Connect
Optimize
Secure
Lusha MCP Server
for AI Agents
Production-ready Lusha MCP server with 40 extensible actions — plus built-in authentication, security, and optimized execution.
Lusha MCP Server
Built by 
StackOne
StackOne 
Coverage
40 Agent Actions
Create, read, update, and delete across Lusha — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Lusha MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Lusha tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.
Prompt Injection Defense →
Performance
Max Agent Context. Min Cost.
Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Lusha call.
Tools Discovery →What is the Lusha MCP Server?
A Lusha MCP server lets AI agents read and write Lusha data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Lusha MCP server ships with 40 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, and optimized agent context. Connect it from MCP clients like Claude Desktop, Cursor, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.
All Lusha MCP Tools and Actions
Every action from Lusha's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Subscriptions
- Create Subscription
Create one or more webhook subscriptions
- List Subscriptions
List all webhook subscriptions configured for the account
- Get Subscription
Retrieve a single webhook subscription by its ID
- Update Subscription
Update a webhook subscription's URL, signal types, name, active state, or secret
- Delete Subscriptions
Permanently delete one or more webhook subscriptions
Other (35)
- Get Account Usage Statistics
Retrieve current API credit usage statistics
- Search Company Names
Search company name filter values by text
- Get Company Industries
List available industries for company filtering
- Get Company Sizes
List available company size ranges for filtering
- Get Company Revenue Ranges
List available revenue ranges for company filtering
- Search Company Locations
Search location filter values by text for company filtering
- Get Company SIC Codes
List available SIC codes for company filtering
- Get Company NAICS Codes
List available NAICS codes for company filtering
- Get Company Intent Topics
List available intent topics for company filtering
- Search Company Technologies
Search technology filter values by text for company filtering
- Get Contact Departments
List available departments for contact filtering
- Get Contact Seniority Levels
List available seniority levels for contact filtering
- Get Contact Data Points
List available data point filters for contact searches
- Get Contact Countries
List all countries available for contact filtering
- Search Contact Locations
Search location filter values by text for contact filtering
- Search Single Contact
Find and enrich a single contact using search criteria
- Search Multiple Contacts
Enrich multiple contacts in a single request
- Search Single Company
Find detailed information about a single company
- Search Multiple Companies
Search for multiple companies in a single request
- Get Contact Lookalikes
Returns contact lookalikes based on seed contacts
- Get Company Lookalikes
Returns company lookalikes based on seed companies
- Search Prospecting Contacts
Search for contacts using various filters
- Search Prospecting Companies
Search for companies using various filters
- Get Signal Options
Retrieve available signal options for a specific entity type (contact or company)
- Get Contact Signals By ID
Retrieve recent signals (promotion, company change) for up to 100 Lusha contact IDs
- Search Contact Signals
Retrieve signals for contacts identified by LinkedIn URL, email, or name
- Get Company Signals By ID
Retrieve recent signals (hiring, headcount, news, traffic, IT-spend) for up to 100 Lusha company IDs
- Search Company Signals
Search for company signals using identifiers like domain, company name, or ID
- Get Webhook Audit Logs
Retrieve paginated webhook delivery audit logs
- Get Webhook Audit Log Statistics
Retrieve aggregated webhook delivery statistics
- Get Account Webhook Secret
Retrieve the account-level webhook signing secret
- Enrich Prospecting Contacts
Enrich contacts returned by the prospecting search
- Enrich Prospecting Companies
Enrich companies returned by the prospecting search
- Test Subscription
Send a test webhook delivery to verify a subscription's endpoint
- Regenerate Account Webhook Secret
Regenerate the account-level webhook signing secret
Set Up Your Lusha MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Lusha in under 10 lines of code.
MCP Clients
Agent Frameworks
JSON{
"mcpServers": {
"stackone": {
"command": "npx",
"args": [
"-y",
"mcp-remote@latest",
"https://api.stackone.com/mcp?x-account-id=<account_id>",
"--header",
"Authorization: Basic <YOUR_BASE64_TOKEN>"
]
}
}
}
Lusha MCP Server Resources
MCP Code Mode: Keeping Tool Responses Out of Agent Context
Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.
11 min
Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery
Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.
10 min
Indirect Prompt Injection Defense for MCP Tools: A Technical Guide
MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.
12 min
Lusha MCP Server FAQ
Lusha MCP server vs direct API integration — what's the difference?
A Lusha MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Lusha. A Lusha MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling Lusha at runtime. StackOne provides both.
How does Lusha authentication work for AI agents?
Lusha authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own Lusha account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Lusha MCP tools vulnerable to prompt injection?
Yes — Lusha MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.
What is the context bloat of a Lusha agent and how do I avoid it?
Context bloat happens when Lusha tool schemas and API responses eat your Lusha agent's memory, preventing it from reasoning effectively. A single Lusha query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.
Can I limit which actions my Lusha agent can access?
Yes — you can limit which actions your Lusha agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.
Can I create custom agent actions for my Lusha MCP server?
Yes — you can create custom agent actions for your Lusha MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Lusha's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Lusha MCP server?
Skip a Lusha MCP server if your integration is purely software-to-software — direct Lusha API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call Lusha actions at runtime.
What AI frameworks and AI clients does the StackOne Lusha MCP server support?
The StackOne Lusha MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.
Put your AI agents to work
All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.