> For the complete documentation index, see [llms.txt](https://docs.leadbay.app/doc/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.leadbay.app/doc/leadbay-mcp/quickstart.md).
# Quickstart
Connect Leadbay to Claude and get your first qualified leads in about five minutes. This guide uses **Claude** (Claude.ai or Claude Desktop) — the simplest path. Using a different assistant? See [Installation](/doc/leadbay-mcp/installation.md) for step-by-step setup of Claude Code, ChatGPT, and Codex.
{% hint style="info" %}
You'll need a [Leadbay account](https://leadbay.ai/) and Claude (Pro, Max, Team, or Enterprise). That's it — no API tokens to copy or paste; you add one URL and sign in with your browser.
{% endhint %}
***
## First — which one are you?
Adding a custom connector needs a **paid Claude plan**, and in a **company workspace only an admin can add it**. Find your situation, then follow the steps below:
| Your situation | What to do |
| ---------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Solo / personal paid plan** (not in a company workspace) | Add it yourself — follow Step 1 below. |
| **In a company workspace, and you're the admin** | Add it yourself (Step 1) — your teammates then just **Connect**. |
| **In a company workspace, not the admin** | You can't add it yourself. Send your admin the [Admin setup](/doc/leadbay-mcp/admin-setup.md) guide; once they've added it, skip to **Step 2 — Sign in**. |
| **Can't add connectors / no admin to ask** | On **Claude Desktop**, install the [`.dxt` extension](/doc/leadbay-mcp/installation.md#fallback-install-the-extension) instead — a per-user install with no admin gate. |
***
## Step 1 — Add the Leadbay connector
[**Add the Leadbay connector →**](https://claude.ai/customize/connectors?modal=add-custom-connector\&connectorName=Leadbay\&connectorUrl=https%3A%2F%2Fmcp.leadbay.app%2Fmcp), then click **Add**. There are two server URLs — this link uses the US one, `https://mcp.leadbay.app/mcp`. If you're in France, use `https://mcp.leadbay.app/fr/mcp` instead.
{% hint style="info" %}
Prefer step-by-step screenshots, or on a different assistant (Claude Desktop, Claude Code, ChatGPT, Codex)? See the full [Installation](/doc/leadbay-mcp/installation.md) walkthrough.
{% endhint %}
***
## Step 2 — Sign in
1. Open the new **Leadbay** connector and click **Connect**.
2. A **Sign in with Leadbay** page opens in your browser — log in (or confirm your existing session) and click **Approve**.
3. The tab closes itself and Claude is connected.
That's the whole connection — no tokens, no config files. Claude is now linked to **your** Leadbay account, with all the leads you already have. You can revoke access anytime from **Settings → Connected apps**.
***
## Step 3 — Ask for your first leads
Open a new conversation and type:
> *Show me today's leads and tell me which two are worth opening first.*
Claude calls your Leadbay tools and replies with a short, ranked shortlist — company, why it fits, and the best contact to reach.
{% hint style="info" %}
First message gets *"I don't see any Leadbay tools"*? The tools are still loading. Send any second message (even just *"try again"*) and Claude will pick them up.
{% endhint %}
***
## Step 4 — What you should see
A successful first response looks like a **ranked table of leads**, not a wall of text. For each lead you'll get:
* a **score** (how well it matches your audience),
* a one-line **why it fits**,
* the **best contact** with a link where available.
If Claude replies with leads like that, you're fully connected. 🎉
A successful first reply: a ranked table of prospects, then the two worth opening first.
***
## Step 5 — Keep going
Once you've seen your first leads, try these:
> *Research the top one for me — is it a fit?*
> *Draft me an outreach email to them.*
> *I just emailed them. Log it as outreach.*
Claude remembers the leads it surfaced, so you can keep referring to "the top one" without repeating yourself.
***
## Using another assistant?
{% content-ref url="/pages/gVHUYrjZtE3ZkIfxLRuz" %}
[Installation](/doc/leadbay-mcp/installation.md)
{% endcontent-ref %}
Step-by-step setup for **Claude.ai**, **Claude Desktop**, **Claude Code**, **ChatGPT**, and **Codex**. US accounts use `https://mcp.leadbay.app/mcp`; France / EU use `https://mcp.leadbay.app/fr/mcp`.
***
## Where to next
{% content-ref url="/pages/alp1pPMtNOaF49Nro0F4" %}
[Example prompts](/doc/leadbay-mcp/example-prompts.md)
{% endcontent-ref %}
{% content-ref url="/pages/KYxczcA4BfuwR6LTxaMQ" %}
[Tools reference](/doc/leadbay-mcp/tools-reference.md)
{% endcontent-ref %}
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:
```
GET https://docs.leadbay.app/doc/leadbay-mcp/quickstart.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.