blockrun-debug
Use when the BlockRun MCP server (@blockrun/mcp) is installed but misbehaving — 'Failed to connect', spawn npx ENOENT, blockrun missing from claude mcp list,…
GenTech Labs' integration patterns for BlockRun MCP from Hermes Agent. Covers daily usage patterns, cost-optimized workflows, multi-tool pipelines, and reliable error handling for BlockRun's full toolset.
$ npx -y skills add BlockRunAI/blockrun-mcp --skill gentech-blockrun --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/gentech-blockrunContext preview
The summary Claude sees to decide when to auto-load this skill.
GenTech Labs' integration patterns for BlockRun MCP from Hermes Agent. Covers daily usage patterns, cost-optimized workflows, multi-tool pipelines, and reliable error handling for BlockRun's full toolset.
name: gentech-blockrun description: "GenTech Labs' integration patterns for BlockRun MCP from Hermes Agent. Covers daily usage patterns, cost-optimized workflows, multi-tool pipelines, and reliable error handling for BlockRun's full toolset." triggers: - "blockrun" - "blockrun chat" - "blockrun search" - "blockrun price" - "blockrun defi" - "blockrun video" - "blockrun music" - "blockrun speech" - "blockrun wallet" - "blockrun rpc" - "blockrun surf" - "blockrun markets" - "blockrun exa" - "x402 payment" - "pay per call" - "micropayment" - "BlockRun MCP" - "cost optimization blockrun" - "multi-tool pipeline" - "agent wallet blockrun" - "gen tech blockrun"
Real-world patterns from running BlockRun MCP in production across 32 cron jobs and daily agent operations.
---
# Set up BlockRun wallet (one-time) blockrun_wallet(action="setup") # → Follow the QR to fund the wallet with USDC
# Set a global budget cap so spending never surprises you blockrun_wallet(action="budget", budget_action="set", budget_amount=10.0) # Spawn child agents with delegate budgets blockrun_wallet(action="delegate", agent_id="researcher", agent_limit=2.0) blockrun_wallet(action="delegate", agent_id="data-poller", agent_limit=0.50)
blockrun_wallet(action="status") # → Two wallets: Base + Solana. Active chain shown. Check before expensive runs.
---
Crypto, FX and commodity quotes cost **nothing** — `blockrun_price` is free for those categories (`stocks`/`usstock` quotes are not served since 2026-09-05 — the gateway 501s before payment; only the ticker catalog works). Use them liberally. (`blockrun_surf`, which used to charge $0.0085 for the same quote, was removed in 0.49.0 — the gateway 410s every Surf path since 2026-09-06.)
# Single price blockrun_price(action="price", category="crypto", symbol="BTC-USD") # Batch of prices blockrun_price(action="price", category="crypto", symbol="ETH-USD") blockrun_price(action="price", category="crypto", symbol="SOL-USD") # Free — discover available symbols blockrun_price(action="list", category="crypto", query="sol")
**Cost:** $0 — crypto/FX/commodity price *and* list calls are both free. `category:"stocks"` price/history currently return 501 (equity quotes withdrawn 2026-09-05, nothing charged); its `list` catalog is free.
Start with the free tools, then pay only for what they cannot answer.
# 1. Free — DEX liquidity + volume (free endpoint)
blockrun_dex({ query: "SOL" })
# 2. FREE — CEX price (crypto category is free)
blockrun_price(action="price", category="crypto", symbol="SOL-USD")
# 3. $0.0060 each — Protocol TVL
blockrun_defi({ path: "protocols" })
blockrun_defi({ path: "protocol/jupiter" })
# 4. $0.0060 — Chain TVL
blockrun_defi({ path: "chains" })**Total: ~$0.018 per full token analysis** (2 free calls + 3 x $0.0060 DefiLlama). Replace CoinGecko/CMC tabs entirely.
Use Exa (neural search) + BlockRun Chat (second opinion) for thorough research.
# 1. $0.0110 — Neural web search with Exa
blockrun_exa({ path: "search", body: {
query: "latest AI agent infrastructure developments 2026",
numResults: 10,
category: "research paper"
}})
# 2. per-token — Get second opinion from GLM-5 (excellent for technical details)
blockrun_chat({ mode: "glm", message: "Summarize the key trends..." })**Cost-conscious tip:** Use `mode: "free"` on `blockrun_chat` for zero-cost generation (NVIDIA models).
Use `blockrun_wallet` + `agent_id` for multi-agent cost tracking.
# Allocate budget per agent group
blockrun_wallet(action="delegate", agent_id="research", agent_limit=2.0)
blockrun_wallet(action="delegate", agent_id="content", agent_limit=1.0)
# Pass agent_id on every call
blockrun_defi({ path: "protocols", agent_id: "research" })
blockrun_search({ body: { query: "latest news", sources: ["web"] }, agent_id: "research" })
# Audit at end of day
blockrun_wallet(action="report")---
# 1. TVL & protocol health ($0.0060)
blockrun_defi({ path: "protocol/aave-v3" })
# 2. Yield pools ($0.0060)
blockrun_defi({ path: "yields" })
# 3. Token price (FREE — crypto category)
blockrun_price(action="price", category="crypto", symbol="AAVE-USD")
# 4. DEX activity (free)
blockrun_dex({ token: "0x7Fc66500c84A76Ad7e9c93437bFc5Ac33E2DDaE9" })# 1. Current holdings (free — local data or blockrun_rpc)
blockrun_rpc({ network: "base", method: "eth_getBalance", params: ["0xabc...", "latest"] })
# 2. Token prices (FREE — crypto category)
blockrun_price(action="price", category="crypto", symbol="ETH-USD")
blockrun_price(action="price", category="crypto", symbol="USDC-USD")
# 3. Prediction market positions ($0.0085)
blockrun_markets({ path: "polymarket/positions" })# 1. Research ($0.0110)
blockrun_exa({ path: "search", body: { query: "agentic commerce trends", numResults: 5 }})
# 2. Image generation for post ($0.01675 cheapest to $0.106 quality)
blockrun_image({ prompt: "AI agent futuristic dashboard with neon grids" })
# 3. Voiceover for video ($0.0535/1k chars)
blockrun_speech({ input: "Your narration text here...", voice: "sarah" })
# 4. Music track ($0.1585)
blockrun_music({ prompt: "upbeat synthwave background" })
# 5. Short video clip ($0.421)
blockrun_video({ prompt: "animated data visualization", duration_seconds: 8 })---
| Call Type | Price | Frequency | |-----------|-------|----------
Live data for AI agents — search, research, markets, crypto, X/Twitter. Pay-per-call via x402 micropayments.
Repo: BlockRunAI/blockrun-mcp
Use when the BlockRun MCP server (@blockrun/mcp) is installed but misbehaving — 'Failed to connect', spawn npx ENOENT, blockrun missing from claude mcp list,…
Use when asked to install, add, configure, or set up the BlockRun MCP server (@blockrun/mcp) in Claude Code, Claude Desktop, Cursor, Windsurf, Codex CLI, Grok…
Use when the BlockRun MCP server prints 'Update available', when asked to upgrade, update, or pin @blockrun/mcp, when a fix 'should be in the new version' but…
Pay-per-call access to AI models, real-time data, media generation and multi-chain RPC over x402 micropayments (USDC on Base or Solana). No API keys, no…
Use for any crypto data question — token/coin prices, FX, commodities, stocks, OHLC history, DEX pairs and liquidity, DeFi TVL, yield/APY pools, or raw…
Use when researching products, finding academic papers, discovering competitors, reading webpage content, or getting cited answers grounded in real web…