Back to home

DeeplyClear MCP

Use DeeplyClear inside your AI tools

Connect an AI agent to your DeeplyClear workspace so it can list maps, read map structure, create new maps, and apply node or edge updates.

Jump to a platform

ChatGPTCodexClaude CodeOpenCodeCursorOther MCP clients

Jump to a platform

ChatGPTCodexClaude CodeOpenCodeCursorOther MCP clients

Hosted MCP endpoint

Use OAuth when your client supports it. Use a scoped DeeplyClear API key for OpenCode, Cursor, scripts, CI, and manual connections.

https://mcp.deeplyclear.com

Before You Start

Sign in to DeeplyClear, then open AI tool connections to create an API key when your client needs manual authentication. API keys are shown once and can be revoked from the same page.

Recommended

OAuth

Best for interactive clients. The user signs in to DeeplyClear and approves access without copying a secret.

Manual authentication

API key

Best for clients without OAuth and for automation. Give every client a separate, minimally scoped key and keep it out of source control.

What Your Agent Can See

Map tools return structured nodes and edges, an inline PNG preview image, and a live DeeplyClear map link. ChatGPT can render the interactive canvas widget when the DeeplyClear app is connected; other MCP clients can use the PNG preview and link.

The read, create, prompt-edit, elaborate-node, and operation tools include previews automatically. Agents can also call `deeplyclear_preview_map` when they only need a fresh visual snapshot.

Published plugin

ChatGPT

Open in ChatGPT
  1. 1Open the DeeplyClear plugin page in ChatGPT and select Install.
  2. 2Sign in when prompted, then approve access to your DeeplyClear workspace.
  3. 3Start a new chat and ask ChatGPT to create a DeeplyClear map from your notes, conversation, or project context.

DeeplyClear is published in the ChatGPT Plugins directory, so normal setup no longer requires developer mode, a manual connector, or an API key.

OAuth or API key

Codex

Codex MCP docs
  1. 1Add the MCP server to your global ~/.codex/config.toml or a trusted project .codex/config.toml.
  2. 2Run codex mcp login deeplyclear and approve the browser-based DeeplyClear OAuth screen.
  3. 3Restart Codex or open /mcp in the Codex TUI to confirm the server is loaded.
[mcp_servers.deeplyclear]
url = "https://mcp.deeplyclear.com"

If you need non-interactive setup, create a DeeplyClear API key from AI tool connections, set `DEEPLYCLEAR_API_KEY`, and use the API-key config instead.

[mcp_servers.deeplyclear]
url = "https://mcp.deeplyclear.com"
bearer_token_env_var = "DEEPLYCLEAR_API_KEY"

OAuth or API key

Claude Code

Claude Code MCP docs
  1. 1Run both commands below to add DeeplyClear as a user-scoped HTTP MCP server and start OAuth.
  2. 2Approve the browser-based DeeplyClear OAuth screen.
  3. 3Open the Code tab in the Claude desktop app. The user-scoped MCP registration is shared with local Claude Code projects.
claude mcp add --transport http --scope user deeplyclear https://mcp.deeplyclear.com
claude mcp login deeplyclear

For non-interactive configuration, use a dedicated API key in an environment variable with Claude Code's `.mcp.json` expansion.

claude mcp add --transport http --scope user deeplyclear https://mcp.deeplyclear.com \
  --header "Authorization: Bearer YOUR_DEEPLYCLEAR_API_KEY"
{
  "mcpServers": {
    "deeplyclear": {
      "type": "http",
      "url": "https://mcp.deeplyclear.com",
      "headers": {
        "Authorization": "Bearer ${DEEPLYCLEAR_API_KEY}"
      }
    }
  }
}

API key

OpenCode

OpenCode MCP docs
  1. 1Create a DeeplyClear API key in AI tool connections. Select only the permissions OpenCode needs.
  2. 2Store the key in the DEEPLYCLEAR_API_KEY environment variable.
  3. 3Add the remote server to your user-level or project-level opencode.json file.
  4. 4Run opencode mcp list, then ask OpenCode to list your DeeplyClear maps.
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "deeplyclear": {
      "type": "remote",
      "url": "https://mcp.deeplyclear.com",
      "enabled": true,
      "oauth": false,
      "headers": {
        "Authorization": "Bearer {env:DEEPLYCLEAR_API_KEY}"
      }
    }
  }
}

OpenCode can use the DeeplyClear tools, preview images, and map links. It does not currently render the interactive MCP Apps canvas inline.

API key

Cursor

Cursor MCP docs
  1. 1Open Cursor settings and find the MCP or Tools & Integrations section.
  2. 2Create or edit your mcp.json file.
  3. 3Paste a remote MCP server entry for DeeplyClear, then restart or reconnect MCP tools.
{
  "mcpServers": {
    "deeplyclear": {
      "url": "https://mcp.deeplyclear.com",
      "headers": {
        "Authorization": "Bearer YOUR_DEEPLYCLEAR_API_KEY"
      }
    }
  }
}

Store this in a user-level Cursor config when possible. If you keep MCP config in a repository, do not commit a real API key.

Other MCP Clients

Use Streamable HTTP, the hosted endpoint, and an `Authorization` header:

Transport: Streamable HTTP
URL: https://mcp.deeplyclear.com
Authorization: Bearer YOUR_DEEPLYCLEAR_API_KEY

After connecting, ask the agent to list your DeeplyClear maps or create a new map from a prompt. Access is limited to the workspace and permissions assigned to the API key.

References

DeeplyClear for ChatGPTOpenAI Apps SDK authCodex MCPClaude Code MCPCursor MCPOpenCode MCP