Convert text into dense vectors. Accepts a single string or a batch (max 2048). Returns one vector per input plus token usage. Currently proxies OpenAI /v1/embeddings (model: text-embedding-3-small by default, overridable via OPENAI_EMBEDDING_MODEL). Requires Authorization: Bearer <api_key> to ca...
AI agents call iliad_embeddings to retrieve information from AXIS iliad without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a pure read operation: it takes text as input and returns vectorized representations without side effects. There is no data creation, modification, deletion, or code execution involved. The tool is a wrapper around OpenAI's embedding API, which is fundamentally a stateless transformation service.
From the tool's definition Tool accepts text input and returns 'dense vectors' and 'token usage' — no modification, deletion, or execution of external operations.
Attacks that exploit this kind of access
Convert text into dense vectors. Accepts a single string or a batch (max 2048). Returns one vector per input plus token usage. Currently proxies OpenAI /v1/embeddings (model: text-embedding-3-small by default, overridable via OPENAI_EMBEDDING_MODEL). Requires Authorization: Bearer <api_key> to call. When OPENAI_API_KEY is not provisioned, returns a structured. It is categorised as a Read tool in the AXIS iliad MCP Server, which means it retrieves data without modifying state.
Register the AXIS iliad MCP server in PolicyLayer and add a rule for iliad_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 AXIS iliad. Nothing to install.
iliad_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 iliad_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 iliad_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.
iliad_embeddings is provided by the AXIS iliad MCP server (lastmanupinc-hub/axis-iliad). 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 →