MCP server | BriefPanel

BriefPanel is a remote MCP server. Connect it to Cursor, Claude Code, Windsurf, or anything that speaks the Model Context Protocol, and your agent can start monitoring pages and read back what changed.

This is the technical reference. For an overview of what the integration is for, see the MCP page.

Endpoint

https://actions.briefpanel.com/mcp

Transport — Streamable HTTP, stateless: one JSON-RPC request per POST, answered with a JSON response. Server-Sent Events are deprecated and not required.
Protocol version — 2024-11-05, advertised in the initialize handshake.

A discovery document is published at https://briefpanel.com/.well-known/mcp.json, so MCP hosts that auto-discover servers by domain can find it without configuration.

Authentication

Send a personal API key as a Bearer token:

Authorization: Bearer YOUR_BRIEFPANEL_API_KEY

Create a key under Settings → Connect your agent in the app (https://app.briefpanel.com/connect-agent). Keys start with bp_mcp_ and the same key works for the REST API.

A missing or invalid key returns 401 with a WWW-Authenticate header.

Scopes

Each key carries scopes. Read tools need read; add_source needs write. Calling a tool your key lacks the scope for fails rather than silently doing nothing.

OAuth

Claude.ai and Claude Desktop custom connectors, and ChatGPT connectors, require OAuth. That flow is coming; until it ships, use any client that can send a Bearer header with the configuration below.

OAuth access tokens (bp_oat_) are audience-bound to the MCP resource, so they authenticate MCP calls only — not the REST API.

Client configuration

Most clients read the standard mcpServers block:

{
  "mcpServers": {
    "briefpanel": {
      "url": "https://actions.briefpanel.com/mcp",
      "headers": { "Authorization": "Bearer YOUR_BRIEFPANEL_API_KEY" }
    }
  }
}

Claude Code takes it as one command:

claude mcp add --transport http briefpanel https://actions.briefpanel.com/mcp \
  --header "Authorization: Bearer YOUR_BRIEFPANEL_API_KEY"

Cursor has a one-click install link on the MCP page.

Tools

Five tools, four of them read-only.

`list_sources`

List the web pages you monitor. No arguments.

`get_source_changes`

Recent content changes across your monitored pages, with AI summaries of what changed.

Argument	Type	Notes
`limit`	number	Maximum entries to inspect, 1–25. Defaults to 10.

`get_credit_balance`

Your remaining credits. Each page check costs credits. No arguments.

`whoami`

The identity and scopes tied to the current API key — useful for confirming which account a key belongs to. No arguments.

`add_source`

Start monitoring a new page. This is the only tool that writes, and it needs the write scope. Checking the page later costs credits.

Argument	Type	Notes
`url`	string	Required. The page URL to monitor.
`userPrompt`	string	What changes matter, in plain language.
`monitoringFrequency`	number	Minutes between checks. Defaults to 60, clamped to 5 minutes–7 days.
`notificationsEnabled`	boolean	Whether to notify on changes. Defaults to `false`.

Calling it again with the same URL and userPrompt returns the existing source instead of creating a duplicate.

Reading history

The MCP tools are built for conversation: they answer "what changed recently" in a form an agent can summarize. For the full typed change history of a single item — every recorded update, with before/after values and the captured evidence — use the REST API.