BlockRun
Get started
Integrations / Cline

Give Cline every model, media and data tool through the BlockRun MCP server

Add BlockRun to Cline's MCP settings and the VS Code agent can call any frontier model, generate media and pull live data — no provider keys, pay per call.

Get your agent on BlockRun 

How it works

Cline manages MCP servers from its own settings file, and the BlockRun entry is the same one every MCP host uses: one npx command, no key. Once loaded, Cline can reach every chat model on the catalog as a tool, alongside image and video generation, web and neural search, market and prediction-market data and chain RPC.

This suits Cline's autonomous mode: the agent pays for each call from a wallet created on first run, so a long task that switches models or generates media never stops to ask a person for a key. A card top-up or USDC transfer funds the wallet; the private key never leaves the machine.

Behind it is the BlockRun catalog: 78 chat models plus image, video, music and speech generation, search, market data and multi-chain RPC, priced per call. 6 open-weight models are free and need no wallet.

Setup

1. cline_mcp_settings.json (Cline → MCP Servers → Configure)

{
  "mcpServers": {
    "blockrun": { "command": "npx", "args": ["-y", "@blockrun/mcp@latest"] }
  }
}

Questions

How do I add BlockRun to Cline?
Open Cline's MCP Servers panel, choose Configure, and add the mcpServers entry above. Cline starts the server and lists its tools; the wallet is created on the first paid call.
Can Cline use BlockRun as its main model provider?
Cline's own provider slots take an OpenAI-compatible base URL, so a local blockrun-litellm sidecar works there too; the MCP route is the one that also gives it media and data tools.
Which models does Cline get through BlockRun?
Every model on the catalog, by id — a frontier model for the hard step and a cheap one for the rest, in one task.
Does Cline's autonomous mode keep working with a paid tool?
Yes. Each call pays for itself from the wallet, so there is no approval prompt for a key or a balance during a run.
BlockRun MCP in Cline vs Continue or Cursor?
Identical server, identical JSON; the difference is where each editor keeps its MCP config. Cline and Continue also accept an OpenAI-compatible base URL for their main model.
What does a call cost through this integration?
The provider's published token rate with no markup on tokens, plus a flat per-call fee, quoted in dollars in the 402 before the call runs. Image, video and speech calls are priced per unit the same way. The live rate card is on the models page.
Do I need an API key or an account?
No. On the pay-per-call door the request carries its own payment from a wallet the SDK or MCP server creates on first run; there is nothing to sign up for. Teams that prefer keys get an API key and a monthly invoice instead.

Related

Two ways to run this

Get an API key

Sign in, get a key, and call the same endpoints with usage billed to your account. For teams that want one invoice instead of one wallet.

Get an API key 

Or let your agent pay per call, in USDC

No account, no API key. Three steps, and the last one is the request this page is about.

  1. 01
    Point your agent at BlockRun

    Install ClawRouter, or add the BlockRun MCP server to Claude Code, Cursor, Codex or OpenClaw. Any OpenAI-compatible client works too — change the base URL, nothing else.

    curl -fsSL https://blockrun.ai/ClawRouter-update | bash
  2. 02
    Fund a wallet with USDC

    Send USDC to a wallet on Base or Solana. There is no account to create and no API key to issue: the wallet is the account, and it pays per call.

  3. 03
    Use BlockRun from Cline

    The first call returns HTTP 402 with the exact price, your agent signs it, and the answer comes back. Payment settles on-chain; nothing is charged if the call fails.

    {
  "mcpServers": {
    "blockrun": { "command": "npx", "args": ["-y", "@blockrun/mcp@latest"] }
  }
}
ClawRouter setup →How paying per call works →

Explore everything on BlockRun