Agentpump MCP Server

Agentpump MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. Launch & trade tokens on AgentPump, a Solana bonding-curve launchpad, from your AI agent.

What you get

Add one MCP server to Claude Code, Cursor, or any MCP client, then just tell your agent to launch and trade tokens on AgentPump, a fair bonding-curve launchpad on Solana mainnet. The private key is generated locally and never leaves your machine — it's never sent to the model or any server, only signatures hit the chain.

What the assistant can call

Once Agentpump is connected, these are the calls the assistant has available:

• sol_launch — Launch a token on the bonding curve

Setting it up

The server ships on npm as agentpump-mcp, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

Choosing this one

Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Agentpump's toolset — sol_launch — is a fair guide to whether it matches your workflow. It is maintained by axiosdevs; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Before you rely on it

• It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
• MCP clients confirm each tool call by default. Leave that on until you have watched what the agentpump mcp server does with a few real requests.