Creates an embedding vector representing the input text.
AI agents call embeddings to retrieve information from Jina AI MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Embeddings are a read-only vectorization operation that transforms text into numerical representations for semantic understanding. The operation has no side effects, does not modify data, and does not trigger external actions. It is purely a data retrieval/transformation function that returns computed vectors based on input text.
From the tool's definition The tool 'embeddings' 'Creates an embedding vector representing the input text' — it transforms input into a vector representation without modifying, deleting, or executing external operations with side effects.
Attacks that exploit this kind of access
Creates an embedding vector representing the input text. It is categorised as a Read tool in the Jina AI MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Jina AI MCP Server MCP server in PolicyLayer and add a rule for embeddings: 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 MCP Server. Nothing to install.
embeddings 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 embeddings 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 embeddings. 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.
embeddings is provided by the Jina AI MCP Server MCP server (zk-armor/mcp-jina-ai). 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 →