AI agents use update_issue to create or update resources in GitHub Kanban MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your GitHub Kanban MCP Server environment.
Update operations are reversible writes—changes can be undone by updating again with previous values. While it modifies persistent data in GitHub, it does not delete or destroy information, nor does it execute arbitrary code or move money.
From the tool's definition Tool name is "update_issue" and description states it updates existing issues (「既存のissueを更新します」- updates existing issues). This modifies data in GitHub reversibly.
Documented attack patterns abuse exactly the kind of access update_issue gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and GitHub Kanban MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for update_issue:
{
"version": "1",
"default": "deny",
"tools": {
"update_issue": {
"limits": [
{
"counter": "update_issue_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update_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.
既存のissueを更新します. It is categorised as a Write tool in the GitHub Kanban MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the GitHub Kanban MCP Server MCP server in PolicyLayer and add a rule for update_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 GitHub Kanban MCP Server. Nothing to install.
update_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 update_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 update_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.
update_issue is provided by the GitHub Kanban MCP Server MCP server (sunwood-ai-labs/github-kanban-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from GitHub Kanban MCP Server, 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.
4 GitHub Kanban MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.