Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

ai.callmcp/server

NPM · @CALLMCP/SERVER

One MCP tool contract for telephony — any call provider, hosted, local, or BYOK.

Available components

0 this week 74 Trust /100

Last scanned (6 hours ago)

Scores higher than 48% of npm servers

Category Communication

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security81
  • No malware found by supply-chain analysis.Pass
  • CVE check failed: a known high-severity CVE affects zod 3.25.76, a direct dependency. A fixed version is available. View diagnostics → Fail
  • No install/post-install scripts declared.Pass
  • 31 of 94 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability60
  • AI-judged instruction clarity (fair).Partial
  • Tool/resource definitions use about 1004 tokens (~71/item across 14 items; 14 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage75
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 25% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
  • An AI judge read all 14 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 4 Nov 26 0
    • Stability: 0.97 → pass security
  • 3 Nov 26 0
    • Stability: pass → 0.97 functional
  • 28 Oct 26 0
    • Stability: 0.97 → pass security
  • 27 Oct 26 0
    • Stability: pass → 0.97 functional
  • 24 Oct 26 −5
    • CVE-2023-54404 affects this package: high ▼ security
    • Known CVEs: pass → fail ▼ security
  • 21 Oct 26 0
    • Stability: 0.97 → pass security
  • 20 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 19 Oct 26 −1
    • Stability: pass → 0.93 functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 5 Nov 2026 · Analysed npm/@callmcp/server@0.1.2

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Vulnerabilities 1 finding
ID CVE Severity Vector Fix available
GHSA-mrhx-c7xc-m3w5 CVE-2023-54404 high CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H yes

Background: What a vulnerability scan can and cannot prove →

Dependencies 94 packages
Packages resolved 94
Stale 30
No linked repository 1
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 14 exposed · ~1,004 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
buy_number ~83

Purchases a phone number (SPEC §1.11). Spends money but does not contact a third party, so no human approval gate.

NameTypeReqDescription
complianceobject––
driverstring––
numberstringyesa number returned by search_numbers
optionsobject–namespaced driver-specific passthrough, keyed by driver_id

No output schema declared.

No examples provided.

configure_number ~88

Updates routing/configuration for an already-owned number (SPEC §1.12).

NameTypeReqDescription
agent_config_refstring|null––
caller_id_namestring|null––
driverstring––
numberstringyes–
optionsobject–namespaced driver-specific passthrough, keyed by driver_id
sms_webhook_urlstring|null––

No output schema declared.

No examples provided.

end_call ~45

Terminates an in-progress call (SPEC §1.5). Capability-gated by supports_hangup.

NameTypeReqDescription
call_idstringyes–
reasonstring––

No output schema declared.

No examples provided.

get_call_status ~36

Read-only poll fallback for clients that don't subscribe to resource updates (SPEC §1.6).

NameTypeReqDescription
call_idstringyes–

No output schema declared.

No examples provided.

get_recording ~42

Returns a resource link to the call's audio recording (SPEC §1.8). Capability-gated by supports_recording.

NameTypeReqDescription
call_idstringyes–

No output schema declared.

No examples provided.

get_transcript ~45

Returns a call's transcript, inline or as a subscribable resource link (SPEC §1.7).

NameTypeReqDescription
call_idstringyes–
formatstring––

No output schema declared.

No examples provided.

list_approvals ~60

Read-only. Returns pending approvals, allowlist entries, and active campaign grants (SPEC §1.3).

NameTypeReqDescription
cursorstring––
driverstring––
scopestring––
statestring––

No output schema declared.

No examples provided.

list_calls ~56

Read-only call history/inventory (SPEC §1.14).

NameTypeReqDescription
cursorstring––
driverstring––
sincestring––
statusstring––
untilstring––

No output schema declared.

No examples provided.

list_drivers ~30

Read-only capability introspection. Call before assuming any other tool's behavior (SPEC §1.1).

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_numbers ~35

Read-only inventory of owned numbers (SPEC §1.13).

NameTypeReqDescription
cursorstring––
driverstring––

No output schema declared.

No examples provided.

make_call ~159

Places an outbound call (SPEC §1.4). Requires a valid, unexpired approval_id or an allowlist match; otherwise the server elicits approval inline rather than dialing.

NameTypeReqDescription
agent_config_refstring–opaque reference to an already-configured agent/assistant
approval_idstring–omit only if `to` matches a standing allowlist entry
driverstring––
fromstring–E.164 caller-id number; if omitted, driver default number is used
max_duration_secondsinteger––
metadataobject––
optionsobject–namespaced driver-specific passthrough, keyed by driver_id
tostringyesE.164 destination number

No output schema declared.

No examples provided.

request_call_approval ~146

Creates a pending human authorization for a destination, allowlist entry, or campaign batch (SPEC §1.2). Fires MCP elicitation when supported; otherwise returns an out-of-band approval URL.

NameTypeReqDescription
campaign_max_contactsinteger–required when scope=campaign_batch
channelstring––
destinationsarrayyes–
driverstring––
optionsobject–namespaced driver-specific passthrough, keyed by driver_id
purposestring–human-readable reason shown in the elicitation/approval UI
scopestringyes–
ttl_secondsinteger–see SPEC §3.2 for tier defaults

No output schema declared.

No examples provided.

search_numbers ~70

Read-only search for purchasable phone numbers (SPEC §1.10).

NameTypeReqDescription
area_codestring––
capabilities_requiredarray––
countrystringyesISO 3166-1 alpha-2
cursorstring––
driverstring––

No output schema declared.

No examples provided.

send_sms ~109

Sends an outbound message over SMS, WhatsApp, or RCS (SPEC §1.9). Capability-gated; approval-gated like make_call.

NameTypeReqDescription
approval_idstring––
bodystringyes–
channelstring––
driverstring––
fromstring––
media_urlsarray––
optionsobject–namespaced driver-specific passthrough, keyed by driver_id
tostringyes–

No output schema declared.

No examples provided.

Install

How do I install the ai.callmcp/server MCP server?

ai.callmcp/server runs locally as an npm package, launched with npx -y @callmcp/server. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · @callmcp/server

# add to Claude Code
claude mcp add ai-callmcp-server -- npx -y @callmcp/server
Common questions

What is the ai.callmcp/server MCP server?

ai.callmcp/server is an MCP server listed in the public MCP registry as ai.callmcp/server. One MCP tool contract for telephony, any call provider, hosted, local, or BYOK. This page covers its npm package (@callmcp/server).

Is the ai.callmcp/server MCP server safe to use?

ai.callmcp/server scores 74 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 5 November 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the ai.callmcp/server MCP server expose?

ai.callmcp/server exposes 14 tools: list_drivers, request_call_approval, list_approvals, make_call, end_call, and 9 more. Their descriptions and schemas cost roughly 1,004 tokens of context every time the server is loaded.

Is the ai.callmcp/server MCP server still maintained?

ai.callmcp/server is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the ai.callmcp/server MCP server under?

ai.callmcp/server declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.