deep_ingest
AI agents call deep_ingest to retrieve information from mcp Research without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The server is explicitly documented as providing 'read-only tools' with SSRF protection and summarization. All sibling tools are retrieval/research operations. 'deep_ingest' most likely ingests/processes research data for synthesis, consistent with the 'automated multi-source synthesis pipelines' mentioned.
From the tool's definition Tool name 'deep_ingest' appears on a research server with description: 'Enables AI assistants to perform comprehensive web research through tiered search, secure URL fetching with markdown conversion, and automated multi-source synthesis pipelines.
Attacks that exploit this kind of access
deep_ingest. It is categorised as a Read tool in the mcp Research MCP Server, which means it retrieves data without modifying state.
Register the mcp Research MCP server in PolicyLayer and add a rule for deep_ingest: 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 mcp Research. Nothing to install.
deep_ingest 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 deep_ingest 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 deep_ingest. 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.
deep_ingest is provided by the mcp Research MCP server (mabaam/maibaamcrawler). 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 →