Returns the login credentials that will be used for authentication to http://localhost
AI agents call get_login_credentials to retrieve information from MCP Login Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves pre-stored credential data for localhost applications. While credentials are sensitive, this tool merely reads and returns them without creating, modifying, executing, or deleting anything. The actual authentication is performed by sibling tools like 'perform_login'.
From the tool's definition Tool name is 'get_login_credentials' and description states it 'Returns the login credentials'. The verb 'Returns' indicates data retrieval with no modification or execution of side effects.
Attacks that exploit this kind of access
Returns the login credentials that will be used for authentication to http://localhost. It is categorised as a Read tool in the MCP Login Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Login Server MCP server in PolicyLayer and add a rule for get_login_credentials: 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 MCP Login Server. Nothing to install.
get_login_credentials 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_login_credentials 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_login_credentials. 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_login_credentials is provided by the MCP Login Server MCP server (nieperdragon/custom_mcp). 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 →