AI agents use create_deploy_key to create or update resources in GitHub Repos Manager MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your GitHub Repos Manager MCP Server environment.
Creating deploy keys is a reversible write operation that adds SSH authentication credentials to a repository. While deploy keys enable unauthorized access if compromised, the tool itself performs a write action (adding a key). The impact is contained to repository access control and does not directly execute code, delete data, or move funds.
From the tool's definition Tool name 'create_deploy_key' and description 'Add new deploy keys' indicate creation/addition of deployment credentials to a repository.
Documented attack patterns abuse exactly the kind of access create_deploy_key gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and GitHub Repos Manager MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for create_deploy_key:
{
"version": "1",
"default": "deny",
"tools": {
"create_deploy_key": {
"limits": [
{
"counter": "create_deploy_key_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}create_deploy_key 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.
Add new deploy keys. It is categorised as a Write tool in the GitHub Repos Manager MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the GitHub Repos Manager MCP Server MCP server in PolicyLayer and add a rule for create_deploy_key: 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 Repos Manager MCP Server. Nothing to install.
create_deploy_key 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 create_deploy_key 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 create_deploy_key. 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.
create_deploy_key is provided by the GitHub Repos Manager MCP Server MCP server (kurdin/github-repos-manager-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from GitHub Repos Manager 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.
84 GitHub Repos Manager MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.