MCP and API. Included on every plan.Your Agent Asks. SDR Pilot Decides What Goes Out.
SDR Pilot (sdrpilot.ai) is an AI SDR from $97 a month that runs on your own LinkedIn account and can be driven by your own AI agent. Ask Claude Code, Claude Desktop, Cursor or n8n for twenty founders in Berlin, and SDR Pilot researches, scores and sends at its own pace. MCP and API are on every plan.
- Included on every plan
- The pacer keeps the caps
- Nothing to install on LinkedIn
connect with 20 SaaS founders in Berlin who posted about churn this week
Searching, reading each profile, scoring against your ICP. 14 of the 20 passed.
The agent asks. SDR Pilot's pacer decides what actually goes out, and when.
Most people will use SDR Pilot in the app, and nothing about that changes. This page is about the other way in: pointing your own agent at it, so the thing that plans your outbound and the thing that executes it are not the same tool and do not have to be.
MCP and the API are included on every plan, from Pro up. Create an API key in the app under Settings, then API, and point your MCP client at https://mcp.sdrpilot.ai/mcp. Setup steps are at help.sdrpilot.ai/api/api-and-mcp/.
Why drive an SDR from an agent at all
Because the interesting half of outbound is the thinking, and that is where your agent already lives. You have a research step in Claude Code, a scoring prompt you keep tuning, a list in Clay, a workflow in n8n. What you do not have is a safe pair of hands on LinkedIn to act on the result, and building one is a months-long project that ends with somebody's account restricted.
Your agent decides
- Who to go after, and why.
- The research step you keep in Claude Code.
- The scoring prompt you keep tuning.
- The list in Clay, the workflow in n8n.
SDR Pilot decides
- Whether the request goes out at all.
- When it goes out, inside your active hours.
- How fast, at the caps it uses when nobody is driving.
- On the same session and the same dedicated residential IP.
What an agent can ask it to do
The surface mirrors what the app already does, because an agent should not be able to ask for anything a person cannot do in the product.
Search on your ICP
The same people search the app runs, inside the same monthly search budget.
Add and research leads
The profile is opened, read and scored against your ICP before anything else happens.
Queue a connection request
The ones that pass go into the day's queue rather than straight out the door.
Read the inbox
Conversations, who replied, what was said, what the agent said back.
Reply or hand over
Reply in a thread, hand a thread back to the human, or stand down on it.
Post and pull engagers in
Post to your feed, and pull the people who engaged with a post in as leads.
That is the shape of the surface. The full, current tool list and the endpoint reference live in the help docs at help.sdrpilot.ai/api/api-and-mcp/, and they are the source of truth when the two differ.
What stays with SDR Pilot, whoever is driving
This is the part that matters, and it is the reason to drive an SDR rather than a raw LinkedIn API. An external agent proposes. SDR Pilot's pacer disposes. None of the following is exposed as something an agent can raise, and none of it changes because a request arrived from a machine instead of a person.
The daily caps. 20 connection requests a day per sender with a ceiling of 25, 100 messages with a ceiling of 250, 250 profile reads, 30 searches.
The warm-up. A new sender starts at 5 requests a day and reaches 20 on day 16, whatever anything asks for on day two.
One LinkedIn action at a time per sender, queued and paced, never a burst.
One browser identity per sender, captured from the real login, on one dedicated residential IP in the account's own country.
Your active hours, on your own calendar day. Ask at three in the morning and it goes out when your window opens.
The ICP score. A request to connect with somebody who fails your own bar is refused, not sent.
An agent that asks for two hundred connection requests gets twenty today, twenty tomorrow, and an honest answer about the rest.
That is not a limitation of the integration, it is the integration's entire point.
Which clients it is built for
Claude Code
For people who already run their GTM work from a terminal.
Claude Desktop
For the same work without one.
Cursor
For teams whose agent context lives next to their code.
n8n
For workflows that already move data between a CRM, an enrichment step and a spreadsheet.
Anything else that speaks MCP should work, and the API is there for whatever does not. Both are included on every plan.
How to connect it today
Three steps, all inside the app you already use.
Start the 14-day free trial, connect LinkedIn, then create an API key under Settings, then API. Point your MCP client at https://mcp.sdrpilot.ai/mcp with that key, or call the API directly. The key is scoped to your workspace, and you can revoke it and create a new one in the same place.
On Claude Code the quickest way is the SDR Pilot plugin, live now. It sets up the connection with your key, adds a skill Claude reads first (how SDR Pilot is put together, the common workflows, and what it must ask you before it acts), and gives Claude the help docs as they are today. Setup and the prompts to start with are at sdrpilot.ai/claude-linkedin-sdr/.
Why not just give you the LinkedIn tools
Because a raw LinkedIn API hands your agent the account and the risk at the same time. Tools call what they are told to call, as fast as they are told, and the judgement about what is safe ends up inside a prompt that nobody tuned for it. Every restriction story in this category starts there.
SDR Pilot is the opposite trade. You give up the ability to fire two hundred requests in an afternoon, which you should not want, and you get an executor whose defaults were set by watching one real account for months. The caps hold whoever is driving.
FAQQuestions people ask
Can my own AI agent drive SDR Pilot?
Yes. That is what MCP and the API are for, and both are included on every plan. Your agent asks for the work, SDR Pilot researches, scores and sends it at its own pace on your own LinkedIn session. Create an API key in the app under Settings, then API, and point your MCP client at https://mcp.sdrpilot.ai/mcp. Setup steps are at help.sdrpilot.ai/api/api-and-mcp/.
Which MCP clients does SDR Pilot support?
It is built for Claude Code, Claude Desktop, Cursor and n8n, and anything else that speaks MCP should work. There is an API for what does not. The endpoint is https://mcp.sdrpilot.ai/mcp. On Claude Code there is also a plugin that sets up the connection and adds a skill with the SDR Pilot playbook; setup is at sdrpilot.ai/claude-linkedin-sdr/.
Is there an SDR Pilot API?
Yes, on every plan, alongside the MCP server. Create an API key in the app under Settings, then API. The reference is at help.sdrpilot.ai/api/api-and-mcp/.
Who controls the sending limits when an agent drives it?
SDR Pilot does, always. The caps, the warm-up, one action at a time, the active hours and the ICP score are not exposed as things an agent can raise. An agent that asks for two hundred connection requests gets twenty today and twenty tomorrow.
Can an agent bypass the ICP score?
No. A request to contact somebody who fails your own bar is refused rather than sent. The score is part of the executor, not part of what the caller passes in.
How is this different from a LinkedIn API for agents?
A LinkedIn API sells your agent the tools and leaves you to build the SDR, including the pacing and the judgement about what is safe. SDR Pilot is the SDR: the research, the scoring, the playbook, the conversation and the pacer already exist, and your agent drives them.
Start Your Free Trial. Live on LinkedIn Today.
Every plan starts with a 14-day free trial. Create an account, add a card at checkout and connect LinkedIn; nothing is charged before day 15, and you can cancel in the billing portal any time. Plans start at $97 a month for one LinkedIn sender.