# Connect OpenClaw to CommentWatchDog (Instagram and Facebook MCP)

> Add CommentWatchDog to OpenClaw with two commands. Then ask it to build Instagram and Facebook DM automations, set up AI agents and remove spam comments. Nothing goes live, is sent or is removed without your yes.

- MCP address (remote, Streamable HTTP, OAuth sign-in): https://app.commentwatchdog.com/api/mcp
- Server name: commentwatchdog
- Tested by us: 13 November 2026, OpenClaw 2026.11.3
- This page for people: https://commentwatchdog.com/mcp/openclaw
- Every other app: https://commentwatchdog.com/mcp.md

## For OpenClaw itself

If you are OpenClaw: run the first two commands, give your person the page that opens so they can sign in and press Allow, then call `start_here`. It says what the account has and what to do next.

## Connect

1. Add CommentWatchDog to OpenClaw.

   ```
   openclaw mcp set commentwatchdog '{"url":"https://app.commentwatchdog.com/api/mcp","transport":"streamable-http","auth":"oauth"}'
   ```

2. Sign in. OpenClaw opens a CommentWatchDog page in your browser. Sign in, or create your account there, and press Allow. The browser hands the sign-in back to OpenClaw by itself.

   ```
   openclaw mcp login commentwatchdog
   ```

3. Check it. OpenClaw lists every CommentWatchDog tool it can now use.

   ```
   openclaw mcp probe commentwatchdog
   ```

- OpenClaw on another machine, a server you reach over SSH for example: the browser cannot hand the sign-in back to it, and OpenClaw prints the command that finishes it, `openclaw mcp login commentwatchdog --code <code>`.
- OpenClaw asks you before each CommentWatchDog call it makes. That is OpenClaw's own check, on top of CommentWatchDog's yes for anything that goes live, sends or removes.
- Our run used OpenClaw 2026.11.3 on Node 24. That version refused to start on Node 25.

## No account yet

1. The page OpenClaw opens says who is waiting: Create your account to connect OpenClaw.
2. Type your email, then the 6-digit code we send you. Google works too.
3. The first page of your new account is the approval. Press Allow, and a new tab opens to connect your Instagram or Facebook. OpenClaw can build once one is connected.

A person allows OpenClaw in a browser. No agent can create the account or give that consent itself.

## What you can ask

| 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

| 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: 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

### Does OpenClaw need an API key for CommentWatchDog?

No. OpenClaw signs in with OAuth: `openclaw mcp login` opens a CommentWatchDog page, you press Allow, and OpenClaw keeps the sign-in. Nothing is pasted.

### Can OpenClaw create my CommentWatchDog account?

No. The sign-in page it opens lets you create the account yourself, with your email and a 6-digit code or with Google. Then you press Allow. No agent can do either step for you.

### Why does OpenClaw ask me before every call?

OpenClaw asks before calling tools from a server it has not been told are safe to run. CommentWatchDog asks again, in the chat, before anything goes live, is sent or is removed.

### How do I disconnect OpenClaw?

In CommentWatchDog, under Settings › MCP, choose Disconnect next to it. It stops working at once.
