# Connect Claude to CommentWatchDog (Instagram and Facebook MCP)

> Connect Claude to Instagram and Facebook with CommentWatchDog's MCP server. Sign in once, then ask it to build DM automations and remove spam comments.

- MCP address (remote, Streamable HTTP, OAuth sign-in): https://app.commentwatchdog.com/api/mcp
- Server name: commentwatchdog
- Steps from Anthropic's docs, checked 13 November 2026; not yet run by us
- This page for people: https://commentwatchdog.com/mcp/claude
- Every other app: https://commentwatchdog.com/mcp.md

## For Claude itself

If you are Claude: add `https://app.commentwatchdog.com/api/mcp` as a remote MCP server, 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. In Claude, open Customize › Connectors and choose Add custom connector.

2. Name it CommentWatchDog and paste this address:

   ```
   https://app.commentwatchdog.com/api/mcp
   ```

3. Choose Connect and press Allow on the CommentWatchDog page that opens. Then turn it on in a chat from the tools menu.

4. Shortcut: open this link, confirm the external link notice, and the add dialog opens already filled in.

   ```
   https://claude.ai/customize/connectors?modal=add-custom-connector&connectorName=CommentWatchDog&connectorUrl=https%3A%2F%2Fapp.commentwatchdog.com%2Fapi%2Fmcp
   ```

- Works in Claude on the web, the desktop app and the phone. The Free plan allows one custom connector.
- On Team and Enterprise plans an Owner adds the connector first, at claude.ai/admin-settings/connectors.
- You cannot edit the sign-in settings after adding. To change them, remove the connector and add it again.

## No account yet

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

A person allows Claude 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 Claude need an API key for CommentWatchDog?

No. Claude signs in with OAuth: it opens a CommentWatchDog page, you press Allow, and it keeps the sign-in. Nothing is pasted.

### How do I disconnect Claude?

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