AI agents use github__create_issue to create or update resources in Mcpd Proxy — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcpd Proxy environment.
Creating a GitHub issue is a write operation that adds new data to a repository. It is not destructive (the issue can be removed), not financial, and not execute (it doesn't run arbitrary code—it submits structured data to create a tracked item).
From the tool's definition Tool name is `github__create_issue`, which creates a new issue on GitHub. The action is reversible (issues can be deleted or closed), and it modifies data by adding a new resource to a repository.
Documented attack patterns abuse exactly the kind of access github__create_issue gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcpd Proxy, and nothing reaches the server without passing your rules. This is the rule we recommend for github__create_issue:
{
"version": "1",
"default": "deny",
"tools": {
"github__create_issue": {
"limits": [
{
"counter": "github__create_issue_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}github__create_issue 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.
Free to start. No card required.
create_issue tool from github server. It is categorised as a Write tool in the Mcpd Proxy MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcpd Proxy MCP server in PolicyLayer and add a rule for github__create_issue: 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 Mcpd Proxy. Nothing to install.
github__create_issue 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__create_issue 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__create_issue. 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__create_issue is provided by the Mcpd Proxy MCP server (mozilla-ai/mcpd-proxy). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcpd Proxy, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
3 Mcpd Proxy tools catalogued and risk-classified — across an index of 43,000+ MCP servers.