About System Control
System Control is an MCP server published by rainu in the Developer Tools category: mCP-Server which provide tools to control you system.
The repository has 1 stars and 0 forks, with the last commit 8 months ago. Six months or more without a commit doesn't mean the server is broken, but check the open issues before depending on it in production.
Install
git clone https://github.com/rainu/mcp-system-controlThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Ask AI
Ask AI about System Control
Powered by Claude · Grounded in docs
Security checks
Static checks derived from the repository 5 days ago. Heuristics on the source, not an audit.
- ✓README presentThe repository ships documentation.
- ✓License declaredUsable under a stated license.
- ✓Tests presentA test suite exists in the repository.
- ✓Dependencies pinnedA lockfile pins dependency versions.
- !No dynamic code executionSource scan found eval or shell execution. Review how tool inputs reach it before granting credentials.
- !Scoped permissionsDoesn't declare a permission scope. Assume it can do anything its process can.
Releases
README
mcp-system-control
This is an MCP-Server which allows a LLM to control the system. It provides many tools which can be used by the LLM to control the system.
For example:
- executing commands on the system
- file system access
- get system information
Each tool can be disabled. It is also possible to define your own custom tools which can be used by the LLM. Each tool call can also be protected by a user approval. So before a tool is executed, the user will be asked if they want to execute the tool call. This can be useful to prevent accidental tool calls which can be harmful for the system.
Usage
The MCP-Server can be started in tree different modes:
As stdio
mcp-system-control
As SSE serer
mcp-system-control --mcp.sse.bindAddress=":8080"
As Streamable server
mcp-system-control --mcp.streamable.bindAddress=":8080"
Test
To test the server, you can use the following command:
npx @modelcontextprotocol/inspector
User approval
All tools can be protected by a user approval. If a tool is protected by a user approval, the user will be asked if they want to execute the tool call. For asking a user, system tools are used. The server will try if one of these tools are available and use the first one which is available:
If no system tool is available, the tool call will be rejected and an error will be returned to the LLM.
README fetched from the repository 5 days ago. The original is authoritative.