Skip to main content
Glama
Telnyx MCP Server

Telnyx MCP Server

by fastmcp-me

Add to Cursor Add to VS Code Add to Claude Add to ChatGPT Add to Codex Add to Gemini

Telnyx Local Model Context Protocol (MCP) Server

⚠️ DEPRECATED: This Python-based MCP server is deprecated. Please migrate to the official TypeScript version:

New Repository: https://github.com/team-telnyx/telnyx-node/tree/master/packages/mcp-server


Official Telnyx Local Model Context Protocol (MCP) Server that enables interaction with powerful telephony, messaging, and AI assistant APIs. This server allows MCP clients like Claude Desktop, Cursor, Windsurf, OpenAI Agents and others to manage phone numbers, send messages, make calls, and create AI assistants.

Quickstart with Claude Desktop

  1. Get your API key from the Telnyx Portal.

  2. Install uvx (Python package manager), install with curl -LsSf https://astral.sh/uv/install.sh | sh , brew install uv or see the uv repo for additional install methods.

  3. Go to Claude > Settings > Developer > Edit Config > claude_desktop_config.json to include the following:

{
  "mcpServers": {
    "Telnyx": {
      "command": "uvx",
      "args": ["--from", "git+https://github.com/team-telnyx/telnyx-mcp-server.git", "telnyx-mcp-server"],
      "env": {
        "TELNYX_API_KEY": "<insert-your-api-key-here>"
      }
    }
  }
}

If you're using Windows, you will have to enable "Developer Mode" in Claude Desktop to use the MCP server. Click "Help" in the hamburger menu at the top left and select "Enable Developer Mode".

Related MCP server: VoIPbin MCP Server

Running After Download

  1. Get your API key from the Telnyx Portal.

  2. Install uvx (Python package manager), install with curl -LsSf https://astral.sh/uv/install.sh | sh , brew install uv or see the uv repo for additional install methods.

  3. Clone the Git Repository
    Use Git to download the Telnyx MCP Server locally:

    git clone https://github.com/team-telnyx/telnyx-mcp-server.git
    cd telnyx-mcp-server
  4. Configure and Run with uvx
    In your Claude config, you can reference the local folder by using the --from argument. For example:

    {
      "mcpServers": {
        "Telnyx": {
          "command": "uvx",
          "args": ["--from", "/path/to/telnyx-mcp-server", "telnyx-mcp-server"],
          "env": {
            "TELNYX_API_KEY": "<insert-your-api-key-here>"
          }
        }
      }
    }
  5. This instructs Claude to run the server from the folder you cloned. Replace “/path/to/telnyx-mcp-server” with the actual location of the repository.

Available Tools

Assistant Tools

  • Create AI assistants with custom instructions and configurations

  • List existing assistants

  • Get assistant details

  • Update assistant properties

  • Delete assistants

  • Get assistant TEXML configurations

Call Control Tools

  • Make outbound phone calls

  • Hang up active calls

  • Transfer calls to new destinations

  • Play audio files during calls

  • Stop audio playback

  • Send DTMF tones

  • Speak text using text-to-speech

Messaging Tools

  • Send SMS and MMS messages

  • Get message details

  • Access and view ongoing SMS conversations (resource://sms/conversations)

Phone Number Tools

  • List your phone numbers

  • Buy new phone numbers

  • Update phone number configurations

  • List available phone numbers

Connection Tools

  • List voice connections

  • Get connection details

  • Update connection configurations

Cloud Storage Tools

  • Create buckets compatible with Telnyx Cloud Storage

  • List buckets across all regions

  • Upload files

  • Download files

  • List objects in a bucket

  • Delete objects

  • Get bucket location information

Embeddings Tools

  • List existing embedded buckets

  • Scrape and embed a website URL

  • Create embeddings for your own files

Secrets Manager Tools

  • List integration secrets

  • Create new bearer or basic secrets

  • Delete integration secrets

Tool Filtering

You can selectively enable or disable specific tools when running the MCP server. This is useful when you only need a subset of the available functionality.

Listing Available Tools

To see all available tools:

uvx --from /path/to/telnyx-mcp-server telnyx-mcp-server --list-tools

Enabling Specific Tools

You can enable only specific tools using either:

  1. Command-line argument:

    uvx --from /path/to/telnyx-mcp-server telnyx-mcp-server --tools "send_message,get_message,list_phone_numbers"
  2. Environment variable:

    {
      "mcpServers": {
        "Telnyx": {
          "command": "uvx",
          "args": ["--from", "/path/to/telnyx-mcp-server", "telnyx-mcp-server"],
          "env": {
            "TELNYX_API_KEY": "<insert-your-api-key-here>",
            "TELNYX_MCP_TOOLS": "send_message,get_message,list_phone_numbers"
          }
        }
      }
    }

Excluding Specific Tools

You can exclude specific tools while enabling all others:

  1. Command-line argument:

    uvx --from /path/to/telnyx-mcp-server telnyx-mcp-server --exclude-tools "make_call,send_dtmf"
  2. Environment variable:

    {
      "mcpServers": {
        "Telnyx": {
          "command": "uvx",
          "args": ["--from", "/path/to/telnyx-mcp-server", "telnyx-mcp-server"],
          "env": {
            "TELNYX_API_KEY": "<insert-your-api-key-here>",
            "TELNYX_MCP_EXCLUDE_TOOLS": "make_call,send_dtmf"
          }
        }
      }
    }

Example Usage

Try asking Claude:

  • "Create an AI agent that can handle customer service for an e-commerce business"

  • "Send a text message to +5555551234 saying 'Your appointment is confirmed for tomorrow at 3pm'"

  • "Make a call to my customer at +5555551234 and transfer them to my support team"

  • "Find me a phone number in Chicago with area code 312"

  • "Create an auto-attendant system using Telnyx AI assistants and voice features"

Webhook Receiver

The MCP server includes a webhook receiver that can handle Telnyx webhooks directly through ngrok. This is useful for receiving call events and other notifications from Telnyx.

Enabling Webhooks

To enable the webhook receiver, you can either use the --webhook-enabled command-line flag or set the WEBHOOK_ENABLED=true environment variable. If an NGROK_AUTHTOKEN is also provided (see 'Ngrok Integration' below), the ngrok tunnel will be automatically attempted when the server starts. The command-line flag takes precedence if both are set.

Using Command-Line Flag:

telnyx-mcp-server --webhook-enabled --ngrok-enabled

Using Environment Variable:

Alternatively, set the WEBHOOK_ENABLED=true environment variable. This is often convenient when configuring via MCP client settings (see 'Webhook Configuration in Claude Desktop' below) or in .env files.

# Example for your shell
export WEBHOOK_ENABLED=true
export NGROK_AUTHTOKEN=your_ngrok_token # Also needed for ngrok
telnyx-mcp-server

Ngrok Integration

To enable ngrok tunneling:

  1. Get an ngrok authentication token from ngrok.com

  2. Set the NGROK_AUTHTOKEN environment variable or use the --ngrok-authtoken flag:

# Using NGROK_AUTHTOKEN environment variable (recommended)
export NGROK_AUTHTOKEN=your_ngrok_token
telnyx-mcp-server --webhook-enabled # Or use WEBHOOK_ENABLED=true env var

# Or using --ngrok-authtoken command line flag
telnyx-mcp-server --webhook-enabled --ngrok-authtoken your_ngrok_token

If NGROK_AUTHTOKEN is set, the --ngrok-enabled flag is generally not required when webhooks are active.

When ngrok is enabled, the server will print the public URL that can be used to configure webhooks in the Telnyx Portal.

Important: If ngrok fails to initialize (e.g., due to an invalid authtoken, network issues, or conflicts with another ngrok process), the MCP server will exit on startup. Check the server logs for details (see Troubleshooting section).

Parent Process Monitoring

The MCP server monitors the parent process (Claude Desktop) and automatically exits when the parent process is gone. This ensures proper cleanup of resources even if Claude Desktop closes unexpectedly.

Webhook Monitoring and Runtime Control

  • You can inspect the current webhook and ngrok status by querying the resource://webhook/info resource.

  • To retrieve a history of received webhook events, use the get_webhook_events tool.

Webhook Configuration in Claude Desktop

To enable webhooks in Claude Desktop, update your configuration:

{
  "mcpServers": {
    "Telnyx": {
      "command": "uvx",
      "args": ["--from", "git+https://github.com/team-telnyx/telnyx-mcp-server.git", "telnyx-mcp-server"],
      "env": {
        "TELNYX_API_KEY": "<insert-your-api-key-here>",
        "NGROK_AUTHTOKEN": "<insert-your-ngrok-token-here>",
        "WEBHOOK_ENABLED": "true", // Enables webhooks via environment variable
        // Alternatively, you can use command-line flags in "args" instead of WEBHOOK_ENABLED in env:
        // e.g., "args": ["--from", "git+https://github.com/team-telnyx/telnyx-mcp-server.git", "telnyx-mcp-server", "--webhook-enabled"],
      }
    }
  }
}

Webhook Example



Remote MCP Now Available

Telnyx now offers a remote MCP implementation based on the latest MCP specification. This allows you to access Telnyx's powerful communications APIs through a remotely hosted MCP server. No need to run the server locally. Learn more in the official documentation.

Contributing

If you want to contribute or run from source:

  1. Clone the repository:

git clone https://github.com/team-telnyx/telnyx-mcp-server.git
cd telnyx-mcp-server
  1. Create a virtual environment and install dependencies using uv:

uv venv
source .venv/bin/activate
uv pip install -e ".[dev]"  # Includes development dependencies like ruff
  1. Create a .env file and add your Telnyx API key:

echo "TELNYX_API_KEY=YOUR_API_KEY" > .env
  1. Run the tests to make sure everything is working:

pytest
  1. Install the server in Claude Desktop: mcp install src/telnyx_mcp_server/server.py

  2. Debug and test locally with MCP Inspector: mcp dev src/telnyx_mcp_server/server.py

Code Quality with Ruff

This project uses Ruff for linting and formatting Python code. Ruff is a fast Python linter and formatter written in Rust, designed to replace multiple Python code quality tools with a single, unified tool.

Installing Ruff

Ruff is included in the development dependencies. Install it with:

uv pip install -e ".[dev]"

Using Ruff

Linting

To check your code for issues:

ruff check .

To automatically fix issues where possible:

ruff check --fix .

Formatting

To format your code:

ruff format .

Pre-commit Workflow

For the best development experience, run these commands before committing changes:

# Format code
ruff format .

# Fix linting issues
ruff check --fix .

# Run tests
pytest

Configuration

Ruff is configured in the pyproject.toml file. The configuration includes:

  • Code style rules based on PEP 8

  • Import sorting

  • Docstring style checking (Google style)

  • Code complexity checks

  • And more

See the [tool.ruff] section in pyproject.toml for the complete configuration.

Troubleshooting

Logs when running with Claude Desktop can be found at:

  • Windows: %APPDATA%\Claude\logs\mcp-server-telnyx.log

  • macOS: ~/Library/Logs/Claude/mcp-server-telnyx.log

MCP Telnyx: spawn uvx ENOENT

If you encounter the error "MCP Telnyx: spawn uvx ENOENT", confirm its absolute path by running this command in your terminal:

which uvx

Once you obtain the absolute path (e.g., /usr/local/bin/uvx), update your configuration to use that path (e.g., "command": "/usr/local/bin/uvx"). This ensures that the correct executable is referenced.

Server Fails to Start (Especially with Webhooks/Ngrok)

If the MCP server fails to start, particularly if you have webhooks enabled, it might be due to an issue with ngrok initialization. One common cause is an existing ngrok process running in the background, potentially from a previous server instance that didn't shut down cleanly.

  • Check for running processes: Use commands like ps aux | grep telnyx-mcp-server (Linux/macOS) or check Task Manager (Windows) for any lingering telnyx-mcp-server processes. Since ngrok is managed internally by the server, you typically won't see a separate 'ngrok' process.

  • Kill old processes: If found, terminate these old processes.

  • Check logs: Review the server logs (locations mentioned above) for specific error messages related to ngrok or server startup.

Available Tools

46 tools
cloud_storage_create_bucketC

Create a new bucket.

Args: bucket_name: Required. Name of the bucket to create region: Required. Region to create the bucket in (us-east-1, us-west-1, us-central-1) Returns: str: Success!! if it uploaded, otherwise returns an exception message

Inputs: request (required).

cloud_storage_delete_objectB

Delete an object from cloud storage.

Args: object_name: Required. Name of the object to delete bucket_name: Optional. Bucket to delete from (defaults to instance default) Returns: str: 'Success' if the object was deleted successfully

Inputs: request (required).

cloud_storage_download_fileA

Download a file from cloud storage.

Args: object_name: Required. Name of the object to download file_path: Required. Path where to save the downloaded file bucket_name: Optional. Bucket to download from (defaults to instance default) Returns: str: 'Success' if the file was downloaded successfully

Inputs: request (required).

cloud_storage_get_bucket_locationB

Get the region where a bucket is located.

Args: bucket_name: Optional. Name of the bucket. If None, uses default bucket.

Returns: str: The region where the bucket is located

Inputs: request (required).

cloud_storage_list_bucketsA

List all buckets across all regions.

Returns: List[Dict[str, str]]: List of dictionaries containing bucket information: - name: Name of the bucket - region: Region where the bucket is located

Inputs: no named parameters.

cloud_storage_list_objectsA

List objects in a bucket with optional prefix filtering.

Args: prefix: Optional. Only list objects beginning with this prefix. Defaults to "". bucket_name: Optional. Bucket to list from (defaults to instance default)

Returns: List[str]: List of object names

Inputs: request (required).

cloud_storage_upload_fileA

Upload a file to cloud storage.

Args: absolute_file_path: Required. Absolute File Path to the file to upload object_name: Optional. Name to give the object in storage (defaults to file name) bucket_name: Optional. Bucket to upload to (defaults to instance default) Returns: str: Success!! if it uploaded, otherwise returns an exception message

Inputs: request (required).

create_assistantA

Create a new AI Assistant. The user will provide some details (sometimes detailed, sometimes vague) about the agent they want to create.

Args: name: Required. Name of the assistant. If not provided, will be generated based on context. model: Required. Model to use for the assistant. Defaults to meta-llama/Meta-Llama-3.1-70B-Instruct. instructions: Required. Core instructions or behaviors for the agent. description: Optional. A summary of the agent's purpose. tools: Optional. List of tools for the assistant, each containing: - type: Required. Type of tool ("function", "retrieval", "webhook", "hangup", "send_dtmf", "transfer"). - function: Optional. For function tools, contains: - name: Required. Name of the function. - description: Optional. Description of the function. - parameters: Required. Parameters schema for the function. - retrieval: Optional. For retrieval tools, contains: - bucket_ids: Required. List of bucket IDs for retrieval. - max_num_results: Optional. Maximum number of results to retrieve. - webhook: Optional. For webhook tools, contains: - name: Required. The name of the tool. - description: Required. The description of the tool. - url: Required. The URL of the external tool to be called. This URL can be templated like: https://example.com/api/v1/{id}, where {id} is a placeholder for a value that will be provided by the assistant if path_parameters are provided with the id attribute. - method: Optional. The HTTP method to be used. Possible values: [GET, POST, PUT, DELETE, PATCH]. Default value: POST. - headers: Optional. Array of header objects with: - name: String name of the header. - value: String value of the header. Supports mustache templating. e.g., Bearer {{#integration_secret}}test-secret{{/integration_secret}}. Secrets can be found in list_integration_secrets - body_parameters: Optional. JSON Schema object describing the body parameters: - properties: Object defining the properties of the body parameters. - required: Array of strings listing required properties. - type: String. Possible value: "object". - path_parameters: Optional. JSON Schema object describing the path parameters: - properties: Object defining the properties of the path parameters. - required: Array of strings listing required properties. - type: String. Possible value: "object". - query_parameters: Optional. JSON Schema object describing the query parameters: - properties: Object defining the properties of the query parameters. - required: Array of strings listing required properties. - type: String. Possible value: "object". - hangup: Optional. For hangup tools, contains: - description: Optional. Description of the hangup function. Defaults to "This tool is used to hang up the call." - send_dtmf: Optional. For DTMF tools, contains an empty object. This tool allows sending DTMF tones during a call. - transfer: Optional. For transfer tools, contains: - targets: Required. Array of transfer targets, each with: - name: Optional. Name of the target. - to: Required. Destination number or SIP URI. - from: Required. Number or SIP URI placing the call. - custom_headers: Optional. Array of custom SIP headers, each with: - name: Required. Name of the header. - value: Required. Value of the header. Supports mustache templating. greeting: Optional. A short welcoming message. Will be generated if not provided. llm_api_key_ref: Optional. LLM API key reference. transcription: Optional. Transcription settings with: - model: Optional. Model to use for transcription. messaging_settings: Optional. Messaging settings with: - default_messaging_profile_id: Optional. Default messaging profile ID. - delivery_status_webhook_url: Optional. Webhook URL for delivery status updates. insight_settings: Optional. Insight settings with: - insight_group_id: Optional. Insight group ID. dynamic_variables_webhook_url: Optional. Dynamic variables webhook URL. dynamic_variables: Optional. Dynamic variables dictionary.

Returns: Dict[str, Any]: Response data

Inputs: request (required).

create_call_control_applicationA

Create a call control application.

Args: application_name: Required. A user-assigned name to help manage the application. webhook_event_url: Required. The URL where webhooks related to this connection will be sent. Must include a scheme, such as 'https'. active: Optional boolean. Specifies whether the connection can be used. Defaults to True. anchorsite_override: Optional. Directs Telnyx to route media through the site with the lowest round-trip time. Defaults to "Latency". dtmf_type: Optional. Sets the type of DTMF digits sent from Telnyx to this Connection. Defaults to "RFC 2833". first_command_timeout: Optional boolean. Specifies whether calls should hangup after timing out. first_command_timeout_secs: Optional integer. Seconds to wait before timing out a dial command. Defaults to 30. inbound: Optional dictionary. Inbound call settings with these possible keys: - channel_limit: Optional integer. Maximum number of concurrent inbound calls. - shaken_stir_enabled: Optional boolean. Enable SHAKEN/STIR verification for inbound calls. - sip_subdomain: Optional string. SIP subdomain for the application. - sip_subdomain_receive_settings: Optional string. Settings for SIP subdomain receiving. outbound: Optional dictionary. Outbound call settings with these possible keys: - channel_limit: Optional integer. Maximum number of concurrent outbound calls. - outbound_voice_profile_id: Optional string. ID of the outbound voice profile to use. webhook_api_version: Optional. Determines which webhook format will be used. Defaults to "1". webhook_event_failover_url: Optional. The failover URL for webhooks if the primary URL fails. webhook_timeout_secs: Optional integer. Seconds to wait before timing out a webhook. Returns: Dict[str, Any]: Response data

Inputs: request (required).

create_embeddingsC

Embed a bucket that containe files.

Args: bucket_name: Required. Bucket Name. The bucket must exist (string) document_chunk_size: Optional. Document Chunk Size (integer) document_chunk_overlap_size: Optional. Document Chunk Overlap Size (integer) embedding_model: Optional. Supported models (thenlper/gte-large, intfloat/multilingual-e5-large, sentence-transformers/all-mpnet-base-v2) to vectorize and embed documents. loader: Optional. (default, intercom) (string)

Agent should prefer only rely on required fields unless user explicitly provides values for optional fields.

Returns: Dict[str, Any]: Response data containing the embeddings

Inputs: request (required).

create_integration_secretA

Create an integration secret.

Args: identifier: Required. The unique identifier of the secret. type: Required. The type of secret (bearer, basic). token: Optional. The token for the secret (required for bearer type). username: Optional. The username for the secret (required for basic type). password: Optional. The password for the secret (required for basic type).

Returns: Dict[str, Any]: Response data containing the created Integration Secret Object (record_type: "integration_secret")

Inputs: request (required).

create_messaging_profileA

Create a messaging profile.

Args: name: Required. A user friendly name for the messaging profile. whitelisted_destinations: Required. List of destinations to which messages are allowed to be sent (ISO 3166-1 alpha-2 country codes). Use ["*"] to allow all destinations. enabled: Optional boolean. Specifies whether the messaging profile is enabled. Defaults to True. webhook_url: Optional. The URL where webhooks related to this messaging profile will be sent. webhook_failover_url: Optional. The failover URL for webhooks if the primary URL fails. webhook_api_version: Optional. Webhook format version ("1", "2", or "2010-04-01"). Defaults to "2". number_pool_settings: Optional dictionary. Number pool configuration with possible settings: - use_pool: Boolean indicating whether to use number pool. - sticky_sender: Boolean indicating whether to use sticky sender. - pool_weights: Dictionary mapping phone number types to weights. url_shortener_settings: Optional dictionary. URL shortener configuration with possible settings: - enabled: Boolean indicating whether URL shortening is enabled. - domains: List of domains to be shortened. alpha_sender: Optional. The alphanumeric sender ID for destinations requiring it. daily_spend_limit: Optional. Maximum daily spend in USD before midnight UTC. daily_spend_limit_enabled: Optional boolean. Whether to enforce the daily spend limit. mms_fall_back_to_sms: Optional boolean. Enables SMS fallback for MMS messages. mms_transcoding: Optional boolean. Enables automated resizing of MMS media.

Returns: Dict[str, Any]: Response data

Inputs: request (required).

delete_integration_secretB

Delete an integration secret.

Args: id: Required. Secret ID.

Returns: Dict[str, Any]: Empty response on success

Inputs: id (required).

embed_urlC

Scrape and embed a given URL. For a given website, this tool will scrape the content of the pages and save the content in a new bucket. That bucket will be automatically embedded.

Args: url: Required. URL to be scraped and embedded.

Returns: Dict[str, Any]: Response data containing bucket information

Inputs: request (required).

get_assistantB

Get an AI Assistant by ID.

Args: assistant_id: Required. Assistant ID. fetch_dynamic_variables_from_webhook: Optional boolean. Whether to fetch dynamic variables from webhook. from_: Optional. From parameter for dynamic variables. to: Optional. To parameter for dynamic variables. call_control_id: Optional. Call control ID for dynamic variables.

Returns: Dict[str, Any]: Response data

Inputs: request (required).

get_assistant_texmlA

Get an assistant's TEXML by ID.

Args: assistant_id: Assistant ID

Returns: str: Assistant TEXML content

Inputs: assistant_id (required).

get_call_control_applicationC

Retrieve a specific call control application.

Args: id: Required. Identifies the call control application.

Returns: Dict[str, Any]: Response data

Inputs: request (required).

get_connectionA

Get a connection by ID.

Args: id: Required. Connection ID.

Returns: Dict[str, Any]: Response data

Inputs: id (required).

get_messageA

Retrieve a message by ID.

Args: message_id: The ID of the message to retrieve

Returns: Dict[str, Any]: Response data containing message details

Inputs: message_id (required).

get_messaging_profileB

Retrieve a messaging profile by ID.

Args: profile_id: The ID of the messaging profile to retrieve

Returns: Dict[str, Any]: Response data containing messaging profile details

Inputs: profile_id (required).

get_phone_numberA

Get a phone number by ID.

Args: id: Phone number ID as string

Returns: Dict[str, Any]: Response data containing Number Object(s) (record_type: "phone_number")

Inputs: id (required).

get_webhook_eventsA

Get the most recent webhook events received by the handler.

Args: limit: Maximum number of events to return (default: 10) event_type: Filter events by type (default: all types)

Returns: Dict containing webhook events and metadata

Inputs: limit, event_type.

hangupB

Hang up a call.

Args: call_control_id: Required. Call control ID.

Returns: Dict[str, Any]: Response data

Inputs: request (required).

initiate_phone_number_orderC

Initiate a phone number order.

Args: phone_number: Required. Phone number to buy. connection_id: Optional. Connection ID to associate with the number.

Returns: Dict[str, Any]: Response data

Inputs: request (required).

list_assistantsB

List all AI Assistants.

Returns: Dict[str, Any]: List of assistants

Inputs: no named parameters.

list_available_phone_numbersB

List available phone numbers.

Args: page: Optional integer. Page number. Defaults to 1. page_size: Optional integer. Page size. Defaults to 20. filter_phone_number_starts_with: Optional. Filter numbers starting with pattern. filter_phone_number_ends_with: Optional. Filter numbers ending with pattern. filter_phone_number_contains: Optional. Filter numbers containing pattern. filter_locality: Optional. Filter by locality (city). filter_administrative_area: Optional. Filter by administrative area (state). filter_country_code: Optional. Filter by country code. filter_features: Optional. List of features to filter by.

Returns: Dict[str, Any]: Response data

Inputs: request (required).

list_call_control_applicationsA

List call control applications.

Args: page: Optional integer. Page number. Defaults to 1. page_size: Optional integer. Page size. Defaults to 20. filter_application_name_contains: Optional. Filter by application name (case-insensitive, min 3 characters). filter_outbound_voice_profile_id: Optional. Filter by associated outbound voice profile ID. sort: Optional. Sort order for results (created_at, connection_name, active). Defaults to created_at.

Returns: Dict[str, Any]: Response data

Inputs: request (required).

list_connectionsB

List connections.

Args: page: Optional integer. Page number. Defaults to 1. page_size: Optional integer. Page size. Defaults to 20. filter_connection_name_contains: Optional. Filter by connection name. filter_outbound_voice_profile_id: Optional. Filter by outbound voice profile ID. sort: Optional. Sort order (created_at, connection_name, active).

Returns: Dict[str, Any]: Response data

Inputs: request (required).

list_embedded_bucketsA

List user embedded buckets.

Returns: Dict[str, Any]: Response data eg: { "data": { "buckets": [ "string" ] } }

Inputs: no named parameters.

list_integration_secretsA

List integration secrets.

Args: page: Optional integer. Page number. Defaults to 1. page_size: Optional integer. Page size. Defaults to 25. filter_type: Optional. Filter by secret type (bearer, basic).

Returns: Dict[str, Any]: Response data containing Integration Secret Object(s) (record_type: "integration_secret")

Inputs: request (required).

list_messaging_profilesB

List messaging profiles.

Args: page: Optional integer. Page number. Defaults to 1. page_size: Optional integer. Page size. Defaults to 20. filter_name: Optional. Filter by profile name.

Returns: Dict[str, Any]: Response data

Inputs: request (required).

list_phone_numbersC

List phone numbers.

Args: page: Optional integer. Page number. Defaults to 1. page_size: Optional integer. Page size. Defaults to 20. filter_tag: Optional. Filter by phone number tag. filter_phone_number: Optional. Filter by phone number. filter_status: Optional. Filter by phone number status. filter_country_iso_alpha2: Optional. Filter by country ISO alpha-2 code.

Returns: Dict[str, Any]: Response data

Inputs: request (required).

make_callC

Make a call.

Args: to: Required. Destination number or SIP URI. from_: Required. Source number. connection_id: Optional. Connection ID of a call control application to use for the call (same as call_control_application_id).

Returns: Dict[str, Any]: Response data

Inputs: request (required).

mcp_telnyx_delete_assistantB

Delete an AI Assistant.

Args: id: Assistant ID as string

Returns: Dict[str, Any]: Response data containing deletion status

Inputs: id (required).

playback_startA

Start audio playback on a call.

Args: call_control_id: Required. Call control ID. audio_url: Required. URL of audio file to play. loop: Optional. Number of times to loop the audio. Valid values: infinity, 1, 2, 3, 4, 5. overlay: Optional boolean. Whether to overlay the audio on existing audio. Defaults to False. stop: Optional. Which audio to stop. Valid values: current, all. target_legs: Optional. Which leg(s) to play the audio on. Valid values: self, peer, both.

Returns: Dict[str, Any]: Response data

Inputs: request (required).

playback_stopA

Stop audio playback on a call.

Args: call_control_id: Required. Call control ID. overlay: Optional boolean. Whether to stop overlay audio. Defaults to False. stop: Optional. Which audio to stop. Valid values: current, all.

Returns: Dict[str, Any]: Response data

Inputs: request (required).

send_dtmfA

Send DTMF tones on a call.

Args: call_control_id: Required. Call control ID. digits: Required. DTMF digits to send (0-9, *, #, w, W). duration_millis: Optional integer. Duration of each digit in milliseconds. Defaults to 500.

Returns: Dict[str, Any]: Response data

Inputs: request (required).

send_messageC

Send a message.

Args: from_: Required. Sending address (phone number, alphanumeric sender ID, or short code). to: Required. Receiving address(es). text: Required. Message text. messaging_profile_id: Optional. Messaging profile ID. subject: Optional. Message subject. media_urls: Optional. List of media URLs. webhook_url: Optional. Webhook URL. webhook_failover_url: Optional. Webhook failover URL. use_profile_webhooks: Optional boolean. Whether to use profile webhooks. Defaults to True. type: Optional. The protocol for sending the message, either "SMS" or "MMS". auto_detect: Optional boolean. Automatically detect if an SMS message is unusually long.

Returns: Dict[str, Any]: Response data

Inputs: request (required).

speakA

Speak text on a call using text-to-speech.

Args: call_control_id: Required. Call control ID. payload: Required. Text to speak. voice: Required. Voice to use. Defaults to female payload_type: Optional. Type of payload. Valid values: text, ssml. Defaults to "text". service_level: Optional. Service level for TTS. Valid values: basic, premium. Defaults to "basic". stop: Optional. Which audio to stop. Valid values: current, all. language: Optional. Language code (e.g., 'en-US', 'arb').

Returns: Dict[str, Any]: Response data

Inputs: request (required).

start_assistant_callA

Start a call using an AI Assistant with a phone number.

Args: assistant_id: Required. ID of the assistant to use for the call. to: Required. Destination phone number to call. from_: Required. Source phone number to call from (must be a number on your Telnyx account).

Returns: Dict[str, Any]: Response data from the call initiation

Inputs: to (required), from_ (required), assistant_id (required).

transferC

Transfer a call to a new destination.

Args: call_control_id: Required. Call control ID. to: Required. Destination number or SIP URI. from_: Required. Source number.

Returns: Dict[str, Any]: Response data

Inputs: request (required).

update_assistantA

Update an AI Assistant. Once there is an agent created, you can talk the user about what can be updated in an easy manner, rather than asking for a long list of fields to update.

Args: assistant_id: Required. ID of the assistant to update. name: Optional. Name of the assistant. model: Optional. Model to use for the assistant. instructions: Optional. Core instructions or behaviors for the agent. description: Optional. A summary of the agent's purpose. tools: Optional. List of tools for the assistant, each containing: - type: Required. Type of tool (ANY of "hangup", "retrieval", "send_dtmf", "transfer", "webhook"). - retrieval: Optional. For retrieval tools, contains: - bucket_ids: Required. List of bucket IDs for retrieval. - max_num_results: Optional. Maximum number of results to retrieve. - webhook: Optional. For webhook tools, contains: - name: Required. The name of the tool. - description: Required. The description of the tool. - url: Required. The URL of the external tool to be called. This URL can be templated like: https://example.com/api/v1/{id}, where {id} is a placeholder for a value that will be provided by the assistant if path_parameters are provided with the id attribute. - method: Optional. The HTTP method to be used. Possible values: [GET, POST, PUT, DELETE, PATCH]. Default value: POST. - headers: Optional. Array of header objects with: - name: String name of the header. - value: String value of the header. Supports mustache templating, e.g., Bearer {{#integration_secret}}test-secret{{/integration_secret}}. Secrets can be found in list_integration_secrets - body_parameters: Optional. JSON Schema object describing the body parameters: - properties: Object defining the properties of the body parameters. - required: Array of strings listing required properties. - type: String. Possible value: "object". - path_parameters: Optional. JSON Schema object describing the path parameters: - properties: Object defining the properties of the path parameters. - required: Array of strings listing required properties. - type: String. Possible value: "object". - query_parameters: Optional. JSON Schema object describing the query parameters: - properties: Object defining the properties of the query parameters. - required: Array of strings listing required properties. - type: String. Possible value: "object". - hangup: Optional. For hangup tools, contains: - description: Optional. Description of the hangup function. - send_dtmf: Optional. For DTMF tools, contains an empty object. This tool allows sending DTMF tones during a call. - transfer: Optional. For transfer tools, contains: - targets: Required. Array of transfer targets, each with: - name: Optional. Name of the target. - to: Required. Destination number or SIP URI. - from: Required. Number or SIP URI placing the call. - custom_headers: Optional. Array of custom SIP headers, each with: - name: Required. Name of the header. - value: Required. Value of the header. Supports mustache templating. eg: {{#integration_secret}}test-secret{{/integration_secret}} to be used with integration secrets (Available secrets can be found in list_integration_secrets) greeting: Optional. A short welcoming message used by the agent. llm_api_key_ref: Optional. LLM API key reference. This is meant to be used for models provided by external vendors. eg: openai, anthropic, Groq, xai-org. Available secrets can be found in list_integration_secrets transcription: Optional. Transcription settings with: - model: Optional. Model to use for transcription. telephony_settings: Optional. Telephony settings with: - default_texml_app_id: Optional. Default TeXML application ID. messaging_settings: Optional. Messaging settings with: - default_messaging_profile_id: Optional. Default messaging profile ID. - delivery_status_webhook_url: Optional. Webhook URL for delivery status updates. insight_settings: Optional. Insight settings with: - insight_group_id: Optional. Insight group ID. dynamic_variables_webhook_url: Optional. Dynamic variables webhook URL. dynamic_variables: Optional. Dynamic variables dictionary.

Returns: Dict[str, Any]: Response data

Inputs: request (required), assistant_id (required).

update_connectionA

Update a connection.

Note: The Telnyx API does not support updating connections directly. Only GET, HEAD, and OPTIONS methods are allowed. Please create a new connection with the desired settings instead.

Args: id: Required. Connection ID. data: Required. Update data.

Returns: Dict[str, Any]: Response data

Raises: Exception: The Telnyx API does not support updating connections directly.

Inputs: id (required), data (required).

update_messaging_profileA

Update a messaging profile.

Args: profile_id: Required. The ID of the messaging profile to update. name: Optional. A user friendly name for the messaging profile. enabled: Optional boolean. Specifies whether the messaging profile is enabled. webhook_url: Optional. The URL where webhooks related to this messaging profile will be sent. webhook_failover_url: Optional. The failover URL for webhooks if the primary URL fails. webhook_api_version: Optional. Webhook format version ("1", "2", or "2010-04-01"). whitelisted_destinations: Optional list. Destinations to which messages are allowed (ISO 3166-1 alpha-2 country codes). Use ["*"] to allow all destinations. v1_secret: Optional. Secret used to authenticate with v1 endpoints. number_pool_settings: Optional dictionary. Number pool configuration with possible settings: - use_pool: Boolean indicating whether to use number pool. - sticky_sender: Boolean indicating whether to use sticky sender. - pool_weights: Dictionary mapping phone number types to weights. url_shortener_settings: Optional dictionary. URL shortener configuration with possible settings: - enabled: Boolean indicating whether URL shortening is enabled. - domains: List of domains to be shortened. alpha_sender: Optional. The alphanumeric sender ID for destinations requiring it. daily_spend_limit: Optional. Maximum daily spend in USD before midnight UTC. daily_spend_limit_enabled: Optional boolean. Whether to enforce the daily spend limit. mms_fall_back_to_sms: Optional boolean. Enables SMS fallback for MMS messages. mms_transcoding: Optional boolean. Enables automated resizing of MMS media.

Returns: Dict[str, Any]: Response data

Inputs: request (required), profile_id (required).

update_phone_numberC

Update a phone number.

Args: id: Required. Phone number ID. connection_id: Optional. Connection ID to associate with the number. tags: Optional. List of tags to associate with the number.

Returns: Dict[str, Any]: Response data

Inputs: id (required), request (required).

update_phone_number_messaging_settingsC

Update the messaging profile and/or messaging product of a phone number.

Args: id: Required. The phone number ID to update. messaging_profile_id: Optional. Configure the messaging profile this phone number is assigned to. Set to null to keep the current value, set to empty string to unassign, or set to a UUID to assign to that messaging profile. messaging_product: Optional. Configure the messaging product for this number. Set to null to keep the current value, or set to a product ID to change.

Returns: Dict[str, Any]: Response data

Inputs: id (required), request (required).

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    C2.7/5.0

    Scored across 46 tools

    Disambiguation2/5

    Several tools have overlapping purposes: `list_embedded_buckets` vs `cloud_storage_list_buckets`, `create_embeddings` vs `embed_url`, and `update_phone_number` vs `update_phone_number_messaging_settings` all could confuse an agent. The `update_connection` tool is a non-functional trap that always throws an exception, making it worse than useless.

    Naming Consistency2/5

    Naming conventions are inconsistent across domains: some tools use `cloud_storage_*` prefix, others use plain `verb_noun`, and `mcp_telnyx_delete_assistant` is an outlier with an unusual prefix. There is no uniform pattern, though most names are readable.

    Tool Count2/5

    With 46 tools, this server is overstuffed. It spans cloud storage, AI assistants, call control, messaging, phone numbers, and integration secrets—far too many distinct domains for a single MCP server. It would be better split into focused servers.

    Completeness2/5

    CRUD coverage is uneven: messaging profiles lack delete, connections lack create/delete, call control applications lack update/delete, and cloud storage lacks delete bucket. The non-functional `update_connection` tool creates a false sense of capability, and there are no update tools for integration secrets.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      B
      quality
      D
      maintenance
      MCP server for the seven.io API, enabling SMS, voice, RCS messaging, and account management through natural language.
      44
      18 npm
      1
      MIT
    • A
      license
      B
      quality
      B
      maintenance
      An MCP server that enables AI assistants to interact with the VoIPbin CPaaS platform, exposing tools for managing calls, flows, messaging, conferencing, and more.
      66
      1
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      A comprehensive MCP server for TELNYX integration, enabling AI assistants to send SMS messages, make voice calls, and handle incoming communications via webhooks.
      MIT