# ai.callmcp/server (npm · @callmcp/server)

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

- Trust score: 61/100 (medium)
- Change this week: +18
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `@callmcp/server`: 61/100 (this document), [markdown](https://verifymcp.io/servers/ai-callmcp-server/callmcp-server.md), [page](https://verifymcp.io/servers/ai-callmcp-server/callmcp-server)

## Channel facts

- Registry: `npm`
- Package: `@callmcp/server`
- Version: `0.1.2`
- Transport: `stdio`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (96 of 100), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (96 of 100), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 23 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 49/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 1004 tokens (~71/item across 14 items; 14 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 75/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 25% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add ai-callmcp-server -- npx -y @callmcp/server
```

### Codex

```bash
codex mcp add ai-callmcp-server -- npx -y @callmcp/server
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-callmcp-server": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@callmcp/server"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-callmcp-server --command npx --arg -y --arg @callmcp/server
```

### Hermes

```yaml
mcp_servers:
  ai-callmcp-server:
    command: "npx"
    args: ["-y", "@callmcp/server"]
```

### Other

```json
{
  "mcpServers": {
    "ai-callmcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@callmcp/server"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 61, +26)

- [security regression] Install scripts: pass → unverified
- [security regression] Provenance: fail → unverified
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Malware scan: unverified → pass
- [security] Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.
- [functional regression] Maintenance: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] License: pass → unverified
- [functional regression] Capabilities: pass → unverified
- [functional improvement] Stability: unverified → 0.23
- [functional improvement] Dependency health: unverified → partial
- [functional] Licence: MIT

### 2026-08-01 (score 35, −10)

- [security regression] Known CVEs: partial → unverified
- [functional regression] Dependency health: partial → unverified

### 2026-07-31 (score 45, +39)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 6, −63)

- [security regression] Known CVEs: partial → unverified
- [security regression] Malware scan: pass → unverified
- [security regression] Provenance: fail → unverified
- [security regression] Install scripts: pass → unverified
- [functional regression] Dependency health: partial → unverified
- [functional regression] License: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Maintenance: pass → unverified
- [functional] Licence: MIT

### 2026-07-29 (score 69, +43)

- [security regression] Provenance: unverified → fail
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → pass
- [functional regression] Security disclosure: unverified → fail
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Schema quality: unverified → fair
- [functional improvement] License: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional] Licence: MIT

### 2026-07-28 (score 26, −17)

- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Security disclosure: fail → unverified
- [functional improvement] Dependency health: unverified → partial
- [functional] First check of Schema quality: unverified

### 2026-07-27 (score 43)

First indexed and scored.

## MCP tools (14)

### `list_drivers` (~30 tokens)

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

### `request_call_approval` (~146 tokens)

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.

Input parameters:

- `campaign_max_contacts` (integer): required when scope=campaign_batch
- `channel` (string)
- `destinations` (array, required)
- `driver` (string)
- `options` (object): namespaced driver-specific passthrough, keyed by driver_id
- `purpose` (string): human-readable reason shown in the elicitation/approval UI
- `scope` (string, required)
- `ttl_seconds` (integer): see SPEC §3.2 for tier defaults

### `list_approvals` (~60 tokens)

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

Input parameters:

- `cursor` (string)
- `driver` (string)
- `scope` (string)
- `state` (string)

### `make_call` (~159 tokens)

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.

Input parameters:

- `agent_config_ref` (string): opaque reference to an already-configured agent/assistant
- `approval_id` (string): omit only if `to` matches a standing allowlist entry
- `driver` (string)
- `from` (string): E.164 caller-id number; if omitted, driver default number is used
- `max_duration_seconds` (integer)
- `metadata` (object)
- `options` (object): namespaced driver-specific passthrough, keyed by driver_id
- `to` (string, required): E.164 destination number

### `end_call` (~45 tokens)

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

Input parameters:

- `call_id` (string, required)
- `reason` (string)

### `get_call_status` (~36 tokens)

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

Input parameters:

- `call_id` (string, required)

### `get_transcript` (~45 tokens)

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

Input parameters:

- `call_id` (string, required)
- `format` (string)

### `get_recording` (~42 tokens)

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

Input parameters:

- `call_id` (string, required)

### `send_sms` (~109 tokens)

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

Input parameters:

- `approval_id` (string)
- `body` (string, required)
- `channel` (string)
- `driver` (string)
- `from` (string)
- `media_urls` (array)
- `options` (object): namespaced driver-specific passthrough, keyed by driver_id
- `to` (string, required)

### `search_numbers` (~70 tokens)

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

Input parameters:

- `area_code` (string)
- `capabilities_required` (array)
- `country` (string, required): ISO 3166-1 alpha-2
- `cursor` (string)
- `driver` (string)

### `buy_number` (~83 tokens)

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

Input parameters:

- `compliance` (object)
- `driver` (string)
- `number` (string, required): a number returned by search_numbers
- `options` (object): namespaced driver-specific passthrough, keyed by driver_id

### `configure_number` (~88 tokens)

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

Input parameters:

- `agent_config_ref` (string|null)
- `caller_id_name` (string|null)
- `driver` (string)
- `number` (string, required)
- `options` (object): namespaced driver-specific passthrough, keyed by driver_id
- `sms_webhook_url` (string|null)

### `list_numbers` (~35 tokens)

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

Input parameters:

- `cursor` (string)
- `driver` (string)

### `list_calls` (~56 tokens)

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

Input parameters:

- `cursor` (string)
- `driver` (string)
- `since` (string)
- `status` (string)
- `until` (string)

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/ai-callmcp-server/callmcp-server#diagnostics

## Score history

- 2026-08-03: 61
- 2026-08-02: 61
- 2026-08-01: 35
- 2026-07-31: 45
- 2026-07-30: 6
- 2026-07-29: 69
- 2026-07-28: 26
- 2026-07-27: 43

## Links

- npm package: https://www.npmjs.com/package/@callmcp/server
- Socket report: https://socket.dev/npm/package/@callmcp/server
- Repository: https://github.com/CallMCP/callmcp
- Changelog RSS feed: https://verifymcp.io/servers/ai-callmcp-server/callmcp-server/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-callmcp-server/callmcp-server/changelog.json
- HTML version of this page: https://verifymcp.io/servers/ai-callmcp-server/callmcp-server