Model Context Protocol - Infisical

About the Infisical Docs MCP server

The Model Context Protocol (MCP) is an open protocol that creates standardized connections between AI applications and external services like documentation. Infisical hosts an MCP server that exposes its documentation to any MCP client — Claude, Claude Code, Cursor, VS Code, ChatGPT, and others — so your agent can answer questions from Infisical's source documentation instead of relying on its training data.

When an AI tool is connected to the Infisical MCP server, it can search the documentation and retrieve full page content directly while generating a response. This means:

Up-to-date answers: agents pull from current documentation, not stale training data.
Source-grounded responses: agents answer from Infisical's documentation rather than guessing.
No copy-pasting: you don't need to paste documentation snippets into your prompts.

<Tip> The MCP server pairs well with the [Infisical Skills](https://github.com/infisical/ai-skills) repo. The MCP server gives agents access to the documentation; skills teach agents how to use Infisical effectively (project structure, conventions, common workflows). Connect both for the best results. </Tip>

MCP server URL

The Infisical Docs MCP server is publicly available at:

https://infisical.com/docs/mcp

No authentication is required — anyone can connect their AI tool to it.

Connect to the Infisical MCP server

<Tabs> <Tab title="Claude"> <Steps> <Step title="Open Claude's connector settings"> Navigate to the [Connectors](https://claude.ai/settings/connectors) page in your Claude settings. </Step> <Step title="Add the Infisical MCP server"> 1. Select **Add custom connector**. 2. Add the Infisical MCP server: - **Name**: `Infisical` - **URL**: `https://infisical.com/docs/mcp` 3. Select **Add**. </Step> <Step title="Use the MCP server in a chat"> 1. In a Claude chat, select the attachments button (the plus icon). 2. Select the Infisical MCP server. 3. Ask Claude a question about Infisical. </Step> </Steps>

See the [Model Context Protocol documentation](https://modelcontextprotocol.io/docs/tutorials/use-remote-mcp-server#connecting-to-a-remote-mcp-server) for more details.

</Tab> <Tab title="Claude Code"> Run the following command to add the Infisical MCP server to Claude Code:

```bash
claude mcp add --transport http Infisical https://infisical.com/docs/mcp
```

Verify the connection:

```bash
claude mcp list
```

See the [Claude Code documentation](https://docs.anthropic.com/en/docs/claude-code/mcp#installing-mcp-servers) for more details.

</Tab> <Tab title="Cursor"> <Steps> <Step title="Open MCP settings"> 1. Use <kbd>Command</kbd> + <kbd>Shift</kbd> + <kbd>P</kbd> (<kbd>Ctrl</kbd> + <kbd>Shift</kbd> + <kbd>P</kbd> on Windows) to open the command palette. 2. Search for **Open MCP settings**. 3. Select **Add custom MCP**. This opens the `mcp.json` file. </Step> <Step title="Configure the Infisical MCP server"> In `mcp.json`, add:

    ```json
    {
      "mcpServers": {
        "Infisical": {
          "url": "https://infisical.com/docs/mcp"
        }
      }
    }
    ```
  </Step>
  <Step title="Test the connection">
    In Cursor's chat, ask "What tools do you have available?" Cursor should show the Infisical MCP server as an available tool.
  </Step>
</Steps>

See [Installing MCP servers](https://docs.cursor.com/en/context/mcp#installing-mcp-servers) in the Cursor documentation for more details.

</Tab> <Tab title="VS Code"> Create a `.vscode/mcp.json` file in your workspace and add:

```json
{
  "servers": {
    "Infisical": {
      "type": "http",
      "url": "https://infisical.com/docs/mcp"
    }
  }
}
```

See the [VS Code documentation](https://code.visualstudio.com/docs/copilot/chat/mcp-servers) for more details.

</Tab> </Tabs>

Using the MCP server alongside other tools

AI tools can connect to multiple MCP servers at once. Connected servers do not consume context until the AI invokes a search tool, and the AI decides when to search based on query relevance — it does not search every connected server for every question.

A few practices to get the most out of the Infisical MCP server:

Be specific in prompts: mention Infisical explicitly when you want the agent to consult the documentation (e.g., "Using Infisical's CLI, how do I…").
Pair with skills: install the Infisical Skills for opinionated guidance on top of raw documentation access.
Disconnect unused servers: if you have many MCP servers connected, remove ones you aren't actively using to keep responses focused.

FAQ

<AccordionGroup> <Accordion title="What's the difference between the MCP server and the Infisical Skills?"> The MCP server gives an AI agent the ability to search and read Infisical's documentation on demand. The [Infisical Skills](https://github.com/infisical/ai-skills) are reusable instructions that teach an agent how to work with Infisical (conventions, common workflows, etc.). The MCP server provides knowledge; skills provide know-how. They're complementary. </Accordion> <Accordion title="Do I need an Infisical account to use the MCP server?"> No. The Infisical Docs MCP server is publicly available and does not require authentication. It exposes only the public documentation. </Accordion> <Accordion title="Can I use the MCP server with any AI tool?"> Any AI tool that supports the Model Context Protocol over HTTP can connect to it. This includes Claude, Claude Code, Cursor, VS Code (with Copilot), and others. </Accordion> </AccordionGroup>