AI agents call github.branches to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns information about git repository branches without modifying any data, executing code, or triggering external operations. It is purely informational, making it a Read category tool with low severity due to the non-sensitive nature of publicly retrievable repository metadata.
From the tool's definition Tool description states 'Branches of a repository: name, head commit sha, and protection flag. Read-only; no caller key needed.' The 'read-only' designation and retrieval of repository metadata (branch names, commit SHAs, protection status) confirm this is a…
Attacks that exploit this kind of access
Branches of a repository: name, head commit sha, and protection flag. Read-only; no caller key needed. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for github.branches: 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 Mcp. Nothing to install.
github.branches is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the github.branches 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.branches. 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.branches is provided by the MCP server (@2sio/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 →