Skip to main content
Glama
enesjakozh
errajibadr

TwilioManager MCP

by errajibadr
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Twilio マネージャー MCP

Twilio リソースを管理するための Model Context Protocol (MCP) 実装。このパッケージは、標準化された MCP インターフェースを通じて、Twilio サブアカウント、電話番号、規制バンドルを管理するためのツールを提供します。

特徴

  • Twilioサブアカウントの一覧

  • サブアカウントに関連付けられた電話番号を取得する

  • サブアカウント間で電話番号を転送する

  • 規制バンドルSIDを取得する

  • 直接通信とサーバー送信イベント（SSE）通信の両方をサポート

  • Claude Desktop、Cursor、その他のMCP互換ツールとの統合

Related MCP server: Twilio MCP Server

インストール

前提条件

uvをインストールする

macOSの場合:

brew install uv

Windowsの場合:

powershell -c "irm https://astral.sh/uv/install.ps1 | iex"

Linuxの場合:

curl -LsSf https://astral.sh/uv/install.sh | sh

プロジェクトのセットアップ

  1. リポジトリをクローンします。

git clone https://github.com/yourusername/twilio_manager_mcp.git
cd twilio_manager_mcp

  1. uv を使用して依存関係をインストールします。

uv sync

構成

  1. Twilio の資格情報を使用して、ルート ディレクトリに.envファイルを作成します。

TWILIO_ACCOUNT_SID=your_account_sid
TWILIO_AUTH_TOKEN=your_auth_token

  1. .cursor/mcp.jsonファイルを作成して、ツール (Cursor、Claude Desktop など) の MCP を構成します。

{
  "mcpServers": { 
    "twilio_manager_mcp_abs": {
      "command": "uv",
      "args": ["--directory", "/path/to/twilio_manager_mcp", "run", "mcp", "run", "./twilio_manager_mcp.py"],
      "env": {
        "TWILIO_ACCOUNT_SID": "your_account_sid",
        "TWILIO_AUTH_TOKEN": "your_auth_token"
      }
    },
    "twilio_manager_mcp_uvx": {
      "command": "uvx",
      "args": [ "twilio-manager-mcp" ],
      "env": {
        "TWILIO_ACCOUNT_SID": "your_account_sid",
        "TWILIO_AUTH_TOKEN": "your_auth_token"
      }
    },
    "twilio_manager_mcp_sse": {
      "url": "http://localhost:8000/sse"
    }
  }
}

ドッカー

導入と管理を容易にするために、Docker を使用して Twilio Manager MCP を実行できます。

Docker Composeの使用

このプロジェクトには、以下を設定する Docker Compose 構成が含まれています。

  • Twilio Manager MCP サービス

  • 自動HTTPSを備えたTraefikリバースプロキシ

  1. .envファイルで環境変数を設定します。

# Twilio credentials
TWILIO_ACCOUNT_SID=your_account_sid
TWILIO_AUTH_TOKEN=your_auth_token

# Domain configuration for Traefik
DOMAIN_NAME=yourdomain.com
ACME_EMAIL=user@yourdomain.com

# Address details (optional)
ADDRESS_CUSTOMER_NAME=
ADDRESS_FRIENDLY_NAME=
ADDRESS_STREET=
ADDRESS_CITY=
ADDRESS_REGION=
ADDRESS_POSTAL_CODE=
ADDRESS_ISO_COUNTRY=

  1. サービスを開始します。

docker-compose up -d

アプリケーションは、HTTPS が有効になっている構成済みのドメインで利用できるようになります。

Docker Compose なしで Docker を使用する

Traefik を使用せずに Twilio Manager MCP コンテナのみを実行したい場合:

  1. Docker イメージをビルドします。

docker build -t twilio-manager-mcp .

  1. コンテナを実行します。

docker run -p 8000:8000 \
  -e TWILIO_ACCOUNT_SID=your_account_sid \
  -e TWILIO_AUTH_TOKEN=your_auth_token \
  twilio-manager-mcp

SSE エンドポイントはhttp://localhost:8000/sseで利用できます。

使用法

カーソル、クロードデスクトップ、またはその他のMCP互換ツールを使用

この MCP を使用するには、次の 3 つのオプションがあります。

  1. 直接UVX統合（推奨）:

    • twilio_manager_mcp_uvx設定を使用する

    • これは最も簡単な方法であり、uvxですぐに使用できます。

  2. 直接UV統合：

    • twilio_manager_mcp_abs設定を使用する

    • インストール先のフルパスを指定する必要があります

  3. SSE サーバー:

    • twilio_manager_mcp_sse設定を使用する

    • まず SSE サーバーを起動します。

      uvicorn twilio_manager_mcp_sse:app --host 0.0.0.0 --port 8000

利用可能なツール

ツール名

説明

list_twilio_subaccounts

すべてのTwilioサブアカウントを一覧表示する

get_account_phone_numbers

特定のサブアカウントの電話番号を取得する

get_all_phone_numbers

サブアカウント間で電話番号を転送する

get_regulatory_bundle_sid

サブアカウントの規制バンドル SID を取得する

Cursor/Claude デスクトップでの使用例

設定が完了すると、AI アシスタントの会話でツールを直接使用できるようになります。

  1. すべてのサブアカウントを一覧表示します:

# The AI will automatically use the MCP to list all subaccounts
# No need to write code - just ask "List all Twilio subaccounts"

  1. サブアカウントの電話番号を取得します。

# Simply ask: "Show me all phone numbers for subaccount AC..."

Pythonの直接使用

プログラムで直接使用する場合:

from mcp import ClientSession
from clients.client import MCPClient

async with MCPClient("uvx", ["twilio-manager-mcp"], env={}) as session:
    # List available tools
    tools = (await session.list_tools()).tools
    
    # List all subaccounts
    subaccounts = await session.invoke("list_twilio_subaccounts")
    
    # Get phone numbers for a subaccount
    numbers = await session.invoke("get_account_phone_numbers", {"account_sid": "AC..."})

プロジェクト構造

twilio_manager_mcp/
├── api/
│   └── async_twilio_api.py    # Async Twilio API implementation
├── clients/
│   ├── client.py              # Direct MCP client implementation
│   └── client_sse.py          # SSE client implementation
├── twilio_manager_mcp.py      # Core MCP server implementation
├── twilio_manager_mcp_sse.py  # SSE server wrapper
├── requirements.txt           # Project dependencies
└── README.md                 # This file

発達

開発には、UV の仮想環境管理を使用できます。

# Create a virtual environment
uv venv

# Activate the virtual environment
source .venv/bin/activate  # On Unix
.venv\Scripts\activate     # On Windows

# Install dependencies in development mode
uv pip install -e .

貢献

貢献を歓迎します！お気軽にプルリクエストを送信してください。

ライセンス

MITライセンス

Available Tools

4 tools
get_account_phone_numbersC

Get all phone numbers associated with a Twilio subaccount

ParametersJSON Schema
NameRequiredDescriptionDefault
account_sidYes

TDQS

C2.8/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the action ('Get') but doesn't describe what 'Get all phone numbers' entails—e.g., whether it returns a list, includes pagination, requires specific permissions, or has rate limits. This is a significant gap for a tool with no annotation coverage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that directly states the tool's purpose without unnecessary words. It is front-loaded and appropriately sized, making it easy to parse quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the lack of annotations, 0% schema description coverage, and no output schema, the description is incomplete. It doesn't address behavioral aspects like return format, error handling, or usage constraints, which are crucial for a tool with one required parameter and no structured guidance.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 0% description coverage, so the description must compensate. It mentions 'account_sid' implicitly but doesn't explain what this parameter represents, its format, or how to obtain it. Without this additional semantic information, the agent lacks context for proper usage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('Get') and resource ('all phone numbers associated with a Twilio subaccount'), making the purpose immediately understandable. However, it doesn't explicitly differentiate from sibling tools like 'get_all_phone_numbers', which might have overlapping functionality, so it doesn't reach the highest score.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives like 'get_all_phone_numbers' or 'list_twilio_subaccounts'. It lacks context about prerequisites, such as whether the account_sid must be for a subaccount specifically, or any exclusions. This leaves the agent without clear usage instructions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_all_phone_numbersC

Get all phone numbers associated with a Twilio subaccount

ParametersJSON Schema
NameRequiredDescriptionDefault
source_account_sidYes
phone_number_sidYes
target_account_sidYes

TDQS

C2.7/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It states a read operation ('Get'), implying it's likely non-destructive, but doesn't disclose behavioral traits such as authentication needs, rate limits, pagination, error handling, or what 'all' entails (e.g., scope, limits). For a tool with 3 required parameters and no annotation coverage, this is a significant gap in transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that directly states the tool's purpose without unnecessary words. It's appropriately sized and front-loaded, with zero waste, making it easy to parse quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (3 required parameters, no annotations, no output schema), the description is incomplete. It lacks details on parameter usage, behavioral context, and output expectations. For a tool that likely involves account and phone number management, more guidance is needed to help an agent use it correctly, especially with sibling tools present.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, meaning parameters are undocumented in the schema. The description adds no meaning beyond the schema—it doesn't explain what the parameters (source_account_sid, phone_number_sid, target_account_sid) do, why they're required, or how they relate to 'getting all phone numbers'. With 3 required parameters and no compensation in the description, this fails to provide necessary semantic context.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Get') and resource ('all phone numbers associated with a Twilio subaccount'), providing specific verb+resource pairing. However, it doesn't explicitly differentiate from sibling tools like 'get_account_phone_numbers' or 'list_twilio_subaccounts', which likely have overlapping functionality. The purpose is clear but lacks sibling distinction.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites, context for selecting this over siblings like 'get_account_phone_numbers', or any exclusions. Usage is implied by the name and description alone, with no explicit when/when-not instructions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_regulatory_bundle_sidC

Get the regulatory bundle SID for a Twilio subaccount

ParametersJSON Schema
NameRequiredDescriptionDefault
subaccount_sidYes

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the action is to 'Get', implying a read operation, but doesn't specify if it requires authentication, rate limits, error conditions, or what the output format might be (e.g., a string SID). This leaves significant gaps in understanding how the tool behaves.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, clear sentence with no wasted words. It front-loads the key action and resource, making it easy to understand at a glance. Every part of the sentence contributes directly to the tool's purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (a read operation with one parameter), lack of annotations, and no output schema, the description is incomplete. It doesn't explain what a 'regulatory bundle SID' is, how it's used, or what the return value looks like, leaving the agent with insufficient context to use the tool effectively.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description mentions 'for a Twilio subaccount', which aligns with the single parameter 'subaccount_sid' in the schema. However, schema description coverage is 0%, so the description doesn't add details beyond the parameter's existence, such as format or validation rules. With one parameter and no schema descriptions, the baseline is 3 as it minimally compensates.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Get') and the resource ('regulatory bundle SID for a Twilio subaccount'), making the purpose understandable. It doesn't explicitly differentiate from sibling tools like 'list_twilio_subaccounts', which lists subaccounts rather than retrieving a specific bundle SID, but the distinction is implied through the specific resource focus.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. The description lacks context about prerequisites, such as needing a valid subaccount SID, or comparisons to other tools that might handle regulatory data. Usage is implied only by the tool's name and purpose.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_twilio_subaccountsB

List all Twilio subaccounts or filter by friendly name. Provide an empty string for all subaccounts

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

B3.4/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It describes the basic operation (listing/filtering subaccounts) but lacks details on permissions, rate limits, pagination, or response format. For a tool with zero annotation coverage, this is a significant gap in transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that front-loads the main purpose and includes essential details without waste. It's appropriately sized for a simple tool with no parameters, making it easy to understand quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's low complexity (0 parameters, no output schema, no annotations), the description is adequate but has clear gaps. It covers the basic operation but lacks details on behavioral aspects like response format or error handling. Without annotations or output schema, the description should do more to compensate, but it's minimally viable for this simple case.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 0 parameters with 100% coverage, so no parameters are documented in the schema. The description adds value by explaining that filtering by friendly name is possible and that an empty string returns all subaccounts, which clarifies the tool's behavior beyond the empty schema. Since there are 0 parameters, the baseline is 4, and the description provides useful context.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose with a specific verb ('List') and resource ('Twilio subaccounts'), and mentions optional filtering by friendly name. However, it doesn't explicitly differentiate this tool from its sibling tools (get_account_phone_numbers, get_all_phone_numbers, get_regulatory_bundle_sid), which appear to be related but distinct operations. The description is clear but lacks sibling differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage context by mentioning filtering by friendly name and providing an empty string for all subaccounts, but it doesn't explicitly state when to use this tool versus alternatives or any prerequisites. There's no guidance on when not to use it or comparisons with sibling tools, leaving usage somewhat ambiguous.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 4 tool updatesv1.0.0
    • Changedget_account_phone_numbers1 field changed
      • addedInput schema / title
        Added value: +"get_account_phone_numbers_for_subaccountArguments"
    • Changedget_all_phone_numbers1 field changed
      • addedInput schema / title
        Added value: +"transfer_phone_numberArguments"
    • Changedget_regulatory_bundle_sid1 field changed
      • addedInput schema / title
        Added value: +"get_regulatory_bundle_sidArguments"
    • Changedlist_twilio_subaccounts1 field changed
      • addedInput schema / title
        Added value: +"list_all_twilio_subaccountsArguments"
  2. 4 tool updates
    • First observedget_account_phone_numbers
    • First observedget_all_phone_numbers
    • First observedget_regulatory_bundle_sid
    • First observedlist_twilio_subaccounts
Deploy Server
Context Every Agent Can ShareAgents share what they learn, hand off work, and keep it when you switch models. Start with 5 GB free.fulcradynamics.comAd

TDQS

C2.9/5.0

Scored across 4 tools

Disambiguation2/5

Two tools have nearly identical purposes: 'get_account_phone_numbers' and 'get_all_phone_numbers' both retrieve phone numbers for Twilio subaccounts, creating clear ambiguity. The other two tools target distinct resources (regulatory bundles and subaccounts), but the overlap between the first two tools is significant and likely to cause misselection.

Naming Consistency4/5

All tools follow a consistent verb_noun pattern (e.g., get_account_phone_numbers, list_twilio_subaccounts) with clear, descriptive names. The naming style is uniform across the set, making it easy to parse and understand the actions and targets.

Tool Count3/5

With only 4 tools, the count feels thin for a server named 'TwilioManager MCP', which suggests broader Twilio API management. This limited set may not cover essential operations like sending messages, managing calls, or updating resources, making it borderline for the implied scope.

Completeness2/5

The tool surface is severely incomplete for Twilio management, lacking core functionalities such as sending SMS, making calls, or updating subaccounts. It focuses narrowly on retrieval operations (get/list) without create, update, or delete capabilities, leading to significant gaps that will hinder agent workflows.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers