Apply a unified diff to a GitHub branch by committing the changes via createCommitOnBranch.
AI agents use github_apply_patch to create or update resources in Promethean OS MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Promethean OS MCP environment.
This tool creates or modifies data (commits changes to a GitHub branch) but does not delete data or execute arbitrary code. It is reversible via standard Git operations (revert, reset). It is a Write operation rather than Execute because it commits a pre-determined patch rather than executing arbitrary code.
From the tool's definition Apply a unified diff to a GitHub branch by committing the changes via createCommitOnBranch. The tool creates commits and modifies repository state.
Attacks that exploit this kind of access
Apply a unified diff to a GitHub branch by committing the changes via createCommitOnBranch. It is categorised as a Write tool in the Promethean OS MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Promethean OS MCP server in PolicyLayer and add a rule for github_apply_patch: 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 Promethean OS MCP. Nothing to install.
github_apply_patch 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 github_apply_patch 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 github_apply_patch. 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.
github_apply_patch is provided by the Promethean OS MCP server (octave-commons/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 →