MCP server
Connect Cursor, Gemini CLI or any MCP client to Revelica, and what the server offers.
Revelica exposes your workspace over the Model Context Protocol, so your agent can read the product context your team has built and write what it learns back into the same place. For Claude or ChatGPT, add the plugin instead: Claude and Claude Code, ChatGPT and Codex.
Connect
Any client that speaks streamable HTTP and supports OAuth connects with the server URL alone:
https://api.revelica.com/mcpThe first time it connects, the client registers itself and opens a browser window for you to sign in. After that it holds a token scoped to your own account. Revelica doesn't issue API keys, so a client without OAuth support can't connect. You need a Revelica workspace (get Revelica free), and pricing covers which plans can save from your agent.
Cursor
Add the server to .mcp.json in your project, or to your global Cursor MCP
configuration:
{
"mcpServers": {
"revelica": {
"type": "http",
"url": "https://api.revelica.com/mcp"
}
}
}Gemini CLI
Add the server to ~/.gemini/settings.json. Gemini CLI uses httpUrl for
streamable HTTP servers (url means Server-Sent Events):
{
"mcpServers": {
"revelica": {
"httpUrl": "https://api.revelica.com/mcp"
}
}
}Run /mcp and sign in when the browser opens.
Any other client
Most clients only need the URL. If yours asks for a transport, choose streamable HTTP.
The server describes itself in its
server card, and it is
listed in the MCP registry as
com.revelica/revelica.
Tools
8 tools, 5 of them read-only. Clients that understand tool annotations can run the read-only ones without asking every time, and ask before anything writes.
| Tool | What it does | Access |
|---|---|---|
show | Show the user one thing. | Read |
query | Search/filter records in the Revelica workspace by criteria. | Read |
read | Fetch a specific resource by ID. | Read |
create | Create a new artifact or a new version of an existing one. | Write |
update | Update specific fields on an existing artifact or entity. | Write |
load_skill | Load an agent skill's full instructions and reference materials. | Read |
list_skills | List the Revelica skills you can load in this workspace. | Read |
send_feedback | Send Revelica's developers a short report when a Revelica tool got in your way or worked notably well. | Write |
query filters by any record type in your workspace, and when it does, the
response carries that type's schema, so an agent knows the shape before it
writes anything.
Skills
Skills are Revelica's playbooks: instructions an agent loads with load_skill,
along with the workspace data the playbook starts from. They live on the server,
so every client gets the current version and the Revelica app runs the same
ones. The server's instructions tell the agent which skill fits which job:
| Skill | What it's for |
|---|---|
setup-revelica | Sets up the business model, customer profile and team goals. Required: nothing works until it runs. |
drive-product-outcome | Plans the work toward a product goal as ordered tasks. Use for a new goal, what's next, or progress. |
business-strategy | Defines vision, business model, value propositions and goals. Use when setting or changing course. |
product-insights | Researches customers, competitors and markets, and saves interviews and notes. Use for any research. |
product-strategy | Decides which bets to make or drop, and why. Use when asking if something is worth building. |
discover-solutions | Generates solution ideas and writes specs and PRDs. Use when designing or specifying a feature. |
test-product-risks | Tests risky assumptions with surveys, data, experiments or prototypes. Use to check if it'll work. |
implement-spec | Gives a coding agent a spec's context and records what shipped. Use before and while building. |
The Claude and ChatGPT plugins carry the same skills, and in Claude Code each is also a slash command. Every plugin manifest is public at github.com/revelica/skills.
Permissions and security
Every request is signed in as you. Access is enforced in the database by row-level security, so an agent only ever sees and changes data in the workspace you belong to. Never another customer's, and never another workspace's inside your own company.
Revelica does not read your chat history, conversation summaries, or local files. Only what a tool is called with reaches the server.
Connect without a Revelica workspace and every tool returns an explanatory error pointing you at app.revelica.com, rather than failing silently.
See the Privacy Policy for data handling, retention, and sub-processors.
FAQ
Why won't it connect?
Clear the stored tokens for the server in your client and connect again. The
client re-registers and gets fresh ones. In Claude Code and Gemini CLI, /mcp
shows the connection state and lets you sign in again.
Do I need the plugin, or just the server?
The server alone gives you every tool and every skill. In Claude and ChatGPT the plugin also lists the skills in the host, so they show up as suggestions (and, in Claude Code, as slash commands).
I'm reviewing Revelica for a plugin directory
Test setup is in
REVIEWING.md. The
invite link for the demo workspace is in your review notes.