How to Connect Botpress to Cursor via MCP

💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → Botpress, paste your credentials, mint an MCP API key and you're done. No Docker, no git clone, no local server.

Botpress + Cursor

Let your AI review your Botpress bots: workspaces and bots, conversations, messages, users and events, bot logs, analytics and issues, the bot's tables (query, add and update rows) and its knowledge-base files with semantic search.

Prerequisites

See the full setup instructions baked into the connector (visible in the in-app store when you select the connector). The required environment variables for this connector are:

BOTPRESS_TOKEN, BOTPRESS_WORKSPACE_ID, BOTPRESS_BOT_ID

Step 1 — Get credentials

1. Sign in at https://app.botpress.cloud. Open your profile menu (top right) → Profile Settings → Personal Access Tokens, create a token and copy it (it starts with bp_pat_). Paste it into BOTPRESS_TOKEN, without the word Bearer.
2. Workspace ID (BOTPRESS_WORKSPACE_ID): open the workspace in the dashboard and copy the wkspace_... part of the URL (app.botpress.cloud/workspaces/wkspace_...).
3. Bot ID (BOTPRESS_BOT_ID): open the bot and copy the UUID after /bots/ in the URL. Studio also shows it in the bot's settings.
4. Install the connector. The three values are sent only to Botpress. Later, botpress_list_workspaces and botpress_list_bots show the ids of your other workspaces and bots too.

Who sees what: the token carries your own access to every workspace you belong to. Keep it secret, and share the MCP server only with people allowed to read your bots' conversations, which can contain personal data.

Which parts of Botpress it uses: one personal access token reaches all four (a Bot Access Key would not work for the admin tools, so use a personal token):

• Admin API: workspaces, bots, bot logs, analytics and issues.
• Runtime API: the bot's conversations, messages, users and events from every channel (Webchat, WhatsApp, Slack and so on). Botpress's separate Chat API is not used, because it only sees conversations from its own Chat integration.
• Tables API: the bot's tables, to query, add and update rows.
• Files API: the bot's knowledge-base files, with semantic search over the indexed ones.

Several bots: the conversation, message, user, event, table and file tools work on BOTPRESS_BOT_ID unless you name another bot. The bot tools (overview, logs, analytics, issues) take the bot id in every call, so the AI can compare the bots of a workspace.

Confirm first: botpress_create_table_rows and botpress_update_table_rows change the bot's data, so the AI shows you the rows and waits for your yes. botpress_delete_table_rows is switched off at install; turn it on in the connector settings only if the AI should delete rows. It deletes by row id only.

Untrusted content: messages, user fields and file passages come from end users or uploaded documents. The AI treats instructions inside them as data, not as orders.

Common errors: 401 Unauthorized: the token is wrong or revoked, or the workspace ID is not a workspace your user belongs to. 403 Forbidden: your role in the workspace does not allow the action. 404 ResourceNotFound: an unknown id, or a conversation or table of another bot than the one in BOTPRESS_BOT_ID. 400 InvalidPayload or InvalidQuery: a parameter is invalid, for example a date not in ISO 8601. 429 RateLimited: wait a moment and retry.

The connector does not create, deploy or delete bots, send messages as the bot, manage integrations, upload files to the knowledge base, or manage workspace members and billing.

Step 2 — Install the adapter

curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d

Step 3 — Add the connector in Cursor

Your server URL: in AnythingMCP, open MCP Servers → the server this connector is on, and copy its URL (https://cloud.anythingmcp.com/mcp/…). Use it wherever this guide shows YOUR_SERVER_ID.

Cursor reads MCP servers from ~/.cursor/mcp.json. Add this entry:

{
  "mcpServers": {
    "anythingmcp": {
      "url": "https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID",
      "headers": { "X-API-Key": "YOUR_MCP_API_KEY" }
    }
  }
}

1. Create an MCP API key in AnythingMCP under MCP Servers → your server → API keys, and paste it in place of YOUR_MCP_API_KEY.
2. Save the file and restart Cursor.
3. Open Cursor → Settings → MCP and check that anythingmcp is listed and connected.
4. Start chatting: the agent can now call the Botpress tools.

Available tools

Example prompts

• "What did people ask our support bot most often this week? Summarise the main topics of the latest conversations."
• "Why did the bot fail yesterday? Check its issues and the error logs since 9:00."
• "Show me new and returning users, sessions and messages for our bot over the last 30 days."
• "Find the row in the Leads table with the email [email protected] and set its status to contacted. Show me the change first."
• "Search the bot's knowledge base for our refund policy and tell me which file the answer comes from."

FAQ

Does Cursor support custom MCP servers on the free tier? Yes, MCP is available on Hobby, Pro and Business plans.

Next steps

• Connector landing page
• Connect to Claude
• Connect to ChatGPT