Helius for Solana
internet-court/internet-court-skill
Guides building Solana apps on Helius: sending transactions, asset and NFT queries, live streaming, webhooks, priority fees, wallet analysis and API key onboarding.
GenTech Labs' integration patterns for BlockRun MCP from Hermes Agent.
$ npx skills add BlockRunAI/blockrun-mcp --skill gentech-blockrun -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install BlockRunAI/blockrun-mcp gentech-blockrun --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/BlockRunAI/blockrun-mcp.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/gentech-blockrun .claude/skills/gentech-blockrun && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "gentech-blockrun" agent skill from https://github.com/BlockRunAI/blockrun-mcp/tree/main/skills/gentech-blockrun into .claude/skills/gentech-blockrun/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gentech-blockrun", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/BlockRunAI/blockrun-mcp/tree/main/skills/gentech-blockrunType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add BlockRunAI/blockrun-mcp --skill gentech-blockrun -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install BlockRunAI/blockrun-mcp gentech-blockrun --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/BlockRunAI/blockrun-mcp.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/gentech-blockrun .agents/skills/gentech-blockrun && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "gentech-blockrun" agent skill from https://github.com/BlockRunAI/blockrun-mcp/tree/main/skills/gentech-blockrun into .agents/skills/gentech-blockrun/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gentech-blockrun", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add BlockRunAI/blockrun-mcp --skill gentech-blockrun -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install BlockRunAI/blockrun-mcp gentech-blockrun --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/BlockRunAI/blockrun-mcp.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/gentech-blockrun .cursor/skills/gentech-blockrun && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "gentech-blockrun" agent skill from https://github.com/BlockRunAI/blockrun-mcp/tree/main/skills/gentech-blockrun into .cursor/skills/gentech-blockrun/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gentech-blockrun", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/BlockRunAI/blockrun-mcp.git --path skills/gentech-blockrun--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add BlockRunAI/blockrun-mcp --skill gentech-blockrun -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install BlockRunAI/blockrun-mcp gentech-blockrun --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/BlockRunAI/blockrun-mcp.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/gentech-blockrun .gemini/skills/gentech-blockrun && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "gentech-blockrun" agent skill from https://github.com/BlockRunAI/blockrun-mcp/tree/main/skills/gentech-blockrun into .gemini/skills/gentech-blockrun/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gentech-blockrun", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install BlockRunAI/blockrun-mcp gentech-blockrunInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add BlockRunAI/blockrun-mcp --skill gentech-blockrun -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/BlockRunAI/blockrun-mcp.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/gentech-blockrun .github/skills/gentech-blockrun && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "gentech-blockrun" agent skill from https://github.com/BlockRunAI/blockrun-mcp/tree/main/skills/gentech-blockrun into .github/skills/gentech-blockrun/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gentech-blockrun", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add BlockRunAI/blockrun-mcp --skill gentech-blockrun -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install BlockRunAI/blockrun-mcp gentech-blockrun --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/BlockRunAI/blockrun-mcp.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/gentech-blockrun .opencode/skills/gentech-blockrun && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "gentech-blockrun" agent skill from https://github.com/BlockRunAI/blockrun-mcp/tree/main/skills/gentech-blockrun into .opencode/skills/gentech-blockrun/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gentech-blockrun", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
gentech-blockrunGenTech Labs' integration patterns for BlockRun MCP from Hermes Agent.
Gentech Blockrun is an agent skill from BlockRunAI/blockrun-mcp. 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.
Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Backend & APIs, covering Third-party API integration and Crypto and DeFi analysis. It works with Model Context Protocol. The repository describes itself as: Live data for AI agents — search, research, markets, crypto, X/Twitter. Pay-per-call via x402 micropayments. The licence is MIT.
Read from SKILL.md and the folder at commit e9b2bd5. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are python, bash and yaml).
From the folder's file list and the shell code blocks in SKILL.md.
Links to these hosts (documentation or services it may open):
blockrun.ait.meFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Gentech Blockrun loads about 2.5k tokens when it runs. Until then it costs about 55 tokens; SKILL.md has 500 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from BlockRunAI/blockrun-mcp at commit e9b2bd5, republished under its MIT licence (© BlockRunAI). 500 words, ~2,536 tokens.
.claude/skills/gentech-blockrun/SKILL.md (or your agent's skills folder).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 |
|---|---|---|
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 | $0.0535/1k chars | TTS |
blockrun_image | $0.01675–0.106 | image generation |
blockrun_music | $0.1585 | music tracks |
blockrun_video | $0.421+ | 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 |
# ~$0.30/day typical
Daily budget:
Free tools: unlimited (price quotes, dex, list, wallet status)
Crypto data: ~$0.10 (markets, flat $0.0085; defi $0.0060; surf is retired and free)
AI calls: ~$0.10 (chat free mode, occasional glm)
Media: ~$0.10 (occasional image/speech)
Total: ~$0.30/daySet a $5/week budget cap and never hit it with typical usage.
# When the wallet is FUNDED, x402 handles this automatically: the SDK
# signs the payment challenge and retries — no action needed.
#
# When the wallet is EMPTY, the 402 / insufficient-balance surfaces to you.
# Check status and fund FIRST — don't blindly retry the failing tool:
blockrun_wallet(action="status") # then action="setup" / "deposit"# Before a batch of expensive calls:
balance = blockrun_wallet(action="status")
if float(balance["usdcBalance"]) < 0.50:
blockrun_wallet(action="deposit") # → opens Coinbase Onramp link# For async operations (video, music):
# They auto-poll until complete. On a timeout READ THE ERROR: on the Base
# wallet payment settles on completion, so a timeout is not charged and a
# retry is safe; Solana music and every account-rail media job are billed
# at submit, so the timed-out job IS charged, the error names it, and a
# retry bills a second job. Check blockrun_wallet action:"report" first.BlockRun calls are cheap but not free. Cache results that don't change minute-to-minute:
blockrun_price are FREE.GenTech's approach: Don't bother caching prices (crypto/FX/commodity quotes are FREE). Cache TVL and wallet labels aggressively.
# Default is Base. Switch to Solana for Solana-native tools:
blockrun_wallet(action="chain", chain="solana")
# Switch back:
blockrun_wallet(action="chain", chain="base")
# Check which is active:
blockrun_wallet(action="chain")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.
Contributed by GenTech Labs, from real production usage of BlockRun MCP.
© BlockRunAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in skills/gentech-blockrun of BlockRunAI/blockrun-mcp.
Open the folder on GitHubat commit e9b2bd5
Gentech Blockrun next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Gentech Blockrun this skillBlockRunAI/blockrun-mcp | 392 | — | ~2.5k | Automated safety check: Pass | MIT | |
| Helius for Solanainternet-court/internet-court-skill | 6.4k | 2 repos | ~2.7k | Automated safety check: Pass | Apache-2.0 | |
| Solana Devaiskillstore/marketplace | 430 | — | ~2.4k | Automated safety check: Pass | MIT | |
| CoinGecko API Reference2025Emma/vibe-coding-cn | 23k | 2 repos | ~646 | Automated safety check: Pass | MIT | |
| MCP API Key AuthenticationYourdaylight/stock_datasource | 188 | — | ~1.2k | Automated safety check: Pass | MIT | |
| Agentmemory REST APIrohitg00/agentmemory | 29k | — | ~404 | Automated safety check: Pass | Apache-2.0 |
internet-court/internet-court-skill
Guides building Solana apps on Helius: sending transactions, asset and NFT queries, live streaming, webhooks, priority fees, wallet analysis and API key onboarding.
aiskillstore/marketplace
A skill your agent uses when user asks to "build a Solana dapp", "write an Anchor program", "create a token", "debug Solana errors", "set up wallet connection", "test my Solana program", "deploy to…
2025Emma/vibe-coding-cn
CoinGecko API documentation - cryptocurrency market data API, price feeds, market cap, volume, historical data. Use when integrating CoinGecko API, building…
Yourdaylight/stock_datasource
Sets up and troubleshoots MCP API key authentication for a stock data service, covering key creation, client configuration and per-tool usage statistics.
rohitg00/agentmemory
Covers the HTTP REST endpoints of the agentmemory server, its primary interface, for hosts without MCP or when MCP is unavailable.
internet-court/internet-court-skill
Shows how to read Pyth oracle prices in Solana apps, off-chain through the Hermes client or on-chain from an Anchor program, including confidence and EMA values.
BlockRunAI/blockrun-mcp
Prepare or run a polished BlockRun trading demo that discovers a current Polymarket market, combines live price, probability history, smart-money, and liquidity evidence into a balanced signal…
BlockRunAI/blockrun-mcp
Pay-per-call access to AI models, real-time data, media generation and multi-chain RPC over x402 micropayments (USDC on Base or Solana), or a BlockRun account API key.
BlockRunAI/blockrun-mcp
A skill your agent uses when the BlockRun MCP server (@blockrun/mcp) is installed but misbehaving — 'Failed to connect', spawn npx ENOENT, blockrun missing from claude mcp list, HTTP 402 /…
BlockRunAI/blockrun-mcp
A skill your agent uses 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 or another MCP…
BlockRunAI/blockrun-mcp
A skill your agent uses 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 the client still…
BlockRunAI/blockrun-mcp
A skill your agent uses for any crypto data question — token/coin prices, FX, commodities, stocks, OHLC history, DEX pairs and liquidity, DeFi TVL, yield/APY pools, or raw JSON-RPC against a chain…
Works with
GenTech Labs' integration patterns for BlockRun MCP from Hermes Agent. Gentech Blockrun is an agent skill from BlockRunAI/blockrun-mcp. GenTech Labs' integration patterns for BlockRun MCP from Hermes Agent.
Gentech Blockrun fits situations like: tasks that involve Third-party API integration; tasks that involve Crypto and DeFi analysis.
Run `npx skills add BlockRunAI/blockrun-mcp --skill gentech-blockrun -a claude-code`. Or copy the skill folder (skills/gentech-blockrun in BlockRunAI/blockrun-mcp) into .claude/skills/gentech-blockrun in your project. Claude Code loads it when a task matches its description.
Run `npx skills add BlockRunAI/blockrun-mcp --skill gentech-blockrun -a codex`. Or copy the skill folder (skills/gentech-blockrun in BlockRunAI/blockrun-mcp) into .agents/skills/gentech-blockrun in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add BlockRunAI/blockrun-mcp --skill gentech-blockrun -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/gentech-blockrun, .gemini/skills/gentech-blockrun, .github/skills/gentech-blockrun and .opencode/skills/gentech-blockrun in your project.
SKILL.md names no scripts, command-line tools or credentials: Gentech Blockrun is instructions for the agent only. Our summary lists: Python 3.
SKILL.md names 2 domains. As links in the text: blockrun.ai and t.me. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Gentech Blockrun is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.5k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Gentech Blockrun: Helius for Solana (internet-court/internet-court-skill, 6.4k stars), Solana Dev (aiskillstore/marketplace, 430 stars), CoinGecko API Reference (2025Emma/vibe-coding-cn, 23k stars) and MCP API Key Authentication (Yourdaylight/stock_datasource, 188 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
BlockRunAI (a GitHub organization) maintains it in BlockRunAI/blockrun-mcp, which has 392 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on October 8, 2026.
Source: BlockRunAI/blockrun-mcp on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.