Quick-ingest a URL into the knowledge base. Fetches the page, extracts content, chunks it, and stores with immutable source flag. Use when adding web articles, documentation, or research to your second brain.
AI agents use memory_clip to create or update resources in Exocortex — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Exocortex environment.
This tool fetches external web content and writes it into the knowledge base as chunked, stored data. It is a Write operation (creating new records in the memory system). The 'immutable source flag' suggests the stored data cannot be easily modified, increasing misuse risk slightly, but the operation itself is a creation/ingestion—not destructive or financial.
From the tool's definition Quick-ingest a URL into the knowledge base. Fetches the page, extracts content, chunks it, and stores with immutable source flag.
Attacks that exploit this kind of access
Quick-ingest a URL into the knowledge base. Fetches the page, extracts content, chunks it, and stores with immutable source flag. Use when adding web articles, documentation, or research to your second brain. It is categorised as a Write tool in the Exocortex MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Exocortex MCP server in PolicyLayer and add a rule for memory_clip: 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 Exocortex. Nothing to install.
memory_clip is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the memory_clip 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 memory_clip. 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.
memory_clip is provided by the Exocortex MCP server (shawnhack/exocortex). 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 →