Get the publication associated with the authenticated API key. Requires API key.
AI agents call get-me to retrieve information from Paragraph MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves publication information associated with an authenticated user. It performs a read-only query that returns data about the user's publication. No data is created, modified, deleted, or any external operations are triggered. The authentication requirement does not change the fundamental read-only nature of the operation.
From the tool's definition Tool name 'get-me' and description 'Get the publication associated with the authenticated API key' indicates retrieval of data without modification or side effects.
Attacks that exploit this kind of access
Get the publication associated with the authenticated API key. Requires API key. It is categorised as a Read tool in the Paragraph MCP MCP Server, which means it retrieves data without modifying state.
Register the Paragraph MCP server in PolicyLayer and add a rule for get-me: 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 Paragraph MCP. Nothing to install.
get-me 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-me 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-me. 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-me is provided by the Paragraph MCP server (paragraph-xyz/paragraph-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 →