Intranet crawler
Overview
Section titled “Overview”The Intranet crawler is a powerful tool that enables your assistants to search and retrieve information from your organization’s internal intranet. Built on the Model Context Protocol (MCP) standard, it provides your team with secure, authenticated access to intranet content directly within Intric conversations.
The crawler can access and index content behind login-protected intranets using configured service account credentials. This includes employee handbooks, policy documents, internal wikis, and other resources that require authentication, making this knowledge available to your assistants without requiring users to search manually or log in themselves.
Key capabilities
Section titled “Key capabilities”Search Intranet
Section titled “Search Intranet”Enable assistants to search indexed intranet content and retrieve relevant information in response to user queries. The search functionality respects the permissions of the configured service account, ensuring users only access content they’re authorized to see.
Let users suggest corrections
Section titled “Let users suggest corrections”Allow users to suggest corrections to indexed content when they notice outdated or inaccurate information. Suggested corrections are routed to administrators who can review, modify, and approve changes before they’re applied to the index.
This feature has proven particularly valuable for organizations where content governance is distributed, as it enables subject matter experts across the organization to help keep information current.
How it works
Section titled “How it works”The crawler operates as a custom MCP server that you configure in Intric’s administration interface. Once set up:
- The crawler periodically visits configured URLs on your intranet
- It authenticates using credentials you provide (typically a service account)
- Content is extracted, processed, and indexed for search
- Assistants with the Intranet crawler tool enabled can search this content
- Users can submit correction suggestions through a dedicated interface
- Administrators review and manage corrections through the admin panel
Appropriate use cases
Section titled “Appropriate use cases”The Intranet crawler works best for:
- Publicly accessible intranets — Internal sites that don’t require complex multi-step authentication
- Employee handbooks and policy documents — Static or semi-static content that benefits from being searchable
- Knowledge bases — Internal wikis, documentation sites, and reference materials
- Widgets and embedded assistants — Providing intranet search functionality in specific contexts (e.g., HR assistants, onboarding bots)
Security and permissions
Section titled “Security and permissions”The crawler operates under the permissions of the service account you configure during setup. This means:
- The crawler can only access content that the service account can access
- All indexed content becomes searchable by assistants using the tool
- Careful service account scoping is critical to prevent over-indexing
Important: Review your intranet’s permission model before configuring the crawler. If your service account has broad access rights, consider whether all indexed content should be searchable by all users of the assistant.
Security classification rules apply to the Intranet crawler tool just as they do to other tools in Intric. An assistant can only use the crawler if it meets the security requirements of the Space it belongs to.
Next steps
Section titled “Next steps”Ready to enable intranet search for your organization?
- Contact us at support@intric.ai to initiate setup and coordinate with our technical team
- Read the article below to understand the setup process and prepare the necessary information.