submodule
Manages git submodules. Supports list (default), add, update, sync, and deinit actions. List returns structured submodule data with path, SHA, branch, and status.
This record as markdown: /tools/io-github-dave-london-github/submodule.md
What submodule does on Github
AI agents use submodule to create or update resources in Github, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Github environment.
Why submodule is rated Medium
Submodule management is write-capable (modifies .gitmodules and repository configuration), but 'deinit' stops short of irreversible deletion of actual code. The 'list' action is read-only, but the tool enables write operations. Severity is medium because misuse could corrupt repository state or introduce unintended dependencies, but changes are typically reversible via git history.
From the tool's definition Tool description explicitly lists actions including 'add, update, sync, and deinit' — all operations that modify repository structure. 'Add' and 'update' create or modify submodule references; 'sync' and 'deinit' alter submodule state.
Attacks that exploit this kind of access
The rule that runs submodule safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Github, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For submodule, this is the rule to start with:
submodule stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Github, apply this rule, and every submodule call is checked against it from then on.
Questions about submodule
Manages git submodules. Supports list (default), add, update, sync, and deinit actions. List returns structured submodule data with path, SHA, branch, and status. It is categorised as a Write tool in the Github MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Github MCP server in PolicyLayer and add a rule for submodule: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Github. Nothing to install.
submodule is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the submodule rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for submodule. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
submodule is provided by the Github MCP server (@paretools/github). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Github, and thousands of servers like it.
This server
Across the catalogue