xCLAUDE docs

How it works

Claude Desktop talks to tools through two separate channels. The first is local MCP servers — your filesystem tools, custom MCP servers, and any other MCP configured in `claude_desktop_config.json`. The second is native Connectors (Gmail, Drive, GitHub, Slack, etc.), which you connect through Settings → Connectors and which Claude reaches as remote MCPs on the providers' servers.

xCLAUDE rewrites the local config file. After install, each of your local MCP servers is wrapped individually: its entry keeps its own name, but now points to the xCLAUDE proxy, which launches the real server and relays its traffic unchanged. Claude Desktop sees the same servers, with the same names and the same tools. Native Connectors are unaffected — they continue to work directly between Claude Desktop and the providers' servers, outside xCLAUDE's path.

Because every local MCP tool call now passes through xCLAUDE, it audits both sides of the conversation: what Claude Desktop asks your tools to do — which tool, with what parameters — and what those tools send back. That's what makes the audit log possible — and what lets xCLAUDE scan content for credentials, PII, and prompt-injection attempts before the data ever leaves your machine. Tool calls to native Connectors are not visible to xCLAUDE.

  Claude Desktop
       │
       ├──► Native Connectors (Gmail, Drive, ...)
       │    not visible to xCLAUDE
       │
       ▼
    xCLAUDE (one proxy per wrapped server) ← audit + detection + scanning
       │
       ├──► Local MCPs (FileSystem, custom tools...)
       │    stdio — traffic stays on your machine
       │
       └──► Remote Connectors (Notion, Slack, GitHub...)
            http bridge — traffic goes to provider servers

Claude Code is a separate, self-contained source: a session hook records what the model actually consumed, with no config rewriting involved. Wrapping its MCP servers (optional) adds the protocol-level view. See the Claude Code section below.

What v1 covers

• ✓Every MCP tool call — name, parameters, and result
• ✓Claude Code sessions — every tool call via the session hook (native and MCP tools), plus optional wrapping of its MCP servers for the protocol-level view
• ✓Structured PII — verifiable identifiers: emails, phone numbers, IBANs, credit cards, national IDs
• ✓Named entity detection — person names, organisations, and locations in tool arguments (async, best-effort)
• ✓Prompt injection detection in tool arguments and response content
• ✓Credential pattern detection — API keys, tokens, and secrets, masked before they reach the log
• ✓Email send detection in tool arguments and tool names
• ✓Data export command detection in tool arguments — and in responses, where an explicit destination is required
• ✓Tool manifest change detection — warns when a source's tools change since the recorded baseline (tool poisoning)
• ✓Local audit log — per-session JSONL files, consolidated into daily files as sessions finish, under ~/Library/Application Support/xCLAUDE Gateway/wrappers/
• ✓Live dashboard in your menu bar

Dashboard

xCLAUDE lives in your menu bar. Click the icon to open the dashboard at any time. It refreshes every 2 seconds and shows every event with severity, connector, and tool call details. No telemetry leaves your laptop.

Verify it works

The Sources tab includes a Verify detection button — a safe, self-contained end-to-end check. It runs a synthetic risky payload through the audit pipeline and confirms the event is recorded and flagged, so you can see the detectors working without touching any real connector. The result appears in the Sources view.

Connectors

xCLAUDE includes audited versions of the most common MCP connectors. Connect through xCLAUDE instead of Claude Desktop's native Settings → Connectors. If a service is connected in both places, Claude may use the native, unaudited path — disconnect it there first.

One-click connectors

Notion, GitHub, Linear, Atlassian, Stripe, and Apollo connect with one click. No Terminal needed.

1. Open xCLAUDE Gateway → Sources tab → + Add source.
2. Select the connector you want → Connect.
3. Authorize in the browser that opens.
4. Restart Claude Desktop.

Slack

Slack has a 2-step in-app wizard: the Set up button opens Slack with your app pre-configured from a manifest (scopes, redirect and MCP included) — pick your workspace and hit Create — then paste your app's Client ID. No client secret involved (Slack uses public PKCE). Slack asks you to re-authorize about once a month — that's how Slack designed it, not an error.

Google connectors (Gmail, Calendar, Drive)

Google connectors run on your own key: xCLAUDE embeds no Client ID, so you create a Google Cloud project of your own and paste your credentials into the app. The Set up button walks you through a guided 4-step wizard — Cloud project, OAuth client, Preview enrollment, paste your credentials — with deep links at every step. One free OAuth client serves all three; your credentials are stored in the macOS Keychain.

Claude Code

xCLAUDE audits Claude Code as a source of its own, independent of Claude Desktop.

Session auditing (one click)

Open the Sources tab → + Add source → Claude Code → Install hook. From then on, every tool call in your Claude Code sessions — native tools and MCP tools alike — is recorded and classified by the same detection engine, with its own Claude Code view in the app: severity cards, filters, search, and export. To stop, open the Claude Code source and click Uninstall.

Wrapping Claude Code's MCP servers (optional)

Wrapping adds what only the protocol level shows: each server's tool manifest, its stderr, and server-initiated traffic. Calls seen by both sources are correlated by tool-use ID. Setup is manual for now and documented step by step in the README:

Wrapping Claude Code's MCP servers — README →

Uninstall

If you installed the Claude Code hook, remove it first: open the Claude Code source in the Sources tab and click Uninstall.

1. Open xCLAUDE Gateway → Settings (gear icon) → Uninstall. This restores your original MCP configuration.
2. Click the xCLAUDE icon in your menu bar → Quit xCLAUDE Gateway.
3. Drag xCLAUDE Gateway.app to the Trash.
4. Restart Claude Desktop.

Optional cleanup:

• To delete all local data (audit logs, settings, connector baselines), run in Terminal:

  rm -rf ~/Library/Application\ Support/xCLAUDE\ Gateway/

• Google/OAuth credentials live in the macOS Keychain and are NOT removed by the step above. To clear them, run one line per connector you had connected (e.g. gmail, calendar, drive, notion):

  for k in tokens client verifier; do
    security delete-generic-password -s com.xclaude.gateway -a "gmail:$k" 2>/dev/null
  done

  Or open Keychain Access and delete the com.xclaude.gateway items.