MarginGlow AI Signal MCP server
com.marginglow/signalmarginglow.comstreamable-httpv1.0.0Scanned
Evidence-backed opportunity intelligence for small businesses, built for authorised AI agents.
3 tools: 1 do something that can't be undone and 2 change things.
- Reads private data · 0
- Reads text others write · 2
- Can send data out · 0
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here does something that can't be undone. Govern it.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the MarginGlow AI Signal MCP server can do
The MarginGlow AI Signal MCP server is published by marginglow.com, a domain the MCP Registry verified. It has 3 tools. It can do things that cannot be undone, such as sending, paying or publishing (purchase_marginglow_signal) and create or change data (2 tools: analyse_small_business_opportunities and check_marginglow_signal_access), but cannot delete data. None of its tools only reads.
2 tools bring in text other people can write (analyse_small_business_opportunities and purchase_marginglow_signal).
The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 13, 2026, version 1.0.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
3 tools
Can't be undone 1Claude Code: ask
purchase_marginglow_signalCreates a secure Stripe payment link for one MarginGlow AI Signal costing EUR 2, inclusive of applicable tax.Reads text others writeNo findings
Why it is in this group
- The name "purchase_marginglow_signal" says "purchase": a word that usually means money moves, which cannot be taken back.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Creates a secure Stripe payment link for one MarginGlow AI Signal costing EUR 2, inclusive of applicable tax. Use this when analyse_small_business_opportunities reports that no Signal credits remain. A payment-capable agent may follow the payment instructions automatically when supported. Otherwise, give the secure checkout URL to the user. After payment, retry the original analysis request with the same agent API key and Idempotency-Key.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
Changes things 2Claude Code: ask
analyse_small_business_opportunitiesUse this when a user wants practical, evidence-based ways for a specific small business to increase revenue, improve margins, reduce costs, strengthen Google visibility, improve co…Reads text others write1 finding
Why it is in this group
- The name "analyse_small_business_opportunities" says "analyse": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "analyse_small_business_opportunities" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "analyse_small_business_opportunities" says "analyse": a word for reading.
Description, as the server wrote it Use this when a user wants practical, evidence-based ways for a specific small business to increase revenue, improve margins, reduce costs, strengthen Google visibility, improve conversion or prioritise growth actions. Requires the business name and public website. Returns structured evidence, ranked opportunities, confidence, commercial impact and first actions. Consumes one complimentary or paid MarginGlow AI Signal credit. Do not use for generic business definitions, investment advice, regulated advice or analysis that requires private financial data.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
check_marginglow_signal_accessChecks the authenticated agent's complimentary and paid MarginGlow AI Signal balances, whether an analysis can run, which allowance will be used next and the latest successfully cr…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Checks the authenticated agent's complimentary and paid MarginGlow AI Signal balances, whether an analysis can run, which allowance will be used next and the latest successfully credited Stripe purchase. This is read-only and does not consume a Signal.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write2
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:42 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 3
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 3 tools that change things (1 irreversible, 2 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://www.marginglow.com/mcp: tools/list returned 3 tools to an anonymous client, including purchase_marginglow_signal (irreversible), analyse_small_business_opportunities (write), check_marginglow_signal_access (write)
Findings
Matches of fixed checks, with the text they matched.
The server marks "analyse_small_business_opportunities" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "analyse_small_business_opportunities" says "analyse": a word for reading.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http signal https://www.marginglow.com/mcp --header 'Authorization: <your-authorization>'claude mcp add --transport http signal https://www.marginglow.com/mcp --header 'Authorization: <your-authorization>'Run in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [],
"ask": [
"mcp__signal__analyse_small_business_opportunities",
"mcp__signal__check_marginglow_signal_access",
"mcp__signal__purchase_marginglow_signal"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as signal. Review it before you use it.
Capability tags behind 2 rules
- mcp__signal__analyse_small_business_opportunities untrusted-input
- mcp__signal__purchase_marginglow_signal untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/com.marginglow/signal/verify?hash=587293bd16bac73f6d1dfadd77f6febab3cb5b29f0bc02c47cefc946fcc24c08" | jq -e '.changed == false'Pinned hash 587293bd16ba, from Nov 13, 2026, 17:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.marginglow/signal/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.marginglow/signal)Source: MCP Registry. Synced Oct 21, 2026, 17:58 UTC.
MarginGlow AI Signal MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the MarginGlow AI Signal MCP server safe?
- No scan can promise that. What its definitions show: 3 tools, 3 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the MarginGlow AI Signal MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the MarginGlow AI Signal MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: purchase_marginglow_signal.
What tools does the MarginGlow AI Signal MCP server have?
- 3 tools: 1 irreversible, 2 write. purchase_marginglow_signal, analyse_small_business_opportunities and check_marginglow_signal_access.
Does the MarginGlow AI Signal MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the MarginGlow AI Signal MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the MarginGlow AI Signal MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 13, 2026.