duplicate_of
Issue number that this issue is a duplicate of. Only used when state_reason is 'duplicate'. (number, optional)
This record as markdown: /tools/io-github-aifity-omnigit-mcp/duplicate-of.md
What duplicate_of does on GitHub
AI agents use duplicate_of to create or update resources in GitHub, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your GitHub environment.
Why duplicate_of is rated Medium
This appears to be a parameter/field descriptor rather than a standalone tool — it describes a field used when marking an issue as a duplicate. If treated as a tool, it would modify issue metadata (marking duplicate status), which is a reversible write operation. Confidence is low because the description reads like a parameter definition, not an actionable tool, and lacks a clear action verb.
From the tool's definition 'Issue number that this issue is a duplicate of. Only used when state_reason is duplicate'
Attacks that exploit this kind of access
The rule that runs duplicate_of 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 duplicate_of, this is the rule to start with:
duplicate_of stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. 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 duplicate_of call is checked against it from then on.
Questions about duplicate_of
Issue number that this issue is a duplicate of. Only used when state_reason is 'duplicate'. (number, optional). It is categorised as a Write tool in the GitHub MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the GitHub MCP server in PolicyLayer and add a rule for duplicate_of: 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.
duplicate_of 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 duplicate_of 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 duplicate_of. 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.
duplicate_of 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