Connect
Optimize
Secure
Apollo MCP Server
for AI Agents
Production-ready Apollo MCP server with 45 extensible actions — plus built-in authentication, security, and optimized execution.
Apollo MCP Server
Built by 
StackOne
StackOne 
Coverage
45 Agent Actions
Create, read, update, and delete across Apollo — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Apollo MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Apollo 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 Apollo call.
Tools Discovery →What is the Apollo MCP Server?
A Apollo MCP server lets AI agents read and write Apollo data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Apollo MCP server ships with 45 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 Apollo MCP Tools and Actions
Every action from Apollo's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
An Accounts
- Create An Account
Add a new account to your team's Apollo account
- Update An Account
Update existing accounts in your team's Apollo account
Call Records
- Create Call Records
Log calls in Apollo that were made using outside systems
- Update Call Records
Update your team's call records in Apollo
Contacts
- Create Contact
Add a new contact to your team's Apollo account
- Search Contacts
Search for contacts that have been added to your team's Apollo account
- Get Contact
Retrieve details for an existing contact in your team's Apollo database
- Update Contact
Update an existing contact in your team's Apollo account
Contact Stages
- List Contact Stages
Retrieve the IDs for available contact stages in your team's Apollo account
- Update Contact Stages
Update the contact stage for multiple contacts
Deals
- Create Deal
Create new deals for an Apollo account
- Update Deal
Update the details of existing deals within your team's Apollo account
Organizations
- Search Organizations
Search for companies in the Apollo database with various filters
- Get Organization
Retrieve complete details about an organization in Apollo database
Other (31)
- Add Contacts To A Sequence
Add contacts to existing sequences in your team's Apollo account
- Create A Task
Create a single task in Apollo for you and your team
- Create A Custom Field
Add custom fields to your Apollo account for contacts, accounts, or deals
- Search For Accounts
Search for accounts that have been added to your team's Apollo account
- List Account Stages
Retrieve a list of all account stages in your team's Apollo account
- Search For Calls
Find calls that your team has made or received using the Apollo dialer
- List All Deals
Retrieve every deal that has been created for your team's Apollo account
- List Deal Stages
Retrieve information about every deal stage available in your team's Apollo account
- Search People
Search for net new people in the Apollo database with various filters
- Get Organization Job Postings
Retrieve current job postings for a specific company
- Search News Articles
Find news articles related to companies in Apollo database
- Search For Sequences
Search for sequences that have been created for your team's Apollo account
- Search For Outreach Emails
Find emails created and sent as part of Apollo sequences
- Search For Tasks
Find tasks that your team has created in Apollo
- Get A List Of Users
Retrieve the IDs for all users (teammates) in your Apollo account
- Get A List Of Email Accounts
Retrieve information about linked email inboxes in your Apollo account
- Get A List Of All Lists
Retrieve information about every list created in your Apollo account
- Get A List Of Fields
Retrieve information about all fields in your Apollo account
- Update Account Owner For Multiple Accounts
Assign multiple accounts to a different user in your team's Apollo account
- Update Contact Owners
Assign multiple contacts to a different user in your team's Apollo account
- Update Contact Status In A Sequence
Mark contacts as finished or remove them from a sequence
- View An Account
Retrieve details for an existing account in your team's Apollo database
- View Deal
Retrieve complete details about a deal within your team's Apollo account
- Organization Enrichment
Enrich data for one company
- Bulk Organization Enrichment
Enrich data for up to 10 companies with a single API call
- Activate A Sequence
Start an inactive sequence
- Deactivate A Sequence
Stop an active sequence
- Archive A Sequence
Archive a sequence and finish all contacts in it
- Check Email Stats
Review complete details for an email sent as part of an Apollo sequence
- Bulk Create Tasks
Create multiple tasks in a single API request
- View API Usage Stats And Rate Limits
View your team's usage of Apollo's APIs and rate limits for API endpoints
Set Up Your Apollo MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Apollo 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>"
]
}
}
}More Sales MCP Servers
Lemlist
60+ actions
Amplemarket
43+ actions
Salesloft
39+ actions
Gong
34+ actions
Reo.dev
8+ actions
Apollo 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
Apollo MCP Server FAQ
Apollo MCP server vs direct API integration — what's the difference?
A Apollo MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Apollo. A Apollo 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 Apollo at runtime. StackOne provides both.
How does Apollo authentication work for AI agents?
Apollo 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 Apollo account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Apollo MCP tools vulnerable to prompt injection?
Yes — Apollo 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 Apollo agent and how do I avoid it?
Context bloat happens when Apollo tool schemas and API responses eat your Apollo agent's memory, preventing it from reasoning effectively. A single Apollo 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 Apollo agent can access?
Yes — you can limit which actions your Apollo 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 Apollo MCP server?
Yes — you can create custom agent actions for your Apollo MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Apollo's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Apollo MCP server?
Skip a Apollo MCP server if your integration is purely software-to-software — direct Apollo 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 Apollo actions at runtime.
What AI frameworks and AI clients does the StackOne Apollo MCP server support?
The StackOne Apollo 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.