mcpField
B
botcall-mcp

botcall-mcp

Local
github.com/danecodesCommunication0Updated 30w ago

About botcall-mcp

botcall-mcp provides AI agents with phone numbers for receiving SMS and extracting verification codes. Its tools cover number provisioning, inbox access, number management, and usage checks.

Key features

  1. 01Provision phone numbers
  2. 02Extract SMS verification codes
  3. 03Retrieve recent SMS messages
  4. 04List and release numbers
  5. 05Check plan and usage

Use cases

  1. 01Receiving a signup verification code
  2. 02Checking incoming messages on provisioned numbers
  3. 03Releasing numbers after verification
  4. 04Reviewing account usage and limits

MCP support

Exposes phone-number and SMS operations as tools to MCP-compatible clients, including Claude Desktop and Claude Code. It uses the MCP stdio transport and requires a botcall.io API key.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"danecodes-botcall": {
"command": "npx",
"args": [
"-y",
"botcall-mcp"
],
"env": {
"BOTCALL_API_KEY": "<BOTCALL_API_KEY>"
}
}
}
}
Run commandnpx -y botcall-mcp
Environment variables to set
BOTCALL_API_KEYSecretYour botcall API key from botcall.io

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmbotcall-mcp0.1.2

Tools

6

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
countrystringNoISO country code (default: US)
areaCodestringNoPreferred area code (e.g., '206' for Seattle). Optional.

Details

From the project README

botcall-mcp

An MCP server that gives AI agents real phone numbers. Provision a number, receive SMS, and extract verification codes — all through tool calls.

Built for Claude Desktop, Claude Code, and any MCP-compatible client.

Setup

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "botcall": {
      "command": "npx",
      "args": ["-y", "botcall-mcp"],
      "env": {
        "BOTCALL_API_KEY": "bs_live_..."
      }
    }
  }
}
Claude Code
claude mcp add botcall -- npx -y botcall-mcp

Then set your API key in the environment:

export BOTCALL_API_KEY="bs_live_..."
Other MCP clients

Any client that supports the MCP stdio transport works. Run npx botcall-mcp with BOTCALL_API_KEY set.

Get an API key

Sign up at botcall.io, pick a plan, and grab your key from Dashboard → API Keys.

Tools

provision_number

Provision a new phone number for receiving SMS.

ParameterTypeDescription
areaCodestringPreferred area code, e.g. "206" (optional)
countrystringISO country code (default: "US")
get_code

Wait for an incoming SMS and extract the verification code. Long-polls until a message arrives or the timeout expires.

ParameterTypeDescription
timeoutnumberSeconds to wait (default: 30, max: 30)
numberIdstringFilter to a specific number (optional)
get_inbox

Get recent SMS messages received on your numbers.

ParameterTypeDescription
limitnumberMax messages to return (default: 10)
numberIdstringFilter to a specific number (optional)
list_numbers

List all your provisioned phone numbers. No parameters.

release_number

Release a phone number you no longer need.

ParameterTypeDescription
numberIdstringRequired. The number ID to release
get_usage

Get your current plan, limits, and usage stats. No parameters.

Example

You: Sign up for ExampleService using a phone number

Agent: I'll provision a number and handle the verification.

→ provision_number({ areaCode: "415" })
  { number: "+14155550123", id: "pn_abc123" }

→ [agent enters the number on ExampleService's signup page]

→ get_code({ numberId: "pn_abc123" })
  Verification code: 847291

→ [agent enters 847291 to complete verification]

Environment variables

VariableDescription
BOTCALL_API_KEYRequired. Your API key from botcall.io
BOTCALL_API_URLAPI base URL (default: https://api.botcall.io)

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.