Skip to content

Call Desk MCP server

com.modernmustardseed/call-deskmodernmustardseed.comstreamable-httpv1.0.0Scanned

US and Canada calling rules: number checks, calling hours, recording consent, AI voice disclosure.

5 tools: 3 change things and 2 only read.

Tools: 0 delete, 0 irreversible, 3 write, 2 read.
  • Reads private data · 1
  • Reads text others write · 1
  • Can send data out · 3
  • 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.
Govern this server →

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 Call Desk MCP server can do

The Call Desk MCP server is published by modernmustardseed.com, a domain the MCP Registry verified. It has 5 tools. It can create or change data (3 tools: check_phone_number, can_i_call_now and recording_consent_rules), but cannot delete data. 2 tools only read.

1 tool reads private data (list_state_calling_rules); 1 tool brings in text other people can write (list_state_calling_rules); 3 tools can send data out of your system (check_phone_number, can_i_call_now and recording_consent_rules). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.

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 17, 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.

5 tools

Changes things 3Claude Code: ask
  • can_i_call_nowDecide whether a call to a phone number, or to someone in a given state or province, is allowed right now or at a given time under calling-hours law: the FCC TCPA rule and FTC Tele…Can send data out1 finding

    Why it is in this group

    • The name "can_i_call_now" says "call": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • outboundThe input takes a destination (input.phone_number): what the tool writes goes there.

    Findings

    • Warn

      The server marks "can_i_call_now" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "can_i_call_now" says "call": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Decide whether a call to a phone number, or to someone in a given state or province, is allowed right now or at a given time under calling-hours law: the FCC TCPA rule and FTC Telemarketing Sales Rule (8 a.m. to 9 p.m. called party's local time), every stricter state rule we verified (for example Florida, Oklahoma, Maryland, Washington and Wyoming stop at 8 p.m.; Texas Sundays start at noon; Pennsylvania bans Sundays from 2026-10-18; Kentucky starts at 10 a.m.; Maine allows automated solicitation weekdays 9 to 5 only), and in Canada the CRTC rules and British Columbia's holiday ban. Checks every time zone the number could be in, state holiday bans and future effective dates. Returns allowed or not, the reason, the window today, the next allowed time, and every rule applied with its citation, verbatim quote, source URL and as-of date. Choose call_type: sales_automated covers AI voice agents, prerecorded and autodialed sales calls. Informational, not legal advice.

    Annotations the server declares

    • title: Can I call now
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • check_phone_numberCheck a US, Canadian or other North American (+1) phone number before calling or texting it.Can send data outNo 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

    • outboundThe input takes a destination (input.phone_number): what the tool writes goes there.
    Description, as the server wrote it
    Check a US, Canadian or other North American (+1) phone number before calling or texting it. Returns whether it can be a working number (N11 codes and unassigned area codes fail; 555-0100 to 0199, reserved for fiction, is flagged as fictional_range and still resolves), the E.164 form, where the area code rings (US state or territory, Canadian province, or another country on the +1 plan), whether the area code is in service, its overlays, every time zone the exchange covers with the current local time there, and a toll-fraud risk grade (block, high, medium, low) with reasons: Caribbean and Bermuda +1 codes that bill as international calls, 900 premium numbers, Pacific territory codes, non-geographic codes and the 976 exchange. Area code data from NANPA, time zones from libphonenumber; no network access. Informational, not legal advice.

    Annotations the server declares

    • title: Check a phone number
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
Only reads 2Show 2 read-only tools
  • ai_voice_disclosure_rulesList the laws that require a caller or conversational agent to disclose that it is AI, a bot, or an artificial or prerecorded voice, for a US state, Canadian province or phone numb…No findings

    Why it is in this group

    • The description's first verb is "list": a word for reading.
    Description, as the server wrote it
    List the laws that require a caller or conversational agent to disclose that it is AI, a bot, or an artificial or prerecorded voice, for a US state, Canadian province or phone number, or for every jurisdiction. Covers the FCC ruling that AI-generated voices are artificial voices under the TCPA (so AI voice calls need prior express consent), the federal rule that prerecorded messages identify the caller at the start, state AI and chatbot disclosure laws, and state rules on identifying automated messages. Each rule gives what must be disclosed, when, who it applies to, effective and sunset dates, whether it is in force today, the citation, a verbatim quote, the source URL and as-of date. Informational, not legal advice.

    Annotations the server declares

    • title: AI voice disclosure rules
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_state_calling_rulesShow every calling rule Call Desk holds for one US state, DC, territory or Canadian province: its time zones and area codes, federal and state calling-hours rules with windows, hol…Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "list_state_calling_rules" says "list": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "show" and "message": it reads messages.
    • untrusted-inputThe description's first sentence says "show" and "message": it reads messages, which other people can write.
    Description, as the server wrote it
    Show every calling rule Call Desk holds for one US state, DC, territory or Canadian province: its time zones and area codes, federal and state calling-hours rules with windows, holidays and per-day call caps, recording consent, AI disclosure and automated message rules, each with citation, quote, source URL and as-of date, plus any rule we looked for and could not verify. With no state, returns a table of every jurisdiction with hours stricter than federal, the states with no stricter rule, and the all-party recording states. Informational, not legal advice.

    Annotations the server declares

    • title: List state calling rules
    • 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.

3 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 untrusted-input tool breaks every one.

Reads private data1
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 out3
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__call-desk__list_state_calling_rules"
    ]
  }
}

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.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:22 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
  • 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.

    Matched text

    https://mcp.modernmustardseed.com/call-desk: tools/list returned 5 tools to an anonymous client, including check_phone_number (write), can_i_call_now (write), recording_consent_rules (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

1 warn
  • The server marks "can_i_call_now" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "can_i_call_now" says "call": a word for a change.

    What this check looks for

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 call-desk https://mcp.modernmustardseed.com/call-desk
claude mcp add --transport http call-desk https://mcp.modernmustardseed.com/call-desk

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.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__call-desk__ai_voice_disclosure_rules",
      "mcp__call-desk__list_state_calling_rules"
    ],
    "ask": [
      "mcp__call-desk__check_phone_number",
      "mcp__call-desk__can_i_call_now",
      "mcp__call-desk__recording_consent_rules"
    ],
    "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 call-desk. Review it before you use it.

Capability tags behind 4 rules
  • mcp__call-desk__check_phone_number outbound
  • mcp__call-desk__can_i_call_now outbound
  • mcp__call-desk__recording_consent_rules outbound
  • mcp__call-desk__list_state_calling_rules 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.modernmustardseed/call-desk/verify?hash=dc89f7b10d73f80c52945be651ce2c0c84a7abd6dd14f1daedea48586176f336" | jq -e '.changed == false'

Pinned hash dc89f7b10d73, from Nov 17, 2026, 03:17 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/com.modernmustardseed/call-desk/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for com.modernmustardseed/call-desk
[![Anlyon Radar](https://radar.anlyon.com/badge/com.modernmustardseed/call-desk.svg)](https://radar.anlyon.com/servers/com.modernmustardseed/call-desk)

Source: MCP Registry. Synced Oct 21, 2026, 17:59 UTC.

Call Desk MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Call Desk MCP server safe?

No scan can promise that. What its definitions show: 5 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 Call Desk MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the Call Desk 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 Call Desk MCP server have?

5 tools: 3 write, 2 read. check_phone_number, can_i_call_now, recording_consent_rules, ai_voice_disclosure_rules and list_state_calling_rules.

Does the Call Desk MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Call Desk MCP server send data to outside services?

3 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): check_phone_number, can_i_call_now and recording_consent_rules.

Has the Call Desk MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 17, 2026.