pumpgtm-mcp

<p align="center"><a href="https://pumpgtm.com"><img src="assets/banner.png" alt="PumpGTM" width="100%"></a></p>

<h1 align="center">PumpGTM MCP server</h1>

<p align="center"><b>Run LinkedIn, email and X outreach from any AI agent.</b><br>
PumpGTM finds the buyers showing intent this week, drafts and sends the outreach from your own accounts inside each platform's limits, and hands every reply back to a human. This is the public reference for the hosted MCP server at <code>https://mcp.pumpgtm.com/mcp</code>.</p>

<p align="center">
<a href="https://pumpgtm.com/docs/mcp"><img alt="Docs" src="https://img.shields.io/badge/docs-pumpgtm.com%2Fdocs%2Fmcp-2f5cff"></a>
<a href="https://modelcontextprotocol.io"><img alt="MCP" src="https://img.shields.io/badge/MCP-Streamable%20HTTP%20%2B%20OAuth%202.1-000000"></a>
<a href="tools.json"><img alt="Tools" src="https://img.shields.io/badge/tools-27-1f883d"></a>
<a href="https://github.com/pumpgtm/pumpgtm-api"><img alt="REST API" src="https://img.shields.io/badge/REST%20API-OpenAPI%203.1-6f42c1"></a>
<a href="https://pumpgtm.com/yc"><img alt="Backed by Y Combinator" src="https://img.shields.io/badge/Backed%20by-Y%20Combinator-F26522"></a>
<a href="https://pumpgtm.com/blog/ai-founder-led-outbound-system"><img alt="Runs outbound for 10+ YC companies" src="https://img.shields.io/badge/runs%20outbound%20for-10%2B%20YC%20companies-F26522"></a>
<a href="LICENSE"><img alt="License" src="https://img.shields.io/badge/license-MIT-lightgrey"></a>
</p>

<p align="center">
<a href="https://pumpgtm.com/docs/quickstart">Quickstart</a> · <a href="https://pumpgtm.com/docs/mcp">Docs</a> · <a href="tools.json">tools.json</a> · <a href="https://github.com/pumpgtm/pumpgtm-api">REST API</a> · <a href="https://pumpgtm.com/mcp/platforms">Platforms and agencies</a> · <a href="https://www.youtube.com/@pumpgtm">YouTube</a>
</p>

## What your agent is driving

The same workspace the dashboard shows. Plays find people, sequences reach them across LinkedIn, email and X, and every reply waits for a human.

<p align="center"><img src="assets/plays.png" alt="PumpGTM Plays: describe who you want, start from a list, or reach everyone who engaged with a post" width="100%"></p>
<p align="center"><img src="assets/sequences.png" alt="A running PumpGTM sequence with its funnel and message variants" width="100%"></p>

## How it fits together

```mermaid
flowchart LR
  A[Your AI agent<br/>Claude, Cursor, Codex, your own] -- MCP over Streamable HTTP --> M[mcp.pumpgtm.com]
  M --> W[Your PumpGTM workspace]
  W -- find_people --> P[Buyers showing intent]
  W -- sequences --> L[LinkedIn]
  W -- sequences --> E[Email]
  W -- sequences --> X[X]
  L & E & X -- replies --> R[Human decides]
  R -- webhook reply.received --> A
```

## Watch and read

<table>
<tr>
<td width="50%" align="center"><a href="https://pumpgtm.com/blog/what-is-pumpgtm-how-it-works"><img src="https://img.youtube.com/vi/wEb9ZDUIsc0/hqdefault.jpg" alt="What is PumpGTM and how does it work" width="100%"></a><br><sub><b>What is PumpGTM, and how does it actually work?</b><br>4 minute walkthrough</sub></td>
<td width="50%" align="center"><a href="https://x.com/NamanyayG/article/2097783972302557668"><img src="https://pumpgtm.com/blog/covers/ai-founder-led-outbound-system.png" alt="Using AI to run founder-led outbound for 10 YC companies" width="100%"></a><br><sub><b>Using AI to run founder-led outbound for 10 YC companies</b><br>Namanyay's article on X: one lead universe, shared prospects, copy measured by meetings. <a href="https://pumpgtm.com/blog/ai-founder-led-outbound-system">Read on pumpgtm.com</a></sub></td>
</tr>
</table>

More on the [PumpGTM YouTube channel](https://www.youtube.com/@pumpgtm) and in [PumpGTM in the wild](https://pumpgtm.com/customers/videos), videos founders and creators made on their own channels.

## Connect

Endpoint (Streamable HTTP): `https://mcp.pumpgtm.com/mcp`

Two ways to authenticate, both scoped to one workspace:

- **OAuth 2.1** for Claude (web and desktop), Claude Code, Codex, Cursor and ChatGPT. Add the endpoint and sign in; no key is needed. Dynamic client registration and PKCE are supported; metadata is at `https://pumpgtm.com/.well-known/oauth-authorization-server`. Access tokens last 30 days, refresh tokens 90.
- **Workspace key** for your own agent, the MCP SDKs, and the REST API. Sign in at [app.pumpgtm.com](https://app.pumpgtm.com), open **MCP** in the left nav, and copy the key. Send it as `Authorization: Bearer eve_mcp_..` on every request. The key does not expire. Rotation is not self-serve yet: write to hello@pumpgtm.com and we rotate it for you.

The key's database row fixes the workspace. It cannot read or act on any other workspace.

```ts
import { Client } from "@modelcontextprotocol/sdk/client/index.js";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp.js";

const client = new Client({ name: "your-agent", version: "1.0.0" });
await client.connect(
  new StreamableHTTPClientTransport(new URL("https://mcp.pumpgtm.com/mcp"), {
    requestInit: { headers: { Authorization: "Bearer YOUR_WORKSPACE_KEY" } },
  }),
);
const { tools } = await client.listTools(); // up to 26 tools, listed below
```

ChatGPT (until the PumpGTM listing is approved in the ChatGPT directory): in Settings, open **Plugins** and turn on **Developer mode** (Plus, Pro, Business or Enterprise). Click **Plugins** in the sidebar, then **+**: choose **Add MCP Server** in the desktop app, or **Create app** then **Create MCP App** in the browser. Name it PumpGTM, paste `https://mcp.pumpgtm.com/mcp`, keep OAuth, and click **Create**. Sign in to PumpGTM, allow the connection, then ask ChatGPT to find buyers or type @PumpGTM.

Claude Code: `claude mcp add --transport http pumpgtm https://mcp.pumpgtm.com/mcp`, then run `/mcp` (or `claude mcp login pumpgtm`) and sign in. Codex: `codex mcp add pumpgtm --url https://mcp.pumpgtm.com/mcp` then `codex mcp login pumpgtm`. Cursor: add a server with only the URL and sign in when it asks.

## Install as a plugin

The PumpGTM plugin bundles this server with three skills: write a cold message, find buyers, and handle replies. In Claude Code:

```
/plugin marketplace add pumpgtm/pumpgtm-mcp
/plugin install pumpgtm@pumpgtm
```

Then run `/mcp` and sign in to PumpGTM. The plugin's manifest, skills and server config live in [github.com/pumpgtm/pumpgtm-mcp](https://github.com/pumpgtm/pumpgtm-mcp).

In Codex:

```
codex plugin marketplace add pumpgtm/pumpgtm-mcp
codex plugin add pumpgtm@pumpgtm
codex mcp login pumpgtm
```

## How results come back

- Every tool result is one MCP `content` block of type `text` whose `text` is a JSON string, and the same object in `structuredContent`. Parse the JSON.
- Most results include `next`: `{ tool, arguments, reason, requiresConfirmation, requiresNewRequestId? }`. It is the suggested following call, not an instruction to skip the customer.
- Errors return `isError: true` and `{ status, retryable, changed, message, details }`. `changed: false` means nothing was written. A missing object returns code `resource_not_found`.
- Tools that write take a `requestId`: 8 to 120 characters of letters, digits, `. _ : -`, starting with a letter or digit. It is an idempotency key. Use a fresh one per call; reuse one only to retry the same call.
- Metered workspaces carry Energy: one Energy is one person found. `get_workspace` returns `energy` with the monthly allowance, used and remaining, and `find_people` refuses with `energy_exhausted` when a run would exceed it. Workspaces without Energy see no such field. See [Energy](https://pumpgtm.com/docs/api#energy).
- Nothing reaches LinkedIn, email or X until a person approves it. `find_people`, `review_people`, `save_sequence_draft` and `add_leads` never send. Sending starts with `set_sequence_status` `active` on an approved sequence, and each reply is answered only through `decide_reply`.

## A complete flow

1. `get_workspace` to read setup state, sequences, unfinished reviews and pending replies.
2. `find_people` with `targeting` and `confirmed: false` to save a Play and show the targeting summary. Then `find_people` with `playId` and `confirmed: true` to run it.
3. `review_people` with `decisions` and `finish: true` to queue the good fits into a sequence.
4. `save_sequence_draft` with steps, then `set_sequence_status` `approved` with `expectedRevision`, then `active`.
5. `list_pending_replies`, show the draft to the customer, `decide_reply`.

Reporting: `get_workspace` (`view: "summary"` for the funnel and account pacing, `view: "activity"` for the ledger) and `list_leads` with `stage` or `sinceDays`. The same numbers are available over REST at [/docs/api](https://pumpgtm.com/docs/api).

## Resources and prompts

`resources/list` returns six lead-search guides: `gigacatalyst://lead-search/catalog`, `quickstart`, `fields`, `query-builder`, `patterns` and `results`. Read `fields` before writing `targeting` by hand. One prompt, `gigacatalyst_find_people`, takes `requestedCount` ("10" to "100").

## Versioning

Tools scheduled for removal say so in their description for at least 90 days before leaving `tools/list`. There is no fixed rate limit on the MCP server today; discovery is paced by each workspace's daily provider budget.

<details>
<summary><b>Tool reference: all 24 tools, arguments and modes</b> (generated from the live <code>tools/list</code>)</summary>

## Tool reference

Generated from the live `tools/list` on 2026-09-23. "Read only" tools never write. Feature-gated groups return a structured error on workspaces without that feature.

### Start here

#### get_workspace (read only)

Start here. Summary: setup state (LinkedIn, billing, finish-setup link), LinkedIn progress, Plays, eligible sequences, unfinished review, pending replies count, and (when the workspace has the email channel) its mailboxes and email campaigns. view=activity reads the append-only LinkedIn activity ledger with filt