> ## Documentation Index > Fetch the complete documentation index at: https://trygradient.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # Connectors > Data sources available during assessments # Connectors **Connectors** are data sources that candidates can browse and search during an assessment. They simulate the kind of enterprise tools and knowledge bases that professionals use daily: email, project trackers, meeting notes, internal wikis, and enterprise search. Connectors are the in-assessment data sources, and are separate from [ATS integrations](/integrations), which connect Gradient to your hiring stack. ## Connector categories When adding connectors to an assessment, admins choose from categories. Each category has named variants so the connector appears branded to the candidate (e.g., "Gmail" instead of generic "Mail"). | Category | Variants | Description | | ----------------------- | ----------------------------------- | ------------------------------------------ | | **Enterprise Search** | Enterprise Search, Glean, Coveo | Company knowledge base with keyword search | | **Meeting Transcripts** | Meeting Transcripts, Granola, Otter | Search meeting notes and call transcripts | | **Mail** | Email, Gmail, Outlook | Search email messages and threads | | **Tickets** | Linear, Asana, Jira | Search issues and project tasks | | **Company Documents** | Notion, Confluence, Google Drive | Search company documents and wikis | | **MCP Server** | *(custom)* | Connect a real MCP server by URL | All built-in categories use the same keyword-ranking search backend (TF-IDF style). The variant name only affects what the candidate sees and the tool name the AI uses. **Meeting Transcripts** additionally supports participant and meeting-type filters. ## MCP servers Admins can also connect real [Model Context Protocol](https://modelcontextprotocol.io/) servers. When adding an MCP Server connector, the admin provides a server URL, probes it to discover available tools, and adds it to the assessment. Candidates interact with MCP connectors the same way: the tools appear in their AI assistant automatically. MCP servers support optional authentication via static bearer tokens or OAuth flows. ## How candidates use connectors During the **Explore** phase, candidates get oriented and browse the available data sources. During the **Task** phase, they search those data sources through the AI assistant using natural language queries. See [Candidates & Sessions](/concepts/candidates-and-sessions) for the phase model. The search returns relevant documents that the candidate can then reference in their deliverable. ## Signal and noise Each data source is tagged as either **signal** (relevant to the task) or **noise** (a distractor). This distinction is invisible to the candidate, who sees all data sources equally and must determine which ones are useful. The scoring engine tracks: * Which data sources the candidate connected * Which documents they searched for and reviewed * Whether they used signal documents in their deliverable * Whether they included noise data uncritically ## Candidate permissions Admins can control what candidates can do with connectors via the **Candidate Permissions** card in the assessment's Data step. The two connector-related permissions are: | Permission | Default | Effect | | -------------------------- | ------- | ------------------------------------------------------------- | | Browse connector documents | On | Candidates can see individual documents within each connector | | Add custom MCP servers | Off | Candidates can connect their own MCP servers | These are two of the five candidate permissions; the rest govern skills, memory, and the agents.md configuration. See [Assessments](/concepts/assessments#candidate-permissions) for the full set. Connector data can be managed programmatically via the [Connector Data API](/api-reference/connector-data). Upload CSV, JSON, TXT, or Markdown files.