blockrunai/blockrun-mcp/gentech-blockrun
- community
Checking that the SKILL.md file is still in the repository.
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.
Install
npx vskill@latest install blockrunai/blockrun-mcp/gentech-blockrunSKILL.md
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
Budget Controls
Check Balance
Daily Usage Patterns
Pattern 1: Regular Price Checks (FREE)
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.)
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 category:"stocks" price/history currently return 501 (equity quotes withdrawn 2026-09-05, nothing charged); its list catalog is free.
Pattern 2: Token Research Pipeline (~$0.018)
Start with the free tools, then pay only for what they cannot answer.
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.
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.
Multi-Tool Pipelines
DeFi Intelligence Pipeline
Portfolio Health Check
Content Generation Pipeline
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) | FREE | before every session | |
blockrun_price (quote) | FREE | crypto/FX/commodity; stocks quotes not served (501 since 2026-09-05) | |
blockrun_defi | $0.0060 | protocol/chain analysis ($0.0020 for prices/*) | |
blockrun_chat (free mode) | $0 | NVIDIA-backed chat | |
blockrun_chat (glm mode) | per-token | Zhipu GLM-5 coding — billed on tokens used, not a flat rate | |
blockrun_exa (search) | $0.0110 | deep research (contents: $0.002/URL + $0.001) | |
blockrun_speech | per model — live pricing at /api/v1/models | TTS | |
blockrun_image | per model — live pricing at /api/v1/models | image generation | |
blockrun_music | per model — live pricing at /api/v1/models | music tracks | |
blockrun_video | per model — live pricing at /api/v1/models | short video clips (per-second × duration) | |
blockrun_markets | $0.0085 | prediction market data, wallet analytics (flat) | |
blockrun_modal | $0.0020–$192 | remote sandbox execution — timeout drives the price, see the modal skill | |
blockrun_phone | $0.0110–$5.001 | lookups; number buy/renew is $5.001 |
Model-priced tools (chat beyond the free tier, speech, image, music, video) carry no number here because their prices move: read the model's pricing object from GET https://blockrun.ai/api/v1/models (Solana: https://sol.blockrun.ai/api/v1/models) — input/output per 1M tokens for chat, per_1k_chars for speech, per_image, per_track, or per_second for media, each plus transaction_fee. The HTTP 402 challenge quotes the exact amount before anything is signed.
Daily Budget Formula (GenTech's Setup)
Set a $5/week budget cap and never hit it with typical usage.
Error Handling Patterns
402 Payment Required
Insufficient Balance
Rate Limiting / Timeouts
Caching Strategy
BlockRun calls are cheap but not free. Cache results that don't change minute-to-minute:
- Token prices: No need to cache aggressively — crypto/FX/commodity quotes via
blockrun_priceare FREE. - Protocol TVL: Cache for 1 hour (updates hourly)
- Wallet labels: Cache for 24 hours (rarely change)
- On-chain SQL results: Cache for 1 hour (most queries return the same answer)
GenTech's approach: Don't bother caching prices (crypto/FX/commodity quotes are FREE). Cache TVL and wallet labels aggressively.
Switching Chains
Note: Every paid media tool (image, video, music, speech, realface) pays on either chain. Base-only: blockrun_modal, blockrun_defi, claude-* chat with thinking (a plain claude-* call takes the compat path on Solana), and Polymarket funding. Solana works for price, wallet, dex, rpc, markets, etc.
Reference
- BlockRun MCP: https://github.com/BlockRunAI/blockrun-mcp
- BlockRun Docs: https://blockrun.ai/docs
- Models & Pricing: https://blockrun.ai/models
- Community: https://t.me/blockrunAI
_Contributed by GenTech Labs, from real production usage of BlockRun MCP._
Security
- Security scanPassed, 93 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/gentech-blockrun/SKILL.md
Popularity
- Repository stars
- 389
- Repository forks
- 38
- 7-day trend score
- 30
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/blockrunai/blockrun-mcp/gentech-blockrun)