Extension directions
More restartable services: elastic-tracker, tracking_service etc. (add to
KNOWN_RESTARTas needed)Service configuration: migrate startup commands to YAML to avoid hardcoding them in code
This server cannot be installed
Maintenance
ActivityMaintained
ResponsivenessNo issues
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Your org's AI agents, tasks, runs, search, and brain files as MCP tools and resources.
Read-only MCP tools for AI agent discovery, structured resources, and NIULAI information.
The OpenRouter for tools. One MCP connection gives any AI agent 254 hosted tools, pay per call.
A registry of AI agent tools — MCP servers, APIs, CLIs, SDKs — kept current by automated ingestion.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceExposes MCP tools that enable remote LLMs to query local Docker containers, OS processes, and system services in real time.-
- FlicenseNot gradedqualityDmaintenanceEnables AI agents and users to manage workspace files, monitor system metrics, take persistent notes, and retrieve weather data via MCP tools and resources.-
- AlicenseNot gradedqualityBmaintenanceMCP server for AI agents to inspect and control ROS2 graphs, enabling topic listing, node info, service calls, parameter management, and pub/echo without manual ROS2 CLI usage.11MIT