Get the Koyeb API token
AI agents call get-token to retrieve information from Koyeb MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
While this is a Read operation (retrieves data with no side effects), the specific data retrieved is a highly sensitive API token that grants full access to Koyeb resources. Exposure of this credential would allow an attacker to impersonate the user and perform any operation on their Koyeb infrastructure, justifying a high severity rating despite the Read category.
From the tool's definition Tool name is 'get-token' and description states 'Get the Koyeb API token'. The tool retrieves authentication credentials.
Attacks that exploit this kind of access
Get the Koyeb API token. It is categorised as a Read tool in the Koyeb MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Koyeb MCP Server MCP server in PolicyLayer and add a rule for get-token: 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 Koyeb MCP Server. Nothing to install.
get-token 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 get-token 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 get-token. 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.
get-token is provided by the Koyeb MCP Server MCP server (samihalawa/mcp-server-koyeb). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →