vcs_commit
Commit the currently staged changes with a message. Reversible (git reset --soft HEAD~1) and loses nothing, so not gated. Errors clearly if nothing is staged. Commit signing is disabled for this call so it can never block on a passphrase prompt.
This record as markdown: /tools/breakpoint-mcp/vcs-commit.md
What vcs_commit does on Breakpoint
AI agents use vcs_commit to create or update resources in Breakpoint, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Breakpoint environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
message | string | Yes | Commit message |
Parameters from the server's own tool schema.
Why vcs_commit is rated Medium
This tool creates/modifies data (a git commit) but is explicitly reversible and does not destroy data, placing it in Write rather than Destructive. The medium severity reflects that while commits can be reset, they do represent a persistent state change that could introduce unwanted code into the repository if misused by an agent. The high confidence reflects clear documentation of the tool's reversible nature.
From the tool's definition 'Commit the currently staged changes with a message' — creates a permanent record in version control history. Description explicitly notes it is 'Reversible' via `git reset --soft HEAD~1`, confirming it does not irreversibly delete data.
Attacks that exploit this kind of access
The rule that runs vcs_commit safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Breakpoint, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For vcs_commit, this is the rule to start with:
vcs_commit 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 Breakpoint, apply this rule, and every vcs_commit call is checked against it from then on.
Questions about vcs_commit
Commit the currently staged changes with a message. Reversible (git reset --soft HEAD~1) and loses nothing, so not gated. Errors clearly if nothing is staged. Commit signing is disabled for this call so it can never block on a passphrase prompt. It is categorised as a Write tool in the Breakpoint MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
vcs_commit accepts 1 parameter: message. Required: message. The full parameter table on this page comes from the server's own tool schema.
Register the Breakpoint MCP server in PolicyLayer and add a rule for vcs_commit: 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 Breakpoint. Nothing to install.
vcs_commit 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 vcs_commit 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 vcs_commit. 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.
vcs_commit is provided by the Breakpoint MCP server (breakpoint-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Breakpoint, and thousands of servers like it.
This server
Across the catalogue