AI agents call ingest_tool to retrieve information from Alaya without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads external sources (URLs, PDFs, markdown files) and extracts/processes their content for indexing. It is a retrieval and analysis operation with no side effects on the vault or source material. The severity is low because ingesting external content into a personal knowledge vault poses minimal risk even with misuse by an AI agent.
From the tool's definition Tool description states it 'ingest[s]' content and 'returns' processed information (raw_text, title, chunks, wikilinks). No modification of source or vault occurs—it retrieves and processes external content.
Attacks that exploit this kind of access
Ingest a URL, PDF, or markdown file. Returns raw_text, title, chunks indexed, and suggested wikilinks. It is categorised as a Read tool in the Alaya MCP Server, which means it retrieves data without modifying state.
Register the Alaya MCP server in PolicyLayer and add a rule for ingest_tool: 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 Alaya. Nothing to install.
ingest_tool 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 ingest_tool 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 ingest_tool. 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.
ingest_tool is provided by the Alaya MCP server (luke-kucing/alaya). 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 →