base_ref
Git reference (e.g., branch) that the agent will start its work from. If not specified, defaults to the repository's default branch (string, optional)
This record as markdown: /tools/io-github-aifity-omnigit-mcp/base-ref.md
What base_ref does on GitHub
AI agents call base_ref as a supporting operation in GitHub workflows.
Why base_ref is rated Low
The description reads as a parameter definition (specifying a base branch reference), not an actionable tool that performs reads, writes, executes, or destructive operations. It has no side effects on its own. Confidence is lowered because the description is ambiguous about whether this is truly a standalone tool or a parameter field.
From the tool's definition 'Git reference (e.g., branch) that the agent will start its work from' — this appears to be a parameter descriptor rather than an executable tool
Attacks that exploit this kind of access
The rule that runs base_ref 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 base_ref, this is the rule to start with:
base_ref gets a rate cap, and 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 base_ref call is checked against it from then on.
Questions about base_ref
Git reference (e.g., branch) that the agent will start its work from. If not specified, defaults to the repository's default branch (string, optional). It is categorised as a Other tool in the GitHub MCP Server, which means it performs auxiliary operations.
Register the GitHub MCP server in PolicyLayer and add a rule for base_ref: 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.
base_ref is a Other tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the base_ref 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 base_ref. 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.
base_ref is provided by the GitHub MCP server (oci:ghcr.io/aifity/omnigit-mcp:0.5.0). 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