ARC-Relay Email MCP server
com.arc-relay/mcparc-relay.comstreamable-httpv1.3.0Scanned
Checks any domain's DMARC, SPF, MX and DKIM setup, scores it 0-100, and ranks the fixes.
6 tools: 2 change things and 4 only read.
- Reads private data · 2
- Reads text others write · 4
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
2 tools here change things. Govern them.
- 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 ARC-Relay Email MCP server can do
The ARC-Relay Email MCP server is published by arc-relay.com, a domain the MCP Registry verified. It has 6 tools. It can create or change data (2 tools: check_dmarc and check_health), but cannot delete data. 4 tools only read.
2 tools read private data (check_email_health and network_stats); 4 tools bring in text other people can write (check_dmarc, check_email_health, check_spf and 1 more).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 16, 2026, version 1.3.0.
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.
6 tools
Changes things 2Claude Code: ask
check_dmarcCheck a domain's DMARC, SPF, and MX records.Reads text others writeNo 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.
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 Check a domain's DMARC, SPF, and MX records. Use this to diagnose email authentication issues.
Annotations the server declares
- title: Check DMARC, SPF and MX
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
check_healthCheck ARC-Relay service health and uptime.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 Check ARC-Relay service health and uptime.
Annotations the server declares
- title: ARC-Relay service health
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 4Show 4 read-only tools
check_email_healthGet a 0-100 email health score for any domain.Reads private dataReads text others writeNo findings
Why it is in this group
- The description's first verb is "get": a word for reading.
What it can reach
- private-dataThe name "check_email_health" says "email": it reads mail.
- private-dataThe description's first sentence says "get" and "email": it reads mail.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe name "check_email_health" says "email": it reads inbound email, which other people can write.
- untrusted-inputThe description's first sentence says "get" and "email": it reads inbound email, which other people can write.
Description, as the server wrote it Get a 0-100 email health score for any domain. Checks DMARC, SPF, MX, and DKIM records and returns a letter grade (A+ to F) with actionable recommendations. Use this to audit any domain's email security posture.
Annotations the server declares
- title: Email health score
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
check_spfValidate a domain's SPF record.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "validate": a word for reading.
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 Validate a domain's SPF record. Shows mechanisms, DNS lookup count, and warns if over the 10-lookup limit.
Annotations the server declares
- title: Validate SPF record
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
network_leaderboardView top relay nodes ranked by reputation score.No findings
Why it is in this group
- The description's first verb is "view": a word for reading.
Description, as the server wrote it View top relay nodes ranked by reputation score. Filter by region.
Annotations the server declares
- title: Relay node leaderboard
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
network_statsGet public relay network statistics — total nodes, active nodes, messages routed, delivery rate, and the average DMARC rate nodes report about themselves (rates are null until ther…Reads private dataReads text others writeNo findings
Why it is in this group
- The description's first verb is "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "get" and "message": it reads messages.
- untrusted-inputThe description's first sentence says "get" and "message": it reads messages, which other people can write.
Description, as the server wrote it Get public relay network statistics — total nodes, active nodes, messages routed, delivery rate, and the average DMARC rate nodes report about themselves (rates are null until there is traffic).
Annotations the server declares
- title: Relay network stats
- 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 outbound.
- Reads private data2
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write4
- 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, 18:34 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
- 2
- Protocol version
- 2025-03-26
- 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
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://arc-relay.com/mcp: tools/list returned 6 tools to an anonymous client, including check_dmarc (write), check_health (write)
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
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 1.3.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http arc-relay https://arc-relay.com/mcpclaude mcp add --transport http arc-relay https://arc-relay.com/mcpRun 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": [
"mcp__arc-relay__check_email_health",
"mcp__arc-relay__check_spf",
"mcp__arc-relay__network_leaderboard",
"mcp__arc-relay__network_stats"
],
"ask": [
"mcp__arc-relay__check_dmarc",
"mcp__arc-relay__check_health"
],
"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 arc-relay. Review it before you use it.
Capability tags behind 4 rules
- mcp__arc-relay__check_dmarc untrusted-input
- mcp__arc-relay__check_email_health private-data, untrusted-input
- mcp__arc-relay__check_spf untrusted-input
- mcp__arc-relay__network_stats private-data, 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.arc-relay/mcp/verify?hash=6c22e20a072034a9cc228606cb3b8070dcb906019e4069e8d84ea1ed96595a97" | jq -e '.changed == false'Pinned hash 6c22e20a0720, from Nov 16, 2026, 06:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.arc-relay/mcp/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.arc-relay/mcp)Source: MCP Registry. Synced Nov 2, 2026, 22:17 UTC.
ARC-Relay Email MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the ARC-Relay Email MCP server safe?
- No scan can promise that. What its definitions show: 6 tools, 2 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the ARC-Relay Email MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the ARC-Relay Email MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the ARC-Relay Email MCP server have?
- 6 tools: 2 write, 4 read. check_dmarc, check_health, check_email_health, check_spf, network_leaderboard and network_stats.
Does the ARC-Relay Email MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the ARC-Relay Email MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the ARC-Relay Email MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 16, 2026.