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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.