Kitsuvo
RemoteAbout Kitsuvo
Kitsuvo integrations let MCP clients such as Claude Code and Codex operate the user's Kitsuvo browser to browse pages, inspect detection evidence, and check responsive layouts. The repository includes plugins, agent skills, and local and cloud connectors; the browser is installed separately.
Key features
- 01Navigate to pages and read text and snapshots
- 02Click and type into accessible page elements
- 03Inspect evidence behind AI-builder and impersonation verdicts
- 04Resize pages and check layouts
- 05Automate through a separate browser profile
Use cases
- 01Have an agent open a site and read its content
- 02Inspect why a site was flagged as AI-built
- 03Check a page layout at phone and desktop sizes
MCP support
The local MCP connection drives an installed Kitsuvo browser; local HTTP bridging and an authenticated cloud relay are also available. The cloud path forwards selected page results only while the connector is running and after the client is approved.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://kitsuvo-mcp-relay.fly.dev/mcpclaude mcp add --transport http leancoderkavy-kitsuvo https://kitsuvo-mcp-relay.fly.dev/mcp{"mcpServers":{"leancoderkavy-kitsuvo":{"type":"http","url":"https://kitsuvo-mcp-relay.fly.dev/mcp"}}}Open in Cursor{"servers":{"leancoderkavy-kitsuvo":{"type":"http","url":"https://kitsuvo-mcp-relay.fly.dev/mcp"}}}Open in VS Code{"mcpServers":{"leancoderkavy-kitsuvo":{"type":"http","url":"https://kitsuvo-mcp-relay.fly.dev/mcp"}}}{"mcpServers":{"leancoderkavy-kitsuvo":{"serverUrl":"https://kitsuvo-mcp-relay.fly.dev/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
The maintainer has not added details yet. Check the README in the repository.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.