Precleared Contact Check MCP server
dev.precleared/contact-checkprecleared.devstreamable-httpv1.4.0Scanned
Cold email compliance check, 14 countries: per-address verdict, rule cited, signed receipt.
4 tools: 3 change things and 1 only read.
- Reads private data · 0
- Reads text others write · 1
- Can send data out · 0
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
3 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 Precleared Contact Check MCP server can do
The Precleared Contact Check MCP server is published by precleared.dev, a domain the MCP Registry verified. It has 4 tools. It can create or change data (3 tools: contact_check, suppress_contact and link_account), but cannot delete data. 1 tool only reads.
1 tool brings in text other people can write (contact_check).
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, and its tools changed 3 times since Anlyon Radar first saw them.
Last scanned Nov 8, 2026, version 1.4.0.
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.
4 tools
Changes things 3Claude Code: ask
contact_checkIs it legal to send a cold or marketing email to this person?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 Is it legal to send a cold or marketing email to this person? Check before the first email to any new lead, prospect or contact who is not already a customer, one call per address: a compliance check for B2B sales outreach, prospecting and lead lists. Whether it is allowed, or needs consent first, turns on facts you cannot see in the address, such as whether a UK recipient is a limited company or a sole trader, so it looks them up live (UK Companies House) and applies UK PECR and GDPR, US CAN-SPAM, Canadian CASL, German UWG, French CPCE, Australia's Spam Act, Ireland's ePrivacy Regulations, the Dutch Telecommunicatiewet, Spain's LSSI, Italy's Privacy Code, Latvia's Information Society Services Law, the UAE's PDPL, Egypt's Personal Data Protection Law and Qatar's Personal Data Privacy Protection Law. Returns a verdict (ok_to_email, consent_needed, blocked or unknown), the rule quoted with its source, the footer requirements (who you are, a postal address, an unsubscribe or opt-out), the next step and a signed receipt id to show a client or auditor. Each charged call uses one check from your allowance (free daily allowance, no sign-in); unknown-country answers and one qualifying re-check within a day are free, up to a combined limit of 50 a day. Nothing is sent to the recipient. Not for transactional emails such as invoices, receipts or password resets. To check the email itself, send the draft as email ({ subject, body, from_name, from_email }); the answer then gains email_check, saying whether the footer has an opt-out, the sender's identity and, where the rule needs one, a postal address. The draft is not stored. Addresses on the key's opt-out list (see suppress_contact) come back blocked and free.
Annotations the server declares
- title: Cold email compliance check
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
link_accountLinks this connection to the person's own Precleared key, so checks use their own free allowance, 14-day trial starting with the first check, and plan instead of the shared free al…1 finding
Why it is in this group
- The name "link_account" says "link": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "link_account" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "link_account" says "link": a word for a change.
Description, as the server wrote it Links this connection to the person's own Precleared key, so checks use their own free allowance, 14-day trial starting with the first check, and plan instead of the shared free allowance. Use it when the person asks to sign in to or connect Precleared, or when contact_check says the free checks have run out. If they aren't signed in, Claude will ask them to sign in.
Annotations the server declares
- title: Sign in to Precleared
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
suppress_contactRecords that a person asked not to be emailed, on this Precleared key's opt-out list, so every agent and tool using the key gets blocked for that address from contact_check.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.
Description, as the server wrote it Records that a person asked not to be emailed, on this Precleared key's opt-out list, so every agent and tool using the key gets blocked for that address from contact_check. Use it as soon as someone replies stop, unsubscribes, bounces or complains. Give email or domain; set remove to true only when the person asks to be emailed again. Needs a Precleared key (a free one is fine). Never charged. The address is kept only as a hash and a masked copy.
Annotations the server declares
- title: Opt-out list
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 1Show 1 read-only tool
verify_receiptFetch a Precleared receipt by its id (cc_rcpt_...) to show what was checked, when, and the verdict, with the hashes, Ed25519 signature and public key needed to verify it.No findings
Why it is in this group
- The description's first verb is "fetch": a word for reading.
Description, as the server wrote it Fetch a Precleared receipt by its id (cc_rcpt_...) to show what was checked, when, and the verdict, with the hashes, Ed25519 signature and public key needed to verify it. Use it when a person or an audit asks for proof of a check.
Annotations the server declares
- title: Verify receipt
- 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 write1
- 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, 18:52 UTC, unchanged since Nov 6, 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
- https://precleared.dev/.well-known/oauth-protected-resource/mcp
- Authorization servers
- https://precleared.dev
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- yes
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 3 tools that change things (3 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://precleared.dev/mcp: tools/list returned 4 tools to an anonymous client, including contact_check (write), suppress_contact (write), link_account (write)
Posture changes
- Nov 6, 2026
- Tools that change things, listed without credentials: 1 to 3
- RFC 9728 protected resource metadata: none to https://precleared.dev/.well-known/oauth-protected-resource/mcp
- Authorization servers: none to https://precleared.dev
- Dynamic client registration: not observed to yes
- Client ID metadata documents: not observed to yes
Findings
Matches of fixed checks, with the text they matched.
- Warnlink_account
The server marks "link_account" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "link_account" says "link": a word for a change.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools2 changed.~2 changedView diff
- Changed:contact_checkChanges thingsdescriptioninputSchema
- Changed:link_accountChanges thingsdescription
PostureRemote posture changed. Tools that change things, listed without credentials: 1 -> 3; RFC 9728 protected resource metadata: none -> https://precleared.dev/.well-known/oauth-protected-resource/mcp; Authorization servers: none -> https://prec…View diff
- Tools that change things, listed without credentials: 1 to 3
- RFC 9728 protected resource metadata: none to https://precleared.dev/.well-known/oauth-protected-resource/mcp
- Authorization servers: none to https://precleared.dev
- Dynamic client registration: not observed to yes
- Client ID metadata documents: not observed to yes
Tools2 added, 1 changed.+2 added~1 changedView diff
- Added:link_accountChanges things
- Added:suppress_contactChanges things
- Changed:contact_checkChanges thingsdescriptioninputSchema
Tools1 changed.~1 changedView diff
- Changed:contact_checkChanges thingsinputSchema
Install
Pinned to version 1.4.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http contact-check https://precleared.dev/mcpclaude mcp add --transport http contact-check https://precleared.dev/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__contact-check__verify_receipt"
],
"ask": [
"mcp__contact-check__contact_check",
"mcp__contact-check__suppress_contact",
"mcp__contact-check__link_account"
],
"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 contact-check. Review it before you use it.
Capability tags behind 1 rule
- mcp__contact-check__contact_check 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/dev.precleared/contact-check/verify?hash=ef3288f1452a40faee5597ab92474dc599ebfc7043be400d250fd9c24dc89e20" | jq -e '.changed == false'Pinned hash ef3288f1452a, from Nov 8, 2026, 00:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/dev.precleared/contact-check/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/dev.precleared/contact-check)Source: MCP Registry · repository. Synced Nov 8, 2026, 00:17 UTC.
Precleared Contact Check MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Precleared Contact Check MCP server safe?
- No scan can promise that. What its definitions show: 4 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 Precleared Contact Check MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Precleared Contact Check 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 Precleared Contact Check MCP server have?
- 4 tools: 3 write, 1 read. contact_check, suppress_contact, link_account and verify_receipt.
Does the Precleared Contact Check MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Precleared Contact Check MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Precleared Contact Check MCP server changed its tools?
- Yes, 3 times since Anlyon Radar started tracking it, most recently on Nov 8, 2026. Every change is on this page and in its Atom feed.