Revelica in any MCP client

Cursor, Gemini CLI and any agent that speaks MCP can read and save your team's product context. Point it at one URL and sign in through the browser.

Read the MCP docs

The server

Revelica runs a remote MCP server over streamable HTTP. Your client signs in with OAuth in the browser, and every request runs as you. There are no API keys, so a client needs OAuth support to connect.

https://api.revelica.com/mcp

Add it

Cursor

Add the server to .mcp.json in your project, or to your global Cursor MCP settings:

{
  "mcpServers": {
    "revelica": {
      "type": "http",
      "url": "https://api.revelica.com/mcp"
    }
  }
}

Gemini CLI

Add it to ~/.gemini/settings.json, then run /mcp and sign in when the browser opens:

{
  "mcpServers": {
    "revelica": {
      "httpUrl": "https://api.revelica.com/mcp"
    }
  }
}

Any other client

Most clients only need the URL. If yours asks for a transport, choose streamable HTTP. Claude and ChatGPT have their own pages, with directory listings and plugins.

What your agent gets

Seven tools and Revelica's product skills. Apps that can draw the Canvas show records as cards; terminal clients get a link to open the record in Revelica.

querySearch or filter the workspace
readOpen one record in full
createSave a new record
updateChange fields on a record
showShow a record as a card, or a link where there's no UI
list_skillsList Revelica's product skills
load_skillLoad a skill's instructions and starting data