ProspectingConnector
Apollo.io
Search Apollo companies and people, enrich them, run sequences, and read job postings as a hiring signal, from Claude or ChatGPT via Tulina's MCP server.
Official site: app.apollo.io
What it can do
4 read/1 write/1 send
- 01Read
Search organizations and people by firmographic and role criteria
- 02Read
Enrich a person or a company, singly or up to 10 at a time
- 03Read
Read job postings as a hiring signal
- 04Write
Read and edit contacts saved in your Apollo workspace
- 05Send
Create sequences and enroll contacts, and draft or send one-off emails
- 06Read
Read recorded conversations and order phone reveals
Two different signals live in one connector: firmographic and role search for who to reach, and live job postings as a hiring signal for when to reach them. A company hiring for a role your product touches is often a stronger trigger than firmographic fit alone.
Does Apollo have an MCP server?
Yes. Apollo documents its own MCP server at https://mcp.apollo.io/mcp, with OAuth sign-in in a browser, or a master API key for clients that cannot open one. It covers search and enrichment, contacts, accounts and deals, lists, sequences, one-off emails, tasks, analytics and conversations, and it spends your Apollo credits like the app does. Tulina reaches Apollo through its own MCP server instead, on the same link that carries the rest of your stack.
How do you connect Apollo to Claude and ChatGPT?
Through Tulina's own MCP server, in three steps:
- In Apollo, create an API key in the developer settings. Contacts, sequences, emails and conversations need a master key.
- Paste it into Tulina's Apollo connector, for yourself or for the organisation. It is stored in the vault and never shown to the model. Without your own key, company and people search and enrichment run on a small free daily quota of the platform's shared key.
- Add
https://mcp.tulina.ai/mcpto Claude or ChatGPT and sign in with your Tulina account. The MCP page has the same link.
Several Apollo keys can be connected as named accounts, and a request names the one it is for.
Tulina vs Apollo's official MCP server
Both reach the same Apollo data. They differ in how you sign in and in where credits come from.
| Apollo's MCP server | Tulina | |
|---|---|---|
| Endpoint | mcp.apollo.io/mcp, hosted by Apollo | mcp.tulina.ai/mcp, one link for every connected tool |
| Sign-in | OAuth in a browser per Apollo user, or a master API key | An Apollo API key held in Tulina's vault, for a person or for the organisation |
| Without your own key | An active Apollo account is required | A small free daily quota on company and people search and enrichment |
| Search and enrichment | Companies, people, contacts, job postings | Companies, people, job postings, single and bulk enrichment |
| Sequences and email | Create and update sequences, enroll contacts, send one-off emails | The same, with draft and send as two separate calls |
| Deals, lists and tasks | Search, create and update deals; lists; tasks | Not available |
| In the same conversation | Apollo | Apollo plus your CRM, outreach tool, enrichment waterfall and the other connected tools |
If Apollo is the only system the model needs, or you work with deals, lists and tasks, Apollo's own server is the better choice. Tulina earns its place when a prospect list is one step in a longer piece of work.
What you can ask it
"Find VP Sales at SaaS companies in France with 50 to 200 people." The agent searches organizations on the firmographic filters, then searches people at those domains by title and seniority. Search results are obfuscated, so the agent enriches the shortlist, up to 10 people per call, before showing names and emails.
"Which of these companies is hiring a data engineer right now?" The agent reads each company's active job postings and returns the ones that match, which is the hiring signal that tells you when to reach them.
"Add the three people I picked to the Q4 sequence." The agent reads your connected mailboxes and send schedules, finds the sequence, then enrolls the contacts. A dry run first shows who would be enrolled, since this starts an automated campaign to real people.
Processes chain these steps without a prompt each time. Outbound from buying signals, Build a target list from a sentence and Turn signups into pipeline all run on Apollo. Apollo pairs with Hunter and FullEnrich when a verified email or phone is still missing, and with Lemlist for outreach.
What the Apollo connector can't do
- It does not manage deals, lists or tasks, which Apollo's own server does.
- Reveals of phone numbers and personal emails need your own Apollo key. They cost extra credits, and a phone number arrives minutes later and is collected with a separate call.
- Contacts, sequences, one-off emails and conversations always use your own key, and contacts need a master key. A standard key authenticates and then returns 403.
- A contact is not a person. Person search queries Apollo's shared database, while the contact tools only see people your team already saved.
- Bulk matching saves calls, not credits. Apollo bills per person.
- Updating a contact's list labels replaces its list membership instead of adding to it.
- When the free platform quota runs out, calls refuse and say it resets at midnight. Set your own key to lift it.
Why through Tulina
The connection was never the hard part.
Most systems now publish their own way for a model to reach them, and that is good: it is what Tulina connects to. The hard part is deciding who may use it, what it is allowed to return, and what the model knows before it asks.
The keys stay in one place
YouTeamOrganisation
Connect Apollo.io once. The credential is encrypted in a vault, never held in clear, and never pasted into a chat or a workflow file. A person uses their own key where they have one, their team's where they do not, the organisation's after that, so nobody is blocked and nobody holds more access than they need. Revoke it once and everything running on it stops.
What leaves is filtered before it leaves
fields droppedmasked or hashedpseudonymised
Roles decide who can reach Apollo.io at all. Beyond that, a policy on the connector itself decides what comes back. The data is minimised at the source rather than after it has already reached a model.
Every call is on the record
whatwhowhen
Runs are logged for the organisation. That is what makes an automated action reviewable after the fact, and it is what a security review asks for first.
The run starts knowing your company
namingkey accountsdecisions
A direct connection gives a model access. It does not tell it how your company names things, which accounts matter, or what was decided last quarter. Tulina carries that across every tool, so the same request against Apollo.io returns something usable instead of something generic.
Processes that run on Apollo.io
Build a target list from a sentence
AI lead generation from one sentence: companies sourced and scored on dated signals, contacts verified, checked against your CRM and staged as a campaign.
6 steps →Outbound from buying signals
Each morning, companies with a new stack or hiring signal are scored on your rubric, checked against the CRM and live sequences, and given one opener per buyer.
7 steps →Source and qualify leads
A target company gets searched across LinkedIn, ranked against your ICP, and the qualified shortlist lands in your CRM with email and mobile filled in.
6 steps →Turn signups into pipeline
PQL scoring for every trial signup: enriched, scored on your ICP, the first session read, a play chosen by your rules and a deal opened for the right rep.
7 steps →
