Return the bearer token from the Authorization header of the MCP settings, which is used to debug.
AI agents call show_api_key to retrieve information from Jina AI Remote MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
While this tool performs a read operation (retrieves credentials), it returns highly sensitive authentication material (API keys/bearer tokens). If exposed to a compromised AI agent, this would allow an attacker to impersonate the service and access Jina AI APIs with the account's full privileges.
From the tool's definition Tool explicitly returns the bearer token/API key from Authorization header, described as being used for debugging purposes.
Attacks that exploit this kind of access
Return the bearer token from the Authorization header of the MCP settings, which is used to debug. It is categorised as a Read tool in the Jina AI Remote MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Jina AI Remote MCP Server MCP server in PolicyLayer and add a rule for show_api_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 Jina AI Remote MCP Server. Nothing to install.
show_api_key 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 show_api_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 show_api_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.
show_api_key is provided by the Jina AI Remote MCP Server MCP server (matifema/jina-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 →