Fetch a URL, convert HTML to markdown, and index the content. Cached for 24 hours.
AI agents use lctx_fetch_and_index to create or update resources in Logica Context — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Logica Context environment.
This tool fetches external content and writes/indexes it into the persistent memory store. The primary side effect is creating or updating indexed content in the system. While it reads from a URL, the meaningful action is indexing (writing) the result into the knowledge base. It is reversible in principle (content can be purged), so Destructive does not apply.
From the tool's definition Fetch a URL, convert HTML to markdown, and index the content
Attacks that exploit this kind of access
Fetch a URL, convert HTML to markdown, and index the content. Cached for 24 hours. It is categorised as a Write tool in the Logica Context MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Logica Context MCP server in PolicyLayer and add a rule for lctx_fetch_and_index: 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 Logica Context. Nothing to install.
lctx_fetch_and_index 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 lctx_fetch_and_index 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 lctx_fetch_and_index. 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.
lctx_fetch_and_index is provided by the Logica Context MCP server (rovemark/logica-context). 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 →