Apollo MCP Tools for AI Agents
Let an agent search Apollo for target companies and people, enrich known contacts and organizations, and check remaining API capacity.
Available Tools
5 tools available in this integration
Apollo.EnrichOrganization Turn a company domain into firmographics (industry, size, revenue, funding,
Apollo.EnrichPerson Turn a known person into a verified profile with their current role and,
Apollo.GetApiUsage Report per-endpoint rate limits and how many requests remain, so the agent
Apollo.SearchOrganizations Find companies in Apollo's database that match a firmographic profile so a
Apollo.SearchPeople Find people in Apollo's database by role and the firmographics of their
Why agent-optimized tools matter
Built for intent, not API schemas
Ask the agent to "find companies in healthcare with 500–2,000 employees and identify their heads of sales." Arcade helps it use the right Apollo tools without guessing domains, person identifiers, or raw API parameters.
Up to 100x fewer tokens
Apollo searches return concise company and person records, while enrichment adds firmographics or verified profile details only when needed. The agent can qualify a list without loading full records for every match.
Complete the workflow end to end
Find target companies, identify relevant people, enrich the records, verify current roles, and return the shortlist through one toolkit designed around the complete sales-intelligence task.
Make actions predictable and controlled
Arcade tools return structured results and useful errors across users and runs. Teams can apply scope restrictions, redaction, and approval policies so agents follow the same controls every time.
Securing Apollo
The more capabilities agents get, the more useful they are. However, more capabilities bring more risks of undesired effects such as data loss and exfiltration.
This is why Arcade provides you with contextual rules that dictate how and when a tool is allowed to run. Arcade’s contextual access lets you govern tool visibility and behavior at every stage of execution and control who can see a tool, what inputs are allowed, and what comes back.
Learn about Contextual Access PoliciesFor Apollo, you can implement some of these policies:
- Decide which tools an agent is allowed to see at all. A tool that is never listed cannot be called, whoever is asking.
- Inspect the inputs a call is about to run with, and block it or send it for human approval when they fall outside what the agent should do unsupervised.
- Redact personal phone numbers and email addresses from Apollo.EnrichPerson results before they reach the model, so an agent cannot expose direct contact details.
- Strip personal phone numbers and email addresses from Apollo.SearchPeople results, leaving role and firmographic context without private contact data.
- Redact revenue and funding fields from Apollo.EnrichOrganization results before the model sees them, so sensitive company financials stay out of agent context.
How to use Apollo with your agent
Connect Apollo to your MCP client with a shared API key, then try the tools from your agent. Follow the walkthrough to configure the client and run your first company or people search.
Your questions, answered
An Apollo MCP server exposes Apollo sales-intelligence capabilities as structured tools that an AI agent can call through the Model Context Protocol. Agents can search organizations and people, enrich known records, and check API usage.
Arcade provides an Apollo MCP gateway with tools designed for agent workflows, plus authentication brokering, approval policies, redaction, and scope controls. Arcade built and optimized these Apollo tools, so teams can reach them consistently from supported clients without wiring the API themselves.
Arcade agents can search organizations by firmographic criteria, search people by role and company attributes, enrich organizations from a domain, enrich known people with verified profile details, and report Apollo API usage and remaining request limits. All five actions are read-only.
Arcade uses a shared Apollo API key or secret configured once for the integration. The credential must have access to the Apollo search, enrichment, and usage endpoints your workflows call.
No. Apollo uses one shared API key or secret configured for the integration rather than a separate Apollo account connection for every user. Arcade brokers the configured credential, and the model never receives it.
Yes. Contextual Access policies can require human approval before an Apollo call proceeds, redact response fields, or hide Apollo tools from an agent. Because all five Apollo actions are read-only, there are no write or destructive Apollo operations in this integration.
Arcade proxies Apollo API calls and does not persist your content as part of normal tool execution. The Apollo credential is brokered and stored encrypted at rest, and the model never receives it.
Any framework or client that can connect to Arcade's MCP gateway or tool APIs works, including LangChain, OpenAI Agents, CrewAI, Claude Desktop, Claude Code, Cursor, Visual Studio Code, Microsoft Copilot Studio, and GitHub Copilot.
Arcade refreshes access while the Apollo authorization remains valid. If the shared key or secret is revoked, rotated, expires, or can no longer be used, calls stop until the credential is reconnected or updated.
Apollo's own per-endpoint rate limits apply to calls made through Arcade, and searches and enrichments also draw on your Apollo plan's credits. An agent can read how many requests it has left before starting a larger batch, and a call that runs out of credits reports that rather than failing.