AI agents use git_add to create or update resources in Context — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Context environment.
git_add stages changes for later commit but does not irreversibly delete data (would be Destructive) or execute arbitrary code (would be Execute). It's a Write operation because it modifies the repository state reversibly. The medium severity reflects that misuse could stage unintended files, potentially exposing secrets or committing unwanted changes—but the effects are recoverable.
From the tool's definition Tool name 'git_add' and description 'Stage files for commit' indicate the tool modifies Git's index/staging area, which is a reversible write operation (staging can be undone with git reset).
Attacks that exploit this kind of access
Stage files for commit. Pass paths:[. It is categorised as a Write tool in the Context MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Context MCP server in PolicyLayer and add a rule for git_add: 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 Context. Nothing to install.
git_add 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 git_add 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 git_add. 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.
git_add is provided by the Context MCP server (vibhasdutta/context-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →