> For the complete documentation index, see [llms.txt](https://help.nightfall.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.nightfall.ai/nightfall-for-anthropic-claude/comprehensive-claude-coverage.md). # Comprehensive Claude Coverage These are separate Nightfall products. Together they give a Claude customer one set of detection rules and one console. Pick the integration that matches the control you need. Most Claude Enterprise customers run all of them. | Surface | Integration | What it does | Enforcement | | ------------------------------------------------------------------------------------------------- | ----------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------ | | Claude Desktop and the Claude web tab | Nightfall endpoint agent | Scans file uploads and clipboard pastes. Lineage recognizes a corporate Google Drive, SharePoint, or GitHub origin | Inline block, before submit | | claude.ai, Cowork, Claude Desktop, mobile, Claude Code, and Claude in Slack, on Claude Enterprise | Claude Inference Hooks | Scans the prompt before the model runs, including tool results that have already come back. Does not stop a shell command or a tool call before it executes. No agent and no MDM | Inline block, before the model | | Claude Code, and also Cursor and VS Code Copilot | Nightfall AI Agent Security, device hooks | Scans prompts, MCP tool calls, tool responses, shell commands, and model responses. Blocks prompts, tool calls, and shell commands before they run, and blocks tool responses on the macOS and Windows agents before the model reads them (not on VS Code Copilot). Model responses are monitor only | Inline block on the device | | Claude Cowork sessions | OpenTelemetry | Session audit of cost, token usage, and tool invocations | Audit | | Claude Enterprise chats and uploaded files | Claude Compliance API, this section | Server-side scan of chats and uploaded files after they exist | Monitor and audit. No block | The endpoint agent and device hooks block on the laptop. Inference Hooks block in Claude's cloud, including on machines that never received a hook profile. OpenTelemetry audits Cowork sessions. The Compliance API is the organization-wide record for investigation and evidence. Device hooks are still required when a shell command or an MCP tool call must be stopped before it runs, and for Cursor, VS Code, Bedrock, Vertex, and Console API-key sessions. The coverage matrix, use cases, and policy templates are in Data Exfiltration Prevention: [Choosing a control](https://help.nightfall.ai/data-exfiltration-prevention/ai-agent-security/ai-governance/choosing-a-control). --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://help.nightfall.ai/nightfall-for-anthropic-claude/comprehensive-claude-coverage.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.