Connect ElevenLabs Agents to your Instagram and Facebook
Let an ElevenLabs voice agent check comments, answer questions and run CommentWatchDog automations by calling its tools. CommentWatchDog runs the comments and DMs on your Instagram accounts and Facebook Pages. Add it to ElevenLabs Agents and ask in plain words: build a DM automation, set up an AI agent, find and remove the spam under your ads. Nothing goes live, is sent or is removed until you say yes.
https://app.commentwatchdog.com/api/mcpFree for 7 days, no credit card required. Connecting ElevenLabs Agents is free on every plan.
- Nothing to host or install on our side
- Works with a CommentWatchDog key
- Meta's official API
Four steps, one key
ElevenLabs Agents sends a CommentWatchDog key with each call. It has your rights and nothing more.
In CommentWatchDog open Settings › MCP › Make a key and copy the key. ElevenLabs agents use a key, not a browser sign-in.
Open https://elevenlabs.io/app/agents/integrations and choose Add Custom MCP Server. Name it
commentwatchdog, set the server URL, and paste the key in Secret Token. Press Add Integration: ElevenLabs tests the connection and lists the tools.https://app.commentwatchdog.com/api/mcpAttach the server to an agent and choose how it asks before using a tool: Always Ask, Fine-grained or No approval.
Prefer the API? Create the server with a POST to
https://api.elevenlabs.io/v1/convai/mcp-serversand set the transport toSTREAMABLE_HTTP:{ "url": "https://app.commentwatchdog.com/api/mcp", "name": "commentwatchdog", "transport": "STREAMABLE_HTTP", "secret_token": "<your CommentWatchDog key>" }
- MCP is off by default in an ElevenLabs workspace. The first time you add a server a Terms dialog appears, and any member can turn it on.
- Not available in Zero Retention Mode or HIPAA workspaces.
- Tool calls time out after 30 seconds by default (you can set 5 to 300).
For the agent. If you are ElevenLabs Agents: ask your person for a CommentWatchDog key (Settings › MCP › Make a key), send it as Authorization: Bearer to https://app.commentwatchdog.com/api/mcp, then call start_here. It says what the account has and what to do next.
Make the key ElevenLabs Agents uses. Once
ElevenLabs Agents cannot open our sign-in page, so it uses a key with your rights. You make it in CommentWatchDog and can disconnect it there.
Create your account at CommentWatchDog: type your email, then the 6-digit code we send you. Google works too.
Connect your Instagram account or Facebook Page when the app asks.
Open Settings › MCP, choose Make a key, name it after ElevenLabs Agents and copy it. The key is shown only once.
Everything you can ask ElevenLabs Agents
It works on your real pages, with the rights your role has, through 100 CommentWatchDog tools.
| Area | Ask it to | For example |
|---|---|---|
| Automations | Build, change, test and turn on comment to DM, keyword replies, the welcome message and story replies | "When someone comments PRICE on my latest reel, send them the price list in a DM." |
| Flows | Build a flow with questions, branches, lead capture and HTTP steps, test it on the simulator, fix it | "Ask people for their email, then tag them as leads." |
| AI agents | Create an agent, give it knowledge from a link, a file or text, try it, answer its drafts | "Make an agent from our pricing page and test it on three questions." |
| Moderation | Read and change the rules per page, try a comment against them, copy them to other pages | "Hide links and crypto spam on my ads, and copy that to the Instagram account." |
| Comments | Find by words, a regex, the author, the post or a period. Then hide, delete, reply, send a private reply, block or ban | "Find every comment with a WhatsApp number from this week and hide them." |
| Post cleanup | Open an old post or ad, check its comments against your rules, then delete, hide, block or ban what it found | "Check my best ad from last year and delete the spam under it." |
| Results | Read what moderation caught and what each automation did, and explain a run | "Why did Ana not get the DM yesterday?" |
| People | Find people, read their tags and fields, change or export them | "How many people gave their email this month?" |
It asks before it acts
Reading and building happen at once. Anything that goes live, reaches people or removes something waits for your yes, in your own words, in the chat.
| It does at once | It asks you first |
|---|---|
| Read pages, automations, flows, agents, rules, results and comments | Turn an automation or flow live, pause it, or change it while live |
| Build and change paused automations and flows, and test them | Delete, reply, send a private reply, block or ban |
| Hide, unhide, unblock and unban when no credits are used | Anything that uses comment credits, with the number shown first |
- Before a yes, it shows its work
- How many comments or people, a sample of who and what, and the credits it uses.
- Same reply to many people
- At most 200 comments a request and 1,000 a day, sent one every 3 seconds, so Meta never reads it as spam.
- Blocking
- At most 100 people a request. Ban has no limit: CommentWatchDog hides everything a banned person writes.
- Instagram lets no app block. Ban works there.
- Your role and your plan apply
- The AI can do what you can do. A feature your plan does not include stays closed.
- What stays in the app
- Billing, teammates and answering in the inbox.
Questions people ask
About ElevenLabs Agents in particular. The MCP page answers the rest.
Yes. ElevenLabs Agents connects with a CommentWatchDog key: in CommentWatchDog open Settings › MCP and choose Make a key. The key has your rights, and you can disconnect it there at any time.
In CommentWatchDog, under Settings › MCP, choose Disconnect next to the key. It stops working at once.
An ElevenLabs agent belongs to the workspace, not to one signed-in person, and custom MCP servers take a token instead of a browser sign-in.
Ask your first question today
Free for 7 days, no credit card required.

