/gentech-blockrun
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.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/gentech-blockrun
Context 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.
SKILL.md
gentech-blockrun.SKILL.mdname: 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"
GenTech Labs — BlockRun Integration Patterns
Real-world patterns from running BlockRun MCP in production across 32 cron jobs and daily agent operations.
---
Getting Started
Initial Wallet Setup
# Set up BlockRun wallet (one-time)
blockrun_wallet(action="setup")
# → Follow the QR to fund the wallet with USDC
Budget Controls
# 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)
Check Balance
blockrun_wallet(action="status")
# → Two wallets: Base + Solana. Active chain shown. Check before expensive runs.
---
Daily Usage Patterns
Pattern 1: Regular Price Checks (FREE)
Crypto, FX and commodity quotes cost **nothing** — `blockrun_price` is free for those categories (only `stocks`/`usstock` is paid, at $0.0020). Use them liberally, and do not pay $0.0085 to `blockrun_surf` for a quote you can get for $0.
# 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. Only `category:"stocks"` is paid ($0.0020).
Pattern 2: Token Research Pipeline (~$0.018)
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.
Pattern 3: Research + Synthesis (~$0.011 + chat)
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).
Pattern 4: Agent-to-Agent Billing
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_surf({ path: "market/price", params: { symbol: "BTC" }, agent_id: "research" })
blockrun_search({ body: { query: "latest news", sources: ["web"] }, agent_id: "research" })
# Audit at end of day
blockrun_wallet(action="report")---
Multi-Tool Pipelines
DeFi Intelligence Pipeline
# 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" })Portfolio Health Check
# 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" })Content Generation Pipeline
# 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 })---
Cost Optimization Strategies
Tier Mapping
| Call Type | Price | Frequency | |-----------|-------|-----------| | `blockrun_price` (list) | FREE | daily discovery | | `blockrun_dex` | FREE | unlimited | | `blockrun_rpc` | $0.0030 | on-chain reads (batch: $0.002/element + $0.001) | | `blockrun_wallet` (status/report) | F
Read more
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"
GenTech Labs — BlockRun Integration Patterns
Real-world patterns from running BlockRun MCP in production across 32 cron jobs and daily agent operations.
---
Getting Started
Initial Wallet Setup
# Set up BlockRun wallet (one-time) blockrun_wallet(action="setup") # → Follow the QR to fund the wallet with USDC
Budget Controls
# 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)
Check Balance
blockrun_wallet(action="status") # → Two wallets: Base + Solana. Active chain shown. Check before expensive runs.
---
Daily Usage Patterns
Pattern 1: Regular Price Checks (FREE)
Crypto, FX and commodity quotes cost **nothing** — `blockrun_price` is free for those categories (only `stocks`/`usstock` is paid, at $0.0020). Use them liberally, and do not pay $0.0085 to `blockrun_surf` for a quote you can get for $0.
# 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. Only `category:"stocks"` is paid ($0.0020).
Pattern 2: Token Research Pipeline (~$0.018)
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.
Pattern 3: Research + Synthesis (~$0.011 + chat)
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).
Pattern 4: Agent-to-Agent Billing
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_surf({ path: "market/price", params: { symbol: "BTC" }, agent_id: "research" })
blockrun_search({ body: { query: "latest news", sources: ["web"] }, agent_id: "research" })
# Audit at end of day
blockrun_wallet(action="report")---
Multi-Tool Pipelines
DeFi Intelligence Pipeline
# 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" })Portfolio Health Check
# 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" })Content Generation Pipeline
# 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 })---
Cost Optimization Strategies
Tier Mapping
| Call Type | Price | Frequency | |-----------|-------|-----------| | `blockrun_price` (list) | FREE | daily discovery | | `blockrun_dex` | FREE | unlimited | | `blockrun_rpc` | $0.0030 | on-chain reads (batch: $0.002/element + $0.001) | | `blockrun_wallet` (status/report) | F
Live data for AI agents — search, research, markets, crypto, X/Twitter. Pay-per-call via x402 micropayments.
Repo: BlockRunAI/blockrun-mcp
Other skills on blockrun-mcp.
- /blockrun
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 accounts, no subscriptions. Start here when you have the BlockRun MCP installed and need to know WHICH tool answers a
Open skill - /crypto-data
Use for any crypto data question — token/coin prices, FX, commodities, stocks, OHLC history, DEX pairs and liquidity, DeFi TVL, yield/APY pools, on-chain SQL, wallet labels and net worth, social mindshare, news, or raw JSON-RPC against a chain. Routes across five tools that
Open skill - /exa-research
Use when researching products, finding academic papers, discovering competitors, reading webpage content, or getting cited answers grounded in real web sources. Use over generic search when semantic relevance matters.
Open skill - /image-prompting
Use when generating or editing images via `blockrun_image` — especially with GPT Image 2, Nano Banana, or Grok Imagine for posters, UI mockups, marketing assets, product shots, or anything with on-image text. Turns vague user requests ("make me a cool poster") into structured,
Open skill - /modal
Use when the user needs to run isolated code remotely — a disposable container, optional GPU access (T4 → H100), or a safer place for untrusted / heavy code. Prefer local execution for normal repo work; use Modal sandboxes for isolation, hardware access, or one-shot heavy
Open skill - /phone
Use when the user wants phone-number intelligence (lookup, carrier, line type, SIM-swap / call-forwarding fraud signals), US/CA number provisioning (rent a phone number), or outbound AI voice calls (Bland.ai under the hood — schedule, confirm, follow-up). Pay per call in USDC.
Open skill

