Fluxguard MCP server
12 operations1 webhook
Website change monitoring with Fluxguard - add and delete monitored pages, start crawls, read captured page data, and manage the webhooks and site categories that deliver change alerts.
Try Fluxguard with your agent
Connect Fluxguard, then paste this into Claude, ChatGPT or Cursor. For ideas from other apps, see the use cases.
Using Corsair, show me what you can do in Fluxguard on my account, then run one read-only example and show me the result.
Fluxguard tools and triggers
Tools are what your agent can do in Fluxguard through Corsair's MCP server. Triggers are the Fluxguard events a routine can start from.
Monitoring
- Add PageWrite
Add a URL for monitoring, creating a site and session when none is given
monitoring.addPage
- Delete PageDestructive
Stop monitoring a page: Fluxguard hides it and everything captured for it, and the id still resolves with status ignore
monitoring.deletePage
- Delete SiteDestructive
Delete a site with all of its sessions, pages and captured versions
monitoring.deleteSite
- Get PageRead-only
Get one monitored page with its version counts and categories
monitoring.getPage
- Start CrawlWrite
Start capturing a session now; the capture runs in the background and spends account credits
monitoring.startCrawl
Webhooks
- CreateWrite
Add a webhook URL. Every later change event is POSTed to it, so a live URL starts receiving data immediately
webhooks.create
- DeleteDestructive
Remove a webhook so its URL stops receiving change events
webhooks.delete
- ListRead-only
List the webhook URLs change events are posted to
webhooks.list
- SampleRead-only
Get a sample delivery built from this account, to inspect the payload shape
webhooks.sample
Categories
- CreateWrite
Create a site category; sites are assigned to it in the Fluxguard console
categories.create
- ListRead-only
List the site categories change notifications can be limited to
categories.list
Account
- GetRead-only
Get the organisation account: plan, credits, site count and flags
account.get
Connect Fluxguard to Claude, ChatGPT or Cursor
- 1
Connect Fluxguard in Corsair
Add your Fluxguard API key once in Corsair. Corsair stores the credential encrypted and makes the Fluxguard API calls for your agent, so it never goes into a prompt or a config file. Connect Fluxguard
If your link lets the agent add apps, you can skip this: it gives you a sign-in link the first time it needs Fluxguard. On a ChatGPT personal plan, connect Fluxguard here first.
- 2
Add Corsair's MCP server to your agent
Every client uses the same address:
https://mcp.corsair.dev/mcpOpen Customize → Connectors → Add custom connector, paste the address, then select Connect.Add a custom MCP server with the address and choose OAuth. Personal plans get read tools only.Add to CursorOr add this to~/.cursor/mcp.json. Cursor opens Corsair to sign in the first time it connects.{ "mcpServers": { "corsair": { "url": "https://mcp.corsair.dev/mcp" } } }Run this, then run/mcpin Claude Code to sign in.claude mcp add --transport http corsair https://mcp.corsair.dev/mcpCodex, Gemini CLI, VS Code, Zed and other clients with OAuth sign-in work the same way. Clients without it, such as GitHub Copilot's coding agent, use a link's own address and an API key. Setup for every client
- 3
Sign in and choose what needs your approval
Your client opens Corsair to sign in. Pick a link: the apps your agent can use and a mode that decides what it may do without asking. In the default Cautious mode, Fluxguard's read and write operations run right away and its 3 destructive operations wait for your approval. Strict mode asks before every write and refuses destructive operations, and Read mode allows reads only.
FAQ
Install corsair and @corsair-dev/fluxguard, add the Fluxguard plugin, and connect with an API key. Then call methods like corsair.fluxguard.api.account.get() from your app. Corsair verifies webhooks, and keeps each tenant isolated.
Yes. Fluxguard requires an API key from your Fluxguard account or developer dashboard. Create credentials with access that matches what you automate, then paste them into Corsair or connect through managed auth in Hub.
Yes. One Corsair client can hit Fluxguard, GitHub, Notion, Stripe, and the rest. Trigger Fluxguard from a webhook, push updates to Slack, or chain actions across plugins. Same tenant context across integrations, plain TypeScript.
Teams use Corsair for website change monitoring with Fluxguard - add and delete monitored pages, start crawls, read captured page data, and manage the webhooks and site categories that deliver change alerts. Common builds include sync jobs, admin tooling, and agents that call Fluxguard APIs from your backend. Webhook handlers react to Fluxguard events and fan out to Slack, email, or other plugins in the same tenant.
The SDK is open source. Self-host and you pay Corsair nothing for the integration layer. Hub bills for hosted auth and execution, not per Fluxguard API call. Hub has a generous free tier. For hobby projects you can probably run the whole thing on free. Paid plans start to matter with more tenants or heavier traffic.
We maintain @corsair-dev/fluxguard in the open repo. When Fluxguard ships API changes, upgrade the package. Your call sites stay typed. You should not need to rewrite the integration layer each time.
No. Corsair does not read your Fluxguard data or hold individual access credentials. Credentials stay in your database. API calls run on your instance. We do not store Fluxguard data on your behalf.
Yes. Add https://mcp.corsair.dev/mcp as a custom connector or MCP server in Claude, ChatGPT, Cursor, VS Code, Claude Code, Codex or any client that supports remote MCP servers with OAuth sign-in, then sign in to Corsair. On ChatGPT personal plans, custom servers currently get read tools only.
Yes. Put Fluxguard on a link in Strict mode and every write waits for your approval, while destructive actions are refused. The default Cautious mode asks only before the 3 destructive Fluxguard operations. You can change a link's mode at hub.corsair.dev/me.