Brollvia MCP for Claude
Anthropic
Claude.ai connectors and Claude Desktop — the client we run against production ourselves.
MCP client guide · October 2026
One `claude mcp add` command, OAuth in the terminal flow.
Standard MCP connection — this guide follows Anthropic's documented MCP setup. We have not live-verified this client yet, so it does not carry the verified badge.
Anthropic · CLI & terminal agents · Server URL: https://brollvia.com/mcp
Claude Code, Anthropic's terminal agent, takes remote MCP servers with a single command and handles OAuth itself: add Brollvia over HTTP transport, authenticate from the /mcp menu, and Claude Code can search a licensed library, build shot lists and download footage as part of the same session where it is writing your pipeline, your templates or your edit tooling.
Same vendor as the verified client, different surface: our live verification was done in Claude's connector UI, not in Claude Code, so this page is listed as standard. The transport and OAuth flow are the same standards-based machinery — and if you connect it and something disagrees with these steps, we want the report.
One command (add --scope user to make it available in every project):
claude mcp add --transport http brollvia https://brollvia.com/mcpReal prompts, using the real tools — search, script-to-B-roll, collections and licence lookups:
Use Brollvia to find licensed drone footage of a lighthouse in a storm, download the best one to ./media.
Read script.txt, turn it into a Brollvia shot list, and license the picks under my Pro plan.
Check the licence on the last clip you downloaded and print its verification URL.
Because the badge describes the exact surface we tested: Claude's connector UI against the production server, end to end. Claude Code shares the protocol and the vendor but is a different client build with its own auth plumbing; until we run it live, it stays standard — the badge has to mean something.
No. The HTTP transport triggers Claude Code's built-in OAuth support against Brollvia's discovery endpoints — you sign in in a browser and approve scopes. (Config-file clients without OAuth can use API keys; Claude Code does not need that path.)
Claude Code manages it (~/.claude.json and project .mcp.json for project scope). `claude mcp list` shows configured servers; `claude mcp remove brollvia` removes this one. Your Brollvia tokens can also be revoked server-side in Connected apps at any time.
Same server, same URL — every guide below is that client's real setup. The full grid lives on the MCP hub.
Anthropic
Claude.ai connectors and Claude Desktop — the client we run against production ourselves.
OpenAI
Custom MCP connector via Developer mode, signed in with OAuth.
Microsoft
Copilot agent mode with the library one prompt away, via .vscode/mcp.json.
Anysphere
Remote MCP in mcp.json — OAuth connect, then footage inside the agent chat.
Gemini CLI — Google's terminal agent, connected via settings.json.
Google's agent-first editor — add Brollvia as a custom MCP server.
Windsurf (Codeium)
Cascade gains a licensed library via mcp_config.json.
Cline
The VS Code agent extension — MCP servers panel, remote HTTP with OAuth.
Zed
MCP "context servers" in settings.json — remote URL, OAuth sign-in.
JetBrains
IntelliJ, WebStorm, PyCharm & co. — MCP in AI Assistant settings, no config file.
OpenAI
Muse — TOML config or one command, OAuth for remote servers.
Start free, upgrade when the work does. Every download writes a licence record you can verify in public.