# Apollo MCP connector Connect Apollo to Elaichi and Claude, ChatGPT, Cursor, or any MCP client can search people and companies and enrich contacts and accounts, with every lookup running inside each person's own Apollo access. Source: https://elaichi.ai/connectors/apollo/ ## Facts | | | | --- | --- | | Application | Apollo | | Category | Sales Intelligence | | AI tools | 4 | | Authentication | Connects with an API key | | Bring your own OAuth app | No | | MCP endpoint | https://api.elaichi.ai/mcp | | Works with | Claude, ChatGPT, Cursor, any MCP client, and the Elaichi Agent | | Tools advertised by name | No. Connected tools are never listed one by one, however few there are. The endpoint advertises `search_tools` and `execute_tool` instead | ## What you can ask once Apollo is connected - Find VP Sales contacts at fintech companies in Austin - Enrich Priya Shah at Northwind with work email and phone - Which SaaS companies in London have 200 to 500 employees? ## Connect Apollo in Elaichi This happens once for the organization, before any client is involved. 1. Open Connections, choose Add connection, and pick Apollo. 2. Optionally set Share with, then press Connect. 3. Paste an Apollo API key. One person generates a token in Apollo and pastes it once. Everyone else works through Share with, and never sees it. Credentials are vaulted and nobody, including the AI, reads them back. The connection becomes a toolbox immediately, so you can curate which Apollo tools are exposed, rename them, or freeze arguments before anyone points a client at it. ## Apollo MCP connector for Claude Endpoint: https://api.elaichi.ai/mcp 1. Open Customize, then Connectors. 2. Press Add. 3. Name it, paste the MCP server URL, then Continue. 4. Sign in and approve. On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves. ## Apollo MCP connector for Claude Code Endpoint: https://api.elaichi.ai/mcp 1. In a terminal, run `claude mcp add` with the endpoint. 2. Start Claude Code and run `/mcp`. 3. Pick elaichi, then sign in and approve in the browser. ```bash claude mcp add --transport http elaichi --scope user https://api.elaichi.ai/mcp ``` Use `--scope project` instead to share it with the repository through `.mcp.json`. ## Apollo MCP connector for ChatGPT Endpoint: https://api.elaichi.ai/mcp 1. Open Plugins, then press the + button. 2. Name it and paste the endpoint into Server URL. 3. Leave Authentication on OAuth, then tick the risk acknowledgement. 4. Press Create, then sign in and approve. Works on the web today. The plugin directory lives at chatgpt.com/plugins. ## Apollo MCP connector for Cursor Endpoint: https://api.elaichi.ai/mcp 1. Open `~/.cursor/mcp.json`. 2. Add the endpoint under `mcpServers`. 3. Reload Cursor, then sign in and approve. Set up per machine, so repeat it on each computer you work from. ## Connect Apollo to any MCP client Endpoint: https://api.elaichi.ai/mcp 1. Add the endpoint as a remote MCP server. 2. Sign in and approve. The Elaichi Agent already has these tools, with nothing to set up. ## What the consent screen decides Every scope the client asks for starts ticked except "Delete data and remove access", which you tick yourself. Calling a Apollo tool needs "Run your connected tools". Over MCP there is no trusted place to confirm a write in the moment, so the consent screen is the standing approval rather than a formality. Think hard before granting Run your connected tools, which can also delete in connected apps and cannot be undone. ## What teams do with Apollo through Elaichi ### Research an account before the first call Sales. Ask for the company's size, industry, location and funding from Apollo, then the people who hold the titles you sell to. Walk in knowing who matters. ### Build a prospect list from a plain description Sales Development. Describe the titles, industries and regions you want and get a list of matching people from Apollo. Narrow it by company size or seniority in the next message. ### Fill in a lead's email and phone Sales Development. Give a name and a company and Apollo returns the work email, phone, title and LinkedIn profile. No more copying one field at a time. ### Find lookalike companies for a campaign Marketing. Start from a customer you already have and ask Apollo for companies with the same industry, headcount and technology. Hand the list to the team that runs the campaign. ### Clean up a record with missing fields Revenue Operations. Paste a company domain and get its full Apollo profile, including industry, employee count and headquarters, so the account in your CRM is complete. ### Map the people at a target company Recruiting. Ask Apollo who works in engineering or product at a company you are hiring from, with titles and seniority, before anyone writes an outreach message. ## Elaichi vs Zapier MCP vs Composio for Apollo All three can connect Apollo to an AI assistant, and all three have admin controls. They differ in where access lives and how you pay. | What to check | Elaichi | Zapier MCP | Composio | | --- | --- | --- | --- | | Where the AI connects | One address for the whole organization. Endpoint: https://api.elaichi.ai/mcp | A server per member, created at sign-in. | An MCP endpoint per team, or an SDK. | | Control over Apollo tools | Allow or restrict single Apollo tools, per role or user. | App and action restrictions on the account. | Role permissions, down to the action. | | Record of calls | One audit entry per Apollo call. | A History tab of tool calls. | A log of every tool call. | | Single sign-on | SAML or OIDC, plus SCIM, on Gold. | SAML on Enterprise. | SAML and OIDC on Enterprise. | | Price | $15 per user per month. | 2 tasks per successful call. | Billed per tool call. | Sources: Zapier MCP [docs](https://docs.zapier.com/mcp/get-started/quickstart), [security](https://docs.zapier.com/mcp/manage/security), [usage](https://docs.zapier.com/mcp/features/usage); Composio [docs](https://docs.composio.dev/docs/composio-connect), [gateway](https://composio.dev/mcp-gateway), [enterprise](https://composio.dev/enterprise), [pricing](https://composio.dev/pricing). Checked September 2026. Longer take: [Zapier MCP alternative](/blog/zapier-mcp-alternative/) and [when you don't need an MCP gateway](/blog/when-you-dont-need-an-mcp-gateway/). ## Frequently asked questions ### How do I connect Apollo to Claude? Connect Apollo in Elaichi first: Apollo signs in with an API key, which you paste in once, and there is no OAuth application to register and no client ID or secret to generate. Then open Claude, go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. Sign in to Elaichi as yourself and Apollo is available in Claude from that point on. ### Does Apollo work with ChatGPT and Cursor as well as Claude? Yes. Apollo is connected once in Elaichi, and the same endpoint, https://api.elaichi.ai/mcp, is added to Claude, ChatGPT, Cursor, any MCP client, and the Elaichi Agent. There is nothing separate to set up for each client. ### What can an AI agent actually do with my Apollo data? With Apollo connected, an AI agent can search for people by title, seniority, industry and location, search for companies by size, industry and technology, and enrich a single person or company with email, phone, headcount and other profile fields. Short concrete asks work best, such as a name and a company, or a title and a region. This connector looks things up and fills in details; it does not change anything in Apollo. ### Does connecting Apollo give the AI everything in my Apollo account? No. Every Apollo request runs as the person who signed in to Elaichi, so the agent can see only what that person's own Apollo account and credits allow. Elaichi can narrow that further by restricting actions for a team, and it can never widen access beyond what the person already has in Apollo. ### Can my team share one Apollo connection? Yes. One person connects Apollo in Elaichi and shares the connection with a team, and nobody else ever handles the Apollo API key. Each teammate still signs in to Elaichi as themselves, so every Apollo search and enrichment in the audit log names the person who ran it. ### Can I stop an agent from deleting or changing things in Apollo? The Apollo connector only searches and enriches people and companies, so it has no way to delete or edit records in Apollo. Restrictions still work per action: if you restrict enrichment for a team, that action is removed from what their AI client can reach and cannot be called, whatever the prompt says. ### What happens to an Apollo connection when someone leaves? Offboarding a person in Elaichi ends their access to Apollo through every client at once. A shared Apollo connection keeps working for everyone else on the team. If you want Apollo gone entirely, disconnecting it once in Elaichi removes it from Claude, ChatGPT, Cursor, and every other client at the same time. ### Does the Apollo MCP connector work with Gemini, Codex, Claude Code or other MCP clients? Yes. Apollo is reached over the same MCP endpoint every client uses, so anything that speaks MCP can call it — Gemini, Codex, Claude Code, Windsurf, Cline, Zed and OpenCode among them — alongside Claude, ChatGPT, Cursor, and the Elaichi Agent. The tools on offer and the access behind them are identical whichever client asks. Only the setup screen differs. ### Is Elaichi an alternative to Zapier MCP for Apollo? Yes. Both let Claude, ChatGPT or Cursor use Apollo. Zapier MCP fits a team that already automates in Zapier, since each person signs in and acts as themselves in that account. Elaichi fits when IT wants one address for the whole company, per-tool rules by role, and a record of every Apollo call. ### How is Elaichi different from Composio for Apollo? Composio gives AI agents tools and sign-in handling across 1,000+ apps, for developers building agents or people using an assistant, billed per tool call. Elaichi gives a company's own people governed access to Apollo: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call. ## All 4 Apollo tools Every tool below is callable through https://api.elaichi.ai/mcp once Apollo is connected, subject to the toolbox it is in and the restrictions on the caller. - **Apollo people enrichment match** (Action). Find one person by email, LinkedIn URL, or a name (name, or first_name and last_name) together with the company they work at (organization_name or domain), and return their enriched profile. Costs 1-9 credits when a person is matched (more if a mobile phone is revealed), 0 credits on no match. Every parameter is sent as a query-string parameter, even though the HTTP method is POST -- Apollo's own OpenAPI spec marks every one of them `in: query`, and no JSON body is sent. Phone numbers cannot be revealed through this integration: reveal_phone_number triggers an asynchronous webhook/poll flow that is not offered here. - **Apollo organizations enrich** (Action). Find one company by domain, LinkedIn URL, or website (name alone is not accepted -- Apollo returns 422 -- but it narrows the match when sent alongside another identifier), and return its enriched profile. 1 credit per organization matched. Every parameter is sent as a query-string parameter; no JSON body is sent. This is a separate method from the pre-existing organization-enrichment.list (added before unified enrichment existed): that method's `list` resource-method type makes the engine apply the integration's inherited page-format pagination unconditionally, adding `page`/`per_page` query parameters this endpoint does not document; this `enrich` method is a custom-named method, so no pagination logic runs and no undocumented parameters are added. - **List all Apollo mixed people** (List). Search for people. 0 credits. Requires a master API key, or a key with the mixed_people_api_search OAuth scope -- a normal API key gets a 403 "endpoint access denied". Results are partial: there is no email or phone field at all in this search response (only boolean has_email/has_direct_phone flags), and the last name is masked (last_name_obfuscated, e.g. "Hu***n") rather than withheld outright, so every record from this method is partial. Every filter and the page/per_page pagination parameters are sent as query-string parameters, even though the HTTP method is POST. - **List all Apollo mixed companies** (List). Search for companies. 1 credit per page (unlike the people-search sibling, this is not free). Records here are full, not masked. Every filter and the page/per_page pagination parameters are sent as query-string parameters, even though the HTTP method is POST.