Blockrun Mcp

BlockRun MCP

[](https://www.npmjs.com/package/@blockrun/mcp) [](LICENSE) [](https://modelcontextprotocol.io)

Real-time data for Claude — markets, research, X/Twitter, crypto. No API keys. Pay per call.

claude mcp add blockrun -s user -- npx -y @blockrun/mcp@latest

Wallet auto-created. Fund with $5 USDC. Ask Claude anything.

---

Documentation

Full docs: https://blockrun.ai/docs

• MCP tools & setup: https://blockrun.ai/docs/mcp/blockrun-mcp
• All BlockRun SDKs & APIs: https://blockrun.ai/docs

---

What changes

Before BlockRun, Claude can't answer:

• "What's the current Polymarket probability that Bitcoin hits $100k this year?"
• "Find me the top 5 papers on RAG published in the last 30 days"
• "What are people saying about @sama on X right now?"
• "What's the 24h volume on the PEPE/ETH pair on Uniswap?"

After BlockRun, it can. Each query costs fractions of a cent, billed from a local USDC wallet. No subscriptions. No API dashboards. No key rotation.

---

Demo

> User: What's Polymarket saying about the Fed rate decision next month?

> Claude: According to Polymarket, the market currently puts a 73% probability on the Fed holding rates steady at the May meeting, with 24% on a 25bp cut and 3% on a hike. Volume over the last 24h: $2.1M. The "Hold" contract last traded at $0.73. > > (via blockrun_markets · cost: $0.001)

---

> User: Find recent papers on speculative decoding and summarize the key approaches

> Claude: I found 8 papers from the last 60 days via neural search. The dominant approaches are: (1) draft model selection — smaller models predicting N tokens ahead for the larger model to verify in parallel... > > (via blockrun_exa · cost: $0.01)

---

Showcase

Posters generated through blockrun_image with openai/gpt-image-2. Each is a single API call routed through BlockRun, paid in USDC on Base.

Latest — GPT-5.5 now live on BlockRun

Gallery

| | | | |:---:|:---:|:---:| | | | | | Cornell Blockchain Conference 2026 — packed booth recap | Cornell Blockchain Conference 2026 — quiet variant | 100 Trillion Tokens — milestone synthwave poster |

Prompts and a worked example for these are in [skills/image-prompting/SKILL.md](skills/image-prompting/SKILL.md).

---

Prerequisites

• Node.js ≥ 20.19 (node -v)
• ~$5 USDC on Base or Solana (the server auto-creates a wallet on first run; see [Fund your wallet](#fund-your-wallet))
• An MCP client: Claude Code, Claude Desktop, Cursor, Windsurf, or ChatGPT Desktop

---

Install

Claude Code (recommended)

claude mcp add blockrun -s user -- npx -y @blockrun/mcp@latest

The -s user flag 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 after install, Claude Code > likely can't find node/npx on its launcher PATH. Install with your shell PATH passed > through — works on CLI and desktop: > ``bash > claude mcp add blockrun -s user -e PATH="$PATH" -- npx -y @blockrun/mcp@latest > `` > See [Troubleshooting](#troubleshooting) if it persists.

Tool profiles — expose a trimmed tool set so the client loads fewer schemas into context. Pass --profile (or set BLOCKRUN_MCP_PROFILE); omit it for the full set.

| Profile | Tools | |---------|-------| | full (default) | everything | | media | wallet models image video realface music speech | | trading | wallet price dex markets surf defi rpc | | research | wallet models chat search exa surf | | chat | wallet models chat |

# e.g. a media-only install
claude mcp add blockrun-media -s user -- npx -y @blockrun/mcp@latest --profile media
# or a trading-only install
claude mcp add blockrun-trading -s user -- npx -y @blockrun/mcp@latest --profile trading

Equivalent via env: BLOCKRUN_MCP_PROFILE=trading. An unknown profile name falls back to full. modal and phone are available in the full profile only.

Claude Desktop — add to claude_desktop_config.json:

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

Cursor — add to ~/.cursor/mcp.json (macOS / Linux) or %APPDATA%\Cursor\mcp.json (Windows):

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

Windsurf — same JSON, in:

• macOS: ~/.codeium/windsurf/mcp_config.json
• Linux: ~/.config/.codeium/windsurf/mcp_config.json
• Windows: %APPDATA%\Codeium\windsurf\mcp_config.json

---

Fund your wallet

Run blockrun_wallet to see your address. The server pays on Base by default. Send USDC on Base:

| Method | Steps | |--------|-------| | Coinbase | Send → USDC → Base network → paste address | | Bridge from Ethereum | bridge.base.org |

$5 covers ~5,000 market queries, ~500 Exa searches, ~250 image generations, or ~10 Seedance 1.5-pro clips (5s @ 720p+audio, ~$0.46 each).

Pay on Solana

Prefer to pay in USDC on Solana? It's two tool calls — no env vars, no file editing, no restart:

blockrun_wallet action:"chain" chain:"solana"   # provisions + activates the Solana wallet
blockrun_wallet action:"setup"                  # shows the Solana address + funding QR

Then send USDC (SPL) on the Solana network — from Coinbase (pick "Solana"), Phantom, Solflare, or Backpack. Switch back anytime with blockrun_wallet action:"chain" chain:"base". The server keeps both wallets; switching just changes which one pays.

Base-only — these fall back to Base regardless of active chain:

• Tools: blockrun_image, blockrun_music, blockrun_speech, blockrun_video, paid blockrun_realface (enroll/portrait), paid stock blockrun_price. In Solana mode they return a "switch to Base" message instead of charging.
• blockrun_chat routing:"smart" (ClawRouter) and native Anthropic (claude-*) passthrough — on Solana, pass model: or mode: explicitly.

> Advanced: chain selection can also be forced before startup via files/env (~/.blockrun/.chain, SOLANA_WALLET_KEY) — see [Environment Variables](#environment-variables). The action:"chain" command above is the recommended path.

---

Tools

| Tool | Data source | Cost | |------|-------------|------| | blockrun_chat | 66+ LLMs (GPT, Claude, Gemini, DeepSeek, Kimi K2.6, GLM, NVIDIA free tier, ...) with mode tier routing | per token | | blockrun_image | Generation: openai/gpt-image-2 ($0.06–0.12) — flagship, reasoning + text; openai/gpt-image-1 ($0.02–0.04); google/nano-banana ($0.05) / nano-banana-pro ($0.10–0.15, 4K); xai/grok-imagine-image ($0.02) / -pro ($0.07); zai/cogview-4 ($0.015). Edit: openai/gpt-image-, google/nano-banana (img2img, inpaint, fusion). | $0.015–0.15 | | blockrun_video | Sora 2 + xAI Grok Imagine Video + ByteDance Seedance 1.5/2.0/2.0-fast (720p + audio defaults); RealFace asset → real-person video | $0.05–0.30/sec | | blockrun_realface | Enroll a real person (phone liveness) or an AI character (Virtual Portrait, no liveness) as a ta_xxxx asset for Seedance 2.0 video | free; $0.01 to enroll | | blockrun_music | MiniMax music generation | per track | | blockrun_speech | ElevenLabs text-to-speech (Flash/Turbo/Multilingual/v3, 8 voice aliases) + cinematic sound effects; free voice listing | $0.05–0.10/1k chars; $0.0525/effect | | blockrun_price | Pyth-backed realtime + OHLC — crypto / FX / commodity (free), 12 stock markets (paid) | free or $0.001/call | | blockrun_markets | Polymarket (markets, candles, trades, orderbooks, leaderboards, smart-wallet PnL/clusters, UMA oracle), Kalshi, Limitless, Opinion, Predict.Fun, dFlow, Binance Futures, cross-platform match + search | $0.001–0.005/query | | blockrun_surf | Surf (asksurf.ai) — 84 endpoints: CEX market data, on-chain SQL (13 chains, 80+ ClickHouse tables), 100M+ labeled wallets, Polymarket + Kalshi side-by-side, social mindshare, news, search, Surf-1.5 chat with citations | $0.001–0.02/call | | blockrun_exa | Neural web search (Exa) — research, competitors, papers, URL content | $0.01/query | | blockrun_search | Grok Live Search — web + X/Twitter + news with citations | $0.025 × maxresults (default 10) | | blockrun_dex | Live DEX prices via DexScreener | free | | blockrun_rpc | Raw JSON-RPC on 40+ chains (Ethereum, Base, Solana, Bitcoin, Sui, NEAR, ...) via Tatum gateway — ethcall, balances, blocks, logs | $0.002/call | | blockrun_defi | DefiLlama — protocol TVL, chain TVL, yield pools (APY), token prices | $0.001–0.005/call | | blockrun_modal | Isolated code execution in a BlockRun-hosted Modal sandbox — disposable container, optional GPU (T4 → H100) | $0.01 create; $0.001/op | | blockrun_phone | Outbound AI voice calls (Bland) + wallet-owned US/CA numbers (Twilio), carrier + fraud lookups | $0.54/call; $5/number | | blockrun_models | Live catalogue of every LLM/image/video/music model + pricing | free | | blockrun_wallet | Balance, spending, agent budgets, setup QR | free |

---

Tips for effective LLMs

> For LLMs and agents invoking BlockRun MCP tools:

• **CRITICAL: When any blockrun_* tool returns a payment / balance / 402 error, call blockrun_wallet first to check status, then action:"setup" to get funding instructions.** Don't retry the failing tool blindly — the wallet is empty.
• CRITICAL: blockrun_surf's 84-endpoint catalog lives in skills/surf/SKILL.md; blockrun_markets' full endpoint list is in its own tool description (with worked examples in skills/prediction-markets/SKILL.md). Browse those before guessing endpoint paths.
• CRITICAL: blockrun_chat routing:"smart" (ClawRouter) only works on Base wallets. On Solana, pass mode: or model: to pick a model directly.
• CRITICAL: blockrun_music and blockrun_video are payment-on-completion async. Failures or client-side timeouts do NOT charge. Don't retry-loop them — they may take 60–180s.
• CRITICAL: Before spawning child agents, allocate per-agent budget: blockrun_wallet action:"delegate" agent_id:"X" agent_limit:1.00. Pass agent_id:"X" to every downstream blockrun_* call — the child is auto-blocked when the budget hits zero.
• Free tier first for drafts: blockrun_chat mode:"free" (NVIDIA), blockrun_dex, blockrun_price (crypto / FX / commodity), and blockrun_models are all $0. Use them to scaffold before paying for premium models.

---

Key Use Cases

What kinds of questions can Claude (or any LLM agent) answer once BlockRun MCP is installed:

1. Price reads / market data

> "What's BTC trading at? Compare with last week's average." → blockrun_price (free) or blockrun_surf path:market/price

1. Prediction-market consensus

> "What's Polymarket's odds for the next Fed rate decision?" → blockrun_markets path:polymarket/events + filter

1. On-chain forensics

> "This wallet (0xabc...) — what's it labeled as? What does it hold? When did it whale up?" → blockrun_surf paths:wallet/labels/batch, wallet/detail, wallet/net-worth

1. Cited research with sources

> "Find the 5 most-cited papers on speculative decoding from the last 90 days. Summarize the dominant approach." → blockrun_exa action:search then contents

1. Image generation with on-image text

> "Generate a poster announcing GPT-5.5 on BlockRun, retro-futuristic, with the headline 'NOW LIVE'." → blockrun_image + the image-prompting skill 5-section framework

1. Give your agent a voice

> "Use blockrun to speak this with the sarah voice." → blockrun_speech action:speak (default), input + voice → hosted MP3 URL. Sound effects via action:sound_effect

1. Voice phone-out

> "Call +1-415-555-... and confirm the appointment on Friday at 3pm." → blockrun_phone path:voice/call, body: { to, task, from } (provision from first via phone/numbers/buy), then poll voice/call/{call_id}

1. Multi-agent research with budget cap

> "Spawn 3 research agents on competing L1 narratives. Cap each at $0.50." → blockrun_wallet delegate × 3 → children call blockrun_chat + blockrun_exa with their agent_id

1. Cross-chain SQL forensics

> "Top 10 tokens by DEX volume on Base in the last 24h." → blockrun_surf path:onchain/sql, body: { sql: "SELECT..." }

---

Why not just use the APIs directly?

| | Direct APIs | BlockRun | |---|---|---| | Exa | Sign up, $20/mo minimum | $0.01/call, no subscription | | Polymarket | Undocumented, rate-limited | $0.001/call, clean JSON | | Surf (asksurf.ai) | Account + monthly plan | $0.001/call, no Surf account, 84 endpoints | | Multiple sources | 3 accounts, 3 API keys, 3 billing pages | 1 wallet |

One wallet. All sources. No dashboards.

---

When NOT to use BlockRun MCP

BlockRun shines when you want unified billing + many sources + LLM-readable errors. It is not the right fit for:

• High-volume single-API workloads (≥10k calls/day to one source). Direct subscriptions amortize better past the break-even point — Polymarket's free public API plus your own caching beats $0.001 × 10k/day if you don't need cross-source aggregation.
• Compliance-sensitive flows that need a fiat invoice / audit trail. BlockRun settles in USDC; receipts are on-chain (Basescan / Solscan) but are not tax invoices. For enterprise procurement, contract directly with the upstream provider.
• Latency-critical sub-100ms reads. Each x402 call adds ~200–500ms of payment-signing + settlement overhead vs. a direct authenticated request. For HFT-style flows, run your own infra.
• You only need one source forever. If you'll only ever call Polymarket, or only ever Exa, save the indirection — sign up upstream and skip the wallet.

Use BlockRun when you want pay-per-call for exploration, aggregation, or agent-driven workloads where you can't predict which source you'll reach for next.

---

Multi-agent budget delegation

Delegate a spending budget to a child agent with agent_id. The child is auto-blocked when the budget runs out — useful for autonomous agents that shouldn't run up unbounded costs.

---

Troubleshooting

• Insufficient balance / HTTP 402 after retry → Run blockrun_wallet action:"setup". Send USDC on Base (or Solana — see [Environment Variables](#environment-variables)).
• Smart routing (ClawRouter) is not available on Solana → Pass model: or mode: explicitly to blockrun_chat, or switch back to Base with echo base > ~/.blockrun/.chain.
• blockrun doesn't connect / "MCP server failed" / spawn npx ENOENT → Almost always a PATH issue: Claude Code can't find node/npx on the PATH its MCP launcher uses. Common with Homebrew (/opt/homebrew/bin) or nvm, where node isn't on that PATH — and it affects the CLI as well as the desktop app (the launcher doesn't always inherit your interactive shell PATH). Fix by passing your shell PATH at install:

``bash claude mcp remove blockrun -s user claude mcp add blockrun -s user -e PATH="$PATH" -- npx -y @blockrun/mcp@latest ` Then restart Claude Code (or /mcp to reconnect — MCP tools load at session start). Or pin absolute paths: claude mcp add blockrun -s user -- /opt/homebrew/bin/npx -y @blockrun/mcp@latest (use which npx` for your path).

• claude mcp list doesn't show blockrun → Check node -v (must be ≥20.19). Clear the npx cache: rm -rf ~/.npm/_npx. Re-run the install command from above (see the PATH fix above if node/npx aren't found).
• fetch failed / timeout when checking wallet balance → Base RPC transient outage. The tool already falls through 3 public RPCs; retry after 30s. Persistent failures usually = local proxy / firewall blocking outbound RPC.
• **`ENOENT:

…

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: BlockRunAI
• Source: BlockRunAI/blockrun-mcp
• License: MIT

Install and usage instructions live in the source repository linked above.