Connect
Optimize
Secure
Announcing StackOne Defender: leading open-source prompt injection guard for your agent • Read More →
Production-ready Amplemarket MCP server with 43 extensible actions — plus built-in authentication, security, and optimized execution.
Coverage
Create, read, update, and delete across Amplemarket — and extend your agent's capabilities with custom actions.
Authentication
Per-user OAuth in one call. Your Amplemarket MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →Security
Every Amplemarket tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.
Prompt Injection Defense →Performance
Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Amplemarket call.
Tools Discovery →A Amplemarket MCP server lets AI agents read and write Amplemarket data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Amplemarket MCP server ships with 43 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.
Every action from Amplemarket's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Retrieve a paginated list of accounts in Amplemarket
Retrieve a specific account by its ID
Start a batch person enrichment request for up to 10,000 people
Retrieve results of a batch person enrichment request
Start a batch company enrichment request for up to 10,000 companies
Retrieve results of a batch company enrichment request
Retrieve a list of contacts by their IDs
Retrieve a specific contact by their ID
Create a new lead list in Amplemarket
Retrieve a paginated list of all lead lists in Amplemarket
Retrieve a specific lead list by its ID
Start a batch email validation request
Retrieve results of a batch email validation request
Add domains to the exclusion list
Retrieve all excluded domains from the exclusion list
Remove domains from the exclusion list
Add emails to the exclusion list
Retrieve all excluded emails from the exclusion list
Remove emails from the exclusion list
Add leads to an active or paused sequence by its ID
Add leads to an existing lead list
Retrieve the current account information for the authenticated Amplemarket account
Search for people using filters such as departments, job functions, industries, and locations
Search for companies using dynamic query filters
Retrieve a specific contact by their email address
Retrieve a paginated list of all sequences in Amplemarket
Retrieve a paginated list of all calls in Amplemarket
Retrieve all available call disposition categories
Retrieve the recording for a specific call
Retrieve a paginated list of tasks for a specific user in Amplemarket
Retrieve all available task statuses
Retrieve all available task types
Retrieve a paginated list of all mailboxes in Amplemarket
Retrieve a paginated list of all users in Amplemarket
Update the daily email sending limit for a specific mailbox
Find a single person by LinkedIn URL, email, or name and company combination
Cancel an in-progress batch person enrichment request
Find a single company by LinkedIn URL or domain
Cancel an in-progress batch company enrichment request
Log a new call in Amplemarket
Mark a specific task as completed
Skip a specific task
Cancel an in-progress batch email validation request
One endpoint. Any framework. Your agent is talking to Amplemarket in under 10 lines of code.
MCP Clients
Agent Frameworks
{
"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>"
]
}
}
}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
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
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
origin_owner_id.All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.