Live data for AI agents — search, research, markets, crypto, X/Twitter. Pay-per-call via x402 micropayments.
> /plugin marketplace add BlockRunAI/blockrun-mcp
Repo: BlockRunAI/blockrun-mcp
What's inside
claude mcp add blockrun -s user -- npx -y @blockrun/mcp@latest
BlockRun MCP is an open-source Model Context Protocol server that gives Claude — and any MCP-compatible agent — 19 tools for real-time data and real actions: 78 LLMs, image & video generation, prediction-market data, live web/X search, on-chain queries across 40 chains, and the ability to place real, USDC-settled bets on Polymarket.
You pay per call, and you choose how. Wallet mode authenticates with a signature and settles each call in USDC via the x402 protocol — no account, no credit card, no subscription, on Solana or Base. Account mode authenticates with a BlockRun API key (brk_live_…) from user.blockrun.ai, routes service calls through api.blockrun.ai, and draws down card- or wire-funded account credit at exact usage. Same 19 tools either way. MIT licensed.
Read live Polymarket odds and place the bet, from one self-custody wallet, pay-per-call. Jump to Polymarket trading →
Every other data integration was built for human developers — create an account, copy an API key into .env, add a credit card, repeat for every vendor.
BlockRun gives you both payment rails without rebuilding the integration. Use a wallet when the agent should self-custody funds, or use an account key when a team wants card-funded credits and a dashboard.
blockrun_chat mode:"free", blockrun_dex, crypto blockrun_price, blockrun_models) costs $0.blockrun_polymarket places real, confirm-gated trades.BLOCKRUN_CONFIRM_SPEND=on and the agent pauses before any paid call above your threshold; nothing is signed until you approve. Details ↓~/.blockrun/.session, 0600 — or the OS keychain once you opt into BLOCKRUN_KEYCHAIN=strict). BlockRun can't move your funds.| Raw provider APIs | Typical single-vendor MCP | BlockRun MCP | |
|---|---|---|---|
| Setup | Account + API key per vendor | Account/key for 1 vendor | Wallet auto-created — or one BlockRun key for everything |
| Payment | Credit card, monthly minimums | Credit card / vendor plan | USDC per-call via x402, or card/wire-funded account credit |
| Data sources | One per integration | One vendor | 19 tools — LLMs, media, markets, chain |
| Place real bets | Build it yourself | Rare | Yes — Polymarket CLOB, confirm-gated |
| Pay-chain | — | — | Solana + Base, or api.blockrun.ai with no chain at all |
| Agent budgets | Manual | — | Built-in per-agent delegation |
| Spend approval | — | — | Ask-before-pay dialog (MCP elicitation) |
| Generative UI | — | Rare | Order card + wallet panel (MCP Apps) |
| Open source | Varies | Varies | Yes (MIT) |
✓ One wallet or one account key · ✓ Pay-per-call · ✓ Reads and trades · ✓ Multi-chain · ✓ Agent-ready · ✓ Open source
Before BlockRun, Claude can't answer:
After BlockRun, it can. Each query costs fractions of a cent — billed from a local USDC wallet, or from card-funded credit on a BlockRun account through api.blockrun.ai. No subscriptions, no per-vendor signups.
| Wallet (default) | API key | |
|---|---|---|
| Setup | Nothing — a wallet is created on first run | Sign in at user.blockrun.ai, mint a key, use it against api.blockrun.ai |
| Funding | Send USDC (Solana or Base) | Credit card / wire → account credit |
| Billing | Per call, settled on-chain, + $0.001 network fee | Exact-usage account credit, no per-call network fee, no minimum |
| Identity | A keypair on your machine | An account with members, credits, and a usage ledger |
| Best for | Agents, solo devs, anything self-custody | Teams, companies, anyone who can't run a wallet |
| Trade on Polymarket | ✅ | ❌ — needs a keypair to sign |
Both modes reach the same 19 tools. Account mode sends service calls to https://api.blockrun.ai by default. You can switch at any time; setting BLOCKRUN_API_KEY takes priority over a wallet, and unsetting it hands the wallet back.
Claude Code (recommended)
claude mcp add blockrun -s user -- npx -y @blockrun/mcp@latest
-s user installs globally (available in every project). The -- separator ensures -y is passed to npx, not parsed by claude mcp add.
💡 Homebrew / nvm users: if the server doesn't connect, Claude Code likely can't find
node/npxon its launcher PATH. Pass your shell PATH through — works on CLI and desktop:claude mcp add blockrun -s user -e PATH="$PATH" -- npx -y @blockrun/mcp@latestSee Troubleshooting if it persists.
Every MCP client — one command or one JSON block. Verified = we ran the published package on that client and saw the tools listed (client version · date). Documented = install path from the client's own docs; not run by us yet — tell us if it works. The Spend dialog column is whether the client renders the human-in-the-loop payment prompt; on ❌ clients paid calls proceed without asking and BLOCKRUN_BUDGET_LIMIT is the guard.
| Client | Status | Spend dialog | Install |
|---|
FAQ
blockrun-mcp is a Claude Code plugin with 16 hand-picked skills for data work, indexed on Flowy. Install it with the command on its page. It includes blockrun-debug, blockrun-setup, blockrun-upgrade. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.
Is this plugin yours?
Claim it with GitHubSubmit a pluginPromote it