FAQ

Questions and answers

Not here? Email support@intelmcp.io. We answer questions before you subscribe, too.

Coverage

Which channels does IntelMCP collect from?

The collection is public channels, and private channels and groups the operator has reviewed. Public channels are the ones anyone can find and join. A private channel or group is collected only when the collection account is already a member and the operator has approved it; results show "Private channel" instead of a link, because only members could open it. Direct messages are never collected. IntelMCP's software never joins a private channel or group: it reads only those the collection account is already a member of, which the operator adds. The collection is chosen by hand for threat-intelligence value, with the deepest coverage of the Gulf and the wider Middle East, Iran–Israel, Russia–Ukraine hacktivism, and leak, ransomware and CVE trackers. See coverage for dated figures.

Can I see the channel list?

No. We publish topics and regions rather than a channel list. Every search result and match names the channel its message came from, and Claude can list the source topics with how many sources and posts a day each has.

Which languages?

Posts are kept in their original language, mostly Arabic, Persian, Russian, Hebrew and English. You don't need to read them: Claude turns your question into searches in those languages and reads the results back to you in English.

A channel I need is missing. Can you add it?

Ask Claude to request it, with its @username or t.me link. You can make up to 10 channel requests a month. Every request is vetted (automatically, and by the operator when unsure) before a collection account joins the channel, and some are declined: channels that cannot be found or are not public always are. If the channel is already collected, Claude says so, with its last post and the date its stored history starts, and no request is filed.

Can I check whether a channel is collected?

Yes. Ask Claude whether a channel is collected, with its @username or t.me link: it answers from the collection whether the channel is collected and posting, silent, no longer collected or requested, without filing a request.

How far back can I search?

Up to the last 90 days of collected messages.

Is the content verified?

No. Messages are third-party posts as published, and claims in them can be false or exaggerated. Treat them as leads to check, not as facts.

Alerts and triage

What is an incident?

Reposts and copies of the same event within 72 hours are grouped into one incident. The first post is marked new; a later post that adds something: an identifying indicator or a country new to the event, a step up in exploitation (proof of concept, then exploited), a reply in the same channel, a channel posting it a second time, or a match for another of your rules is marked update; the rest are repeats. You review one entry per event instead of one per repost, and webhooks skip repeats.

Who decides whether a match matters?

Your Claude does. A rule match is a candidate, not a finding. The Triage matches prompt has Claude read your watch profile, judge each new match against it and record a verdict: relevant or not, with a severity and a one-line reason.

How do matches reach me?

They wait in IntelMCP until you ask Claude about them. If you want them pushed, add a webhook: each match is posted as signed JSON to your HTTPS endpoint as it is matched, before any triage.

What does the dashboard look like?

In claude.ai and Claude Desktop it opens as IntelMCP's interactive panel: what needs attention, alerts per day by severity, your alerts with the full post, rules, exclusions, webhooks, sources and your account. You can mark alerts relevant or not relevant there, and each verdict is saved at once, with Undo; changes go through IntelMCP's tools, so Claude's tool permissions apply, as in chat. In Claude Code, the Dashboard prompt has Claude draw a one-page overview as an HTML file instead, fresh each time, so the layout varies.

Can I keep the dashboard open as its own page?

Yes: the Command Centre is the same dashboard as a private page in your Claude account, which you can pin to the sidebar; it opens in claude.ai or the Claude app. It calls IntelMCP through your own connection, so it shows your alerts, rules and settings, and the collection your plan includes. Today it is created from Claude Code with the plugin (/intelmcp:command-centre), with IntelMCP connected in claude.ai. It is private to you and cannot be shared.

Can I hide alerts I don't care about?

Yes. Exclusions hide noisy topics, countries, channels or phrases from your alerts and webhooks, across all your rules, without deleting them. A country exclusion hides a post only when every country it mentions is excluded. Ask Claude, or use the interactive panel; removing an exclusion shows the alerts again, but they are not pushed to your webhooks later.

Data and security

Do you train AI on the data?

No. IntelMCP does not train or fine-tune AI models, and does not run one. The analysis happens in your own Claude.

Can other customers see my rules or matches?

No. Each customer's rules, watch profiles, matches and verdicts are separated by row-level security in the database. See security.

Someone posted about me. Can you remove it?

Yes. Email support@intelmcp.io with the message and we remove it from IntelMCP. A post that is still on Telegram may be collected again, so removal of a live post may need repeating. We cannot remove it from Telegram itself.

Is IntelMCP affiliated with Telegram?

No. IntelMCP is an independent service that uses Telegram's API. It is not affiliated with or endorsed by Telegram.

Is IntelMCP affiliated with Anthropic?

No. IntelMCP is an independent service and is not affiliated with or endorsed by Anthropic. It connects to Claude as a custom connector, the way any MCP server can.

Claude

What do I need?

A Claude account that can add custom connectors (claude.ai or Claude Desktop), or Claude Code, and an IntelMCP subscription. On Team or Enterprise plans, an organization owner may need to add the connector first.

Does it use my Claude usage?

Yes. Claude does the reading and judging, so it runs on your own Claude plan. Long triage sessions use more of it.

Should I use the connector or the Claude Code plugin?

One of them, not both. In claude.ai and Claude Desktop, add the connector. In Claude Code, either add the connector with one command or install the plugin, which adds the connector and five commands: the four guides (/intelmcp:setup, /intelmcp:triage, /intelmcp:dashboard and /intelmcp:investigate) and /intelmcp:command-centre, which creates your Command Centre. See the setup guide.

Billing

How much does it cost?

$25 per month for one analyst, billed monthly by Polar, our merchant of record. See pricing.

Is there a free trial?

No free trial. Instead, read the example, the coverage and the docs before you pay, and email us with any question.

Can I share my subscription?

No. One subscription is for one analyst's own sign-in, with the email you paid with. Questions: support@intelmcp.io.

Where do I see my plan and usage?

Ask Claude for your IntelMCP account status, or open the Account view of the interactive panel: your plan, whether the subscription renews or ends and when, today's tool calls and searches against the limits, and how many rules, watch profiles, webhooks and channel requests you use.

How do I cancel?

From the link in your Polar receipt email. Access continues to the end of the month you have paid for. There are no refunds for partial months; see the refund policy.

What happens to my data when I cancel?

Your rules, matches and settings are kept for 90 days after your subscription ends, then deleted. Subscribing again with the same email in that time restores them.