AI Skill Hub 强烈推荐:blockrun-mcp MCP工具 是一款优质的MCP工具。AI 综合评分 8.0 分,在同类工具中表现稳健。如果你正在寻找可靠的MCP工具解决方案,这是一个值得深入了解的选择。
blockrun-mcp MCP工具 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
blockrun-mcp MCP工具 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/BlockRunAI/blockrun-mcp
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"blockrun-mcp-mcp--": {
"command": "npx",
"args": ["-y", "blockrun-mcp"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 blockrun-mcp MCP工具 执行以下任务... Claude: [自动调用 blockrun-mcp MCP工具 MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"blockrun-mcp_mcp__": {
"command": "npx",
"args": ["-y", "blockrun-mcp"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
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 $5 USDC. Ask Claude anything.
---
node -v)---
Claude Code (recommended)
claude mcp add blockrun -s user -- npx -y @blockrun/mcp@latest
The -s user flag installs globally (available in every project). The -- separator ensures -y is passed to npx, not parsed by claude mcp add.
💡 Homebrew / nvm users: if the server doesn't connect after install, Claude Code likely can't findnode/npxon its launcher PATH. Install with your shell PATH passed through — works on CLI and desktop:See Troubleshooting if it persists.> claude mcp add blockrun -s user -e PATH="$PATH" -- npx -y @blockrun/mcp@latest >
Tool profiles — expose a trimmed tool set so the client loads fewer schemas into context. Pass --profile <name> (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 |
```bash
claude mcp add blockrun-media -s user -- npx -y @blockrun/mcp@latest --profile media
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`:json { "mcpServers": { "blockrun": { "command": "npx", "args": ["-y", "@blockrun/mcp"] } } }
**Cursor** — add to `~/.cursor/mcp.json` (macOS / Linux) or `%APPDATA%\Cursor\mcp.json` (Windows):json { "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
---
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
2. Prediction-market consensus > "What's Polymarket's odds for the next Fed rate decision?" → blockrun_markets path:polymarket/events + filter
3. 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
4. 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
5. 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
6. 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
7. 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}
8. 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
9. Cross-chain SQL forensics > "Top 10 tokens by DEX volume on Base in the last 24h." → blockrun_surf path:onchain/sql, body: { sql: "SELECT..." }
---
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)
---
Posters generated through blockrun_image with openai/gpt-image-2. Each is a single API call routed through BlockRun, paid in USDC on Base.
| <img src="assets/posters/cornell-2026-popular-booth.png" width="280" alt="Thank you, Cornell — BlockRun at the Cornell Blockchain Conference 2026, packed booth"> | <img src="assets/posters/cornell-2026.png" width="280" alt="Thank you, Cornell — BlockRun at the Cornell Blockchain Conference 2026"> | <img src="skills/image-prompting/example-100t-poster.jpg" width="280" alt="100 Trillion Tokens served — synthwave milestone poster"> |
| **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.
---
| Variable / File | Default | Effect |
|---|---|---|
~/.blockrun/.session | auto-created on first run | EVM private key (0x...). File exists → use Base. |
~/.blockrun/.chain | unset | Optional explicit chain preference: base or solana. |
~/.blockrun/.solana-session | not created | Solana private key. File exists → switch to Solana unless .chain says base. |
SOLANA_WALLET_KEY | unset | Env-var override of .solana-session. Set → use Solana. |
Chain selection priority (see src/utils/wallet.ts):
~/.blockrun/.chain or ~/.blockrun/payment-chain set to base or solana → explicit preference winsSOLANA_WALLET_KEY env var present → Solana~/.blockrun/.solana-session exists → Solana~/.blockrun/.session auto-created)Switching chains:
The recommended way is the tool itself — it provisions both wallets, applies instantly (no restart), and shows the funding QR:
blockrun_wallet action:"chain" chain:"solana" # or chain:"base"
blockrun_wallet action:"setup" # funding instructions for the active chain
Advanced (force a chain before startup, e.g. in CI): echo solana > ~/.blockrun/.chain then set SOLANA_WALLET_KEY or create ~/.blockrun/.solana-session; echo base > ~/.blockrun/.chain reuses the existing .session (same Base wallet). These edit the same preference file that action:"chain" writes — prefer the tool unless you need pre-startup control.
Some media and paid market-data tools still settle on Base only: blockrun_image, blockrun_music, blockrun_speech, blockrun_video, and paid stock blockrun_price calls — plus blockrun_chat routing:"smart" and native Anthropic (claude-*) passthrough. In Solana mode these return a "switch to Base" message instead of charging.
The server also runs a non-blocking npm registry check at startup and prints an Update available notice to stderr when a newer @blockrun/mcp version exists. Upgrade by re-running the install command — no manual npm update needed.
---
| 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 | $0.001/call, no Surf account, 84 endpoints |
| Multiple sources | 3 accounts, 3 API keys, 3 billing pages | 1 wallet |
One wallet. All sources. No dashboards.
---
- Insufficient balance / HTTP 402 after retry → Run blockrun_wallet action:"setup". Send USDC on Base (or Solana — see Environment Variables). - Smart routing (ClawRouter) is not available on Solana → Pass model: or mode: explicitly to blockrun_chat, or switch back to Base with echo base > ~/.blockrun/.chain. - blockrun doesn't connect / "MCP server failed" / spawn npx ENOENT → Almost always a PATH issue: Claude Code can't find node/npx on the PATH its MCP launcher uses. Common with Homebrew (/opt/homebrew/bin) or nvm, where node isn't on that PATH — and it affects the CLI as well as the desktop app (the launcher doesn't always inherit your interactive shell PATH). Fix by passing your shell PATH at install:
claude mcp remove blockrun -s user
claude mcp add blockrun -s user -e PATH="$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: ~/.blockrun/.session → Expected on first run. The server auto-creates the wallet; check stderr for the WALLET_CREATED line confirming the address. - Video generation timed out (5-min cap) → Upstream Seedance / xAI queue congestion. No charge (payment-on-completion). Retry, or pick a faster model (bytedance/seedance-1.5-pro). - Music generation timed out (200s cap) → Same pattern. No charge. Retry; if it persists, the upstream model is rate-limited — try off-peak.
---
BlockRun MCP 是一个实时数据服务,提供市场、研究、X/Twitter、加密货币等信息。无需 API 密钥,按调用付费。
环境依赖与系统要求:Node.js ≥ 18、~$5 USDC(在 Base 或 Solana 上)、一个 MCP 客户端(Claude Code、Claude Desktop、Cursor、Windsurf 或 ChatGPT Desktop)
安装:使用 Claude Code(推荐)或 Claude Desktop,添加到 claude_desktop_config.json 文件中
使用教程:BlockRun MCP 可以回答 Claude(或任何 LLM 代理)的问题,例如价格读取、市场数据、预测市场共识等
环境变量:~/.blockrun/.session(自动创建,EVM 私钥)、~/.blockrun/.chain(选填,Base 或 Solana)、~/.blockrun/.solana-session(Solana 私钥)
为什么不直接使用 API?BlockRun、Exa、Polymarket、Surf 等 API 有不同的费用和限制
常见问题:不足余额或 HTTP 402 后重试、智能路由(ClawRouter)不可用于 Solana 等
高质量MCP实现,集成多维实时数据源,为AI智能体赋能强大信息获取能力。TypeScript开发维护良好,465星关注度适中,商业付费模式可持续发展。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
总体来看,blockrun-mcp MCP工具 是一款质量优秀的MCP工具,在同类工具中具备一定竞争力。AI Skill Hub 将持续追踪其更新动态,建议收藏备用,结合自身场景选择合适时机引入使用。
| 原始名称 | blockrun-mcp |
| 原始描述 | 开源MCP工具:Live data for AI agents — search, research, markets, crypto, X/Twitter. Pay-per-。⭐465 · TypeScript |
| Topics | MCP服务器实时数据AI智能体加密货币社交媒体市场数据 |
| GitHub | https://github.com/BlockRunAI/blockrun-mcp |
| License | MIT |
| 语言 | TypeScript |
收录时间:2026-05-14 · 更新时间:2026-05-16 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端