About INTERNETS.FUN room reader
INTERNETS.FUN room reader gives MCP clients read-only access to bounded room summaries. Room-scoped bearer tokens limit access; it does not expose AI generation or editing.
Key features
- 01Read bounded room summaries
- 02Use room-scoped bearer tokens
- 03Limit access to a single room
- 04No AI generation or writes
Use cases
- 01Reading a room summary through an MCP client
- 02Granting access limited to one room
- 03Revoking room access by removing a member
MCP support
Exposes room summaries through an MCP endpoint. Clients authenticate with a room-scoped bearer token in the Authorization header.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://internets.fun/api/mcpclaude mcp add --transport http theguysaccount-internets https://internets.fun/api/mcp{"mcpServers":{"theguysaccount-internets":{"type":"http","url":"https://internets.fun/api/mcp"}}}Open in Cursor{"servers":{"theguysaccount-internets":{"type":"http","url":"https://internets.fun/api/mcp"}}}Open in VS Code{"mcpServers":{"theguysaccount-internets":{"type":"http","url":"https://internets.fun/api/mcp"}}}{"mcpServers":{"theguysaccount-internets":{"serverUrl":"https://internets.fun/api/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
From the project READMEINTERNETS.FUN room reader
MCP endpoint: https://internets.fun/api/mcp
Connection metadata: https://internets.fun/agents.json
Use a room-scoped token from the room’s Agents panel in the Authorization header, kept in your MCP client secret store. The example environment variable is a placeholder. No production token is stored here. The token cannot read other rooms and loses access when revoked or its member is removed. Native directories requiring OAuth need an additional OAuth adapter. No room creation, hosted AI generation, reviews or writes are exposed.
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.