Bolna MCP Server
Manage voice AI agents, make calls, run campaigns, and control phone numbers through natural language.
README
Bolna MCP Server
Manage voice AI agents, make calls, run campaigns, and more — through natural language.
Supported Features
🤖 Agents
Build and manage AI voice agents on the Bolna platform.
Create & Configure — Create agents with custom system prompts, voices, and task configs
Manage — Get, list, update, patch, and delete agents
Control — Stop all queued calls for an agent instantly
📞 Calls
Make and manage outbound voice calls.
Outbound Calls — Initiate calls with optional scheduling, retry logic, and dynamic user context
Call Control — Stop an active call at any time
📋 Batch Campaigns
Run outbound call campaigns at scale.
Create & Schedule — Upload a list of numbers and schedule campaigns
Monitor — Track batch status, call counts, and execution history
Control — Stop running batches or delete them
📊 Call History
Executions — Retrieve full call details including transcripts, recording URLs, and telephony data
Raw Logs — Access low-level call logs for debugging
📚 Knowledgebases
Create — Build knowledgebases from PDF files (base64) or web URLs
Manage — List, get, and delete knowledgebases
📱 Phone Numbers
Search & Buy — Find and purchase phone numbers for your account
Inbound Routing — Link phone numbers to agents for inbound call handling
🎯 Dispositions
Extraction — Define structured outputs to extract from call transcripts
Bulk & Test — Create multiple dispositions at once and test them against sample transcripts
🔌 Providers & Integrations
Providers — Add, list, and remove telephony / LLM / TTS providers
Custom LLMs — Plug in your own LLM endpoint
🏢 Sub-Accounts & SIP Trunks
Sub-Accounts — Create and manage sub-accounts with usage tracking
SIP Trunks — Configure SIP trunks and manage their associated numbers
Quick Start
{
"mcpServers": {
"bolna": {
"command": "npx",
"args": ["-y", "@abhinavyadav/bolna-mcp"],
"env": {
"BOLNA_API_KEY": "your_api_key_here"
}
}
}
}
Get your API key at bolna.ai → Dashboard → API Keys.
Setup Instructions
Claude Desktop
Config file:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"bolna": {
"command": "npx",
"args": ["-y", "@abhinavyadav/bolna-mcp"],
"env": {
"BOLNA_API_KEY": "your_api_key_here"
}
}
}
}
Cursor
- Open Settings → Features → MCP
- Click + Add New MCP Server
- Set:
- Name:
bolna - Type:
command - Command:
env BOLNA_API_KEY=your_api_key_here npx -y @abhinavyadav/bolna-mcp
- Name:
Windsurf
Config file: ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"bolna": {
"command": "npx",
"args": ["-y", "@abhinavyadav/bolna-mcp"],
"env": {
"BOLNA_API_KEY": "your_api_key_here"
}
}
}
}
VS Code (Cline / Roo Code)
Config file:
- macOS:
~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
{
"mcpServers": {
"bolna": {
"command": "npx",
"args": ["-y", "@abhinavyadav/bolna-mcp"],
"env": {
"BOLNA_API_KEY": "your_api_key_here"
}
}
}
}
Claude Code (CLI)
claude mcp add npx -- -y @abhinavyadav/bolna-mcp --env BOLNA_API_KEY=your_api_key_here
Example Prompts
Call +919999999999 using my "Demo Agent" and pass candidate name as "Rahul Sharma", age 25.
Create a Hindi appointment booking agent for a hospital, then make a test call to +919999999999.
Show me all executions for agent <agent_id>. Include transcripts for calls longer than 2 minutes.
Create a batch campaign for agent <agent_id> and schedule it for tomorrow at 10 AM IST.
Search for Indian phone numbers in area code 080, show the top 3 with prices, then buy the cheapest.
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。