target
Target branch or commit to compare with (string, required)
This record as markdown: /tools/io-github-aifity-omnigit-mcp/target.md
What target does on GitHub
AI agents call target to retrieve information from GitHub without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why target is rated Low
This tool does not retrieve, create, modify, or delete data on its own; it is a configuration parameter used to designate which branch or commit to use in a comparison operation. It has no side effects and merely selects or references existing data. The most appropriate category is Read, as it contributes to a data retrieval context, with low severity due to its passive nature.
From the tool's definition Tool is named 'target' and described as 'Target branch or commit to compare with (string, required)' — this is a parameter that specifies comparison endpoints, not an action that performs operations.
Attacks that exploit this kind of access
The rule that runs target 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 target, this is the rule to start with:
target is read-only, so it stays allowed. 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 target call is checked against it from then on.
Questions about target
Target branch or commit to compare with (string, required). It is categorised as a Read tool in the GitHub MCP Server, which means it retrieves data without modifying state.
Register the GitHub MCP server in PolicyLayer and add a rule for target: 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.
target 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 target 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 target. 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.
target 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