communicationapi_key

Botpress

Botpress is an open-source platform for building, deploying, and managing chatbots.

Verdict

Botpress lets your team manage conversational AI bots from inside Switchy. @mention it to list conversations, pull bot issues, browse workspaces, or manage files and tags. This is most useful for teams running customer-facing chatbots who want to triage errors, audit conversation threads, or organize bot assets without leaving their AI workspace. You'll need a Botpress API key with read/write permissions. The integration surfaces eight tools — enough to handle common bot ops tasks, but you'll still visit the Botpress dashboard for advanced bot configuration or analytics.

Common use cases

  • Triage bot errors during standup
  • Audit recent customer chat threads
  • Organize bot files by tag
  • Check workspace status before deployment
  • Delete outdated bot assets from chat

Integration

Vendor
Botpress
Category
communication
Auth
API_KEY
Tools
8
Composio slug
botpress

Tools

  • Delete File
    destructive

    Tool to delete a file by its id or key. use after confirming the file exists.

  • Get Account

    Tool to get details of the authenticated account. use after confirming valid credentials.

  • LIST_BOT_ISSUES

    Tool to list issues associated with a specific bot. use when you need to discover errors or configuration problems tied to a bot, optionally paginating through results.

  • LIST_CONVERSATIONS

    Tool to list all conversations. use when you need to retrieve and page through chat threads.

  • LIST_FILE_TAGS

    Tool to list all tags used across all bot files. use when you need to retrieve or display file tag metadata; supports pagination via nexttoken.

  • LIST_FILE_TAG_VALUES

    Tool to list all values for a given file tag across all files. use after determining the tag name; supports pagination via nexttoken.

  • LIST_PUBLIC_WORKSPACES

    Tool to retrieve a list of public workspaces. use when browsing publicly available workspaces before selection.

  • LIST_WORKSPACES

    Tool to retrieve a list of workspaces. use when you need to list and page through your botpress workspaces, optionally filtering by handle.

Setup

Setup guide

  1. 11. In Switchy, open your workspace settings and navigate to the MCP Integrations section. 2. Click 'Add Integration' and select Botpress from the communication category. 3. Log into your Botpress account and generate an API key from the Developer Portal under API Keys — ensure it has permissions for conversations, files, and workspaces. 4. Paste the API key into Switchy's connection form and click 'Connect'. 5. Switchy will validate the key by calling the Get Account tool; if successful, you'll see a green checkmark. 6. Open any Space, type '@Botpress list my workspaces' and send — if you see a list of workspaces returned, the connection is live. 7. You can now @mention Botpress in any message to invoke its tools directly from your team's conversation.

What teammates see: by default, memories from Botpress are scoped to the Space (PROJECT visibility) - you can mark any memory PRIVATE or share it ORG-wide.

Works well with

Top models

Compatibility data appears once enough Spaces have used this MCP together with a given model.

How Switchy teams use it

Not enough Spaces yet to publish anonymised usage stats (we require ≥ 50 Spaces per week).

Starter prompts

List Recent Bot Issues

@Botpress list all issues for bot ID abc123. Show me the most recent 10 entries so I can see what's breaking.
Open in a Space →

Show All Conversations

@Botpress list all conversations from the past week. Include the first 20 results so I can scan for escalations.
Open in a Space →

Get Workspace Details

@Botpress list all workspaces I have access to. I need to verify the production workspace handle before deploying.
Open in a Space →

Find Files by Tag

@Botpress list all values for the tag 'version' across my bot files. I want to see which versions are still in use.
Open in a Space →

Delete Unused File

@Botpress delete the file with ID xyz789. I've verified it's not referenced in any active conversation flow.
Open in a Space →

Example outputs

Illustrative - representative of the model's voice and quality, not literal recordings.

Prompt

@Botpress list all conversations from the last 7 days and group them by bot, showing me which bots are getting the most user engagement.

Output

Retrieved 847 conversations across 4 active bots. Your 'Customer Support Bot' handled 512 conversations (60%), 'Sales Qualifier Bot' handled 203 (24%), 'FAQ Bot' handled 98 (12%), and 'Onboarding Assistant' handled 34 (4%). The Customer Support Bot shows peak activity between 9 AM–11 AM EST, with an average of 4.2 messages per conversation. This data reflects conversations created since January 15, 2025, filtered by your workspace's default timezone.

Notes

This example combines LIST_CONVERSATIONS with AI summarization to surface engagement patterns. Requires an API key with read access to conversations across all bots in your workspace. Pagination may be needed for workspaces with thousands of conversations; the MCP handles nextToken internally but large result sets can slow response time.

Prompt

@Botpress check the issues for bot ID 'bot_3x9k2' and tell me if any are blocking production deployment.

Output

Found 3 open issues for bot 'bot_3x9k2'. Two are warnings: 'Intent confidence threshold below 0.7 in fallback flow' and 'Missing slot validation for email input in lead-capture node.' One is critical: 'Webhook endpoint returning 503 errors for Stripe integration (last 6 hours).' The webhook issue is blocking production—users cannot complete payment flows. The intent and validation warnings are non-blocking but should be addressed before scaling traffic.

Notes

This example uses LIST_BOT_ISSUES to surface configuration and runtime problems. The MCP returns raw issue metadata; the AI interprets severity and impact. Useful for pre-deployment checks or incident triage. Note that issue detection depends on Botpress's internal monitoring—external integration failures may not appear immediately.

Prompt

@Botpress delete all files tagged 'temp-training-data' from my workspace and confirm how many were removed.

Output

Identified 17 files tagged 'temp-training-data' using LIST_FILE_TAG_VALUES. Successfully deleted all 17 files via Delete File. Removed files include 12 CSV exports (conversation logs from staging), 3 JSON intent samples, and 2 markdown documentation drafts. Total storage freed: approximately 8.4 MB. No files remain with the 'temp-training-data' tag in your workspace.

Notes

This example chains LIST_FILE_TAG_VALUES with Delete File to perform bulk cleanup. Deletion is irreversible—the MCP does not confirm each file before removal, so verify the tag filter carefully. Requires API key with file write permissions. Use cautiously in production workspaces; consider exporting files to backup storage before running destructive operations.

Use-case deep-dives

Support bot health monitoring

When Botpress MCP makes sense for chatbot ops teams

A 3-person customer success team runs a Botpress chatbot handling 200+ conversations daily. They use Switchy to check bot health during morning standup: one agent pulls LIST_BOT_ISSUES to surface configuration errors, another scans LIST_CONVERSATIONS to spot stuck threads, and the team lead reviews Get Account to confirm API quota. This MCP wins when your bot is already on Botpress and you need quick diagnostics without opening the vendor dashboard. The trade-off: if you're managing bots across multiple platforms (Intercom, Zendesk, custom), this MCP only covers Botpress—you'll still context-switch for the others. Best fit for teams running 1-3 Botpress bots who want faster triage, not a unified bot-ops layer.

Chatbot knowledge base tagging

Using Botpress MCP to organize bot training files

A solo founder building a SaaS onboarding bot uploads 40 help articles as Botpress files, then realizes she can't remember which topics each file covers. She opens Switchy, runs LIST_FILE_TAGS to see her tagging schema, then LIST_FILE_TAG_VALUES to audit which files are tagged 'billing' versus 'setup'. When a file is misplaced, she uses Delete File to clean it up before re-uploading with correct tags. This scenario works if you're hands-on with Botpress file management and treat Switchy as a faster alternative to clicking through the web UI. It doesn't work if your bot's knowledge base lives in Notion or Google Drive—those need different MCPs. Choose this MCP when Botpress is your single source of truth for bot content.

Multi-workspace bot deployment review

When to use Botpress MCP for agency bot handoffs

A 5-person chatbot agency builds custom Botpress bots for clients, each in a separate workspace. During client handoff calls, the account manager shares their screen in Switchy, runs LIST_WORKSPACES to confirm the client's workspace is live, then LIST_PUBLIC_WORKSPACES to verify the bot isn't accidentally exposed. The MCP saves 2-3 minutes per handoff by skipping Botpress login and navigation. This makes sense if you manage 5+ client workspaces and do frequent audits. It's overkill if you only maintain one or two bots—you'll remember their workspace handles without tooling. The buying threshold: if you're doing more than 10 workspace checks per week, the MCP pays for itself in saved clicks.

Frequently asked

What does the Botpress MCP let me do in Switchy?

It connects your Botpress workspace so Switchy can read conversations, list bot issues, manage files, and browse workspaces. You can ask Switchy to pull chat threads, check for bot configuration errors, or retrieve file metadata without leaving the conversation. It's useful for teams debugging bots or reviewing customer interactions alongside other tools.

Do I need admin access to connect Botpress?

You need a Botpress API key with read and write permissions for the resources you want Switchy to access. Botpress uses API key authentication, not OAuth, so whoever generates the key controls what Switchy can see. If you only want read access to conversations, scope the key accordingly when you create it in your Botpress account settings.

Can the MCP send messages or update bot logic?

No. The current tool set focuses on reading data—listing conversations, checking bot issues, managing file tags, and browsing workspaces. It can delete files, but it won't modify bot flows, send messages to users, or change workspace settings. If you need to update bot behavior, use Botpress Studio directly or their API.

Why use this instead of logging into Botpress?

Switchy lets you query Botpress data in the same thread where you're working with Slack messages, GitHub issues, or Notion pages. Instead of switching tabs to check if a bot has errors or pull a conversation transcript, you ask once and get the answer inline. It's faster for triage and cross-tool workflows.

Who on the team should connect it?

Whoever owns your Botpress workspace and can generate API keys. That's usually a product manager, support lead, or engineer responsible for the bot. Once connected, anyone in your Switchy workspace can query Botpress data through the shared assistant, so you don't need multiple keys or logins.

Data last verified 607 hours ago.Sources aggregated hourly to weekly. See docs/architecture/model-directory.md.