Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add BlockRunAI/blockrun-mcp --skill surfgit clone --depth 1 https://github.com/BlockRunAI/blockrun-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/blockrunai/blockrun-mcp/surf)<a href="https://agentmods.dev/skills/blockrunai/blockrun-mcp/surf"><img src="https://agentmods.dev/badge/skills/blockrunai/blockrun-mcp/surf/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/blockrunai/blockrun-mcp/surf"><img src="https://agentmods.dev/badge/skills/blockrunai/blockrun-mcp/surf.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 76 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00110 | $0.01926 |
| Opus 5.5 | $0.00044 | $0.00770 |
| Sonnet 5.5 | $0.00022 | $0.00385 |
| Haiku 4.5 | $0.00011 | $0.00193 |
Grade A, and why
surf scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 16d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Gateway retirement notice: `curl -s https://blockrun.ai/v1/surf/market/price` (HTTP 410, free) How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Surf — retired on BlockRun (2026-09-06)
Surf (asksurf.ai) is no longer served through BlockRun. Since 2026-09-06 the
gateway answers every /v1/surf/* path with:
HTTP 410
{"error":{"code":"endpoint_retired","message":"The Surf data endpoints are retired. We are looking for a new vendor in this space and expect to publish a replacement under /api/v1/."},
"retired_on":"2026-09-06",
"alternatives":[{"for":"crypto, equity, FX and commodity prices","endpoint":"/api/v1/crypto/price"},
{"for":"protocol TVL and yields","endpoint":"/api/v1/defillama/*"},
{"for":"prediction markets","endpoint":"/api/v1/pm/*"},
{"for":"DEX quotes and swaps","endpoint":"/api/v1/zerox/*"}]}
Verified live 2026-09-08 with an unauthenticated GET (a 410 is free to fetch).
sol.blockrun.ai answers 404 on the same paths, and /api/openapi no longer
lists any Surf route. No 402 is ever issued, so no payment can be made.
blockrun_surf was removed from the server in 0.49.0 and is no longer one of
the 19 tools: a tool that can only
return an error is not worth the schema every agent carries on every turn. An
MCP client will answer an unknown-tool error if a config still names it. Nothing
can be charged either way. Do not describe this as a temporary outage — it is
not; route the question with the table below.
Where each former Surf capability lives now
| The user wants… | Surf used to be | Use now | Cost |
|---|---|---|---|
| BTC/ETH/any coin price, OHLC history | market/price, exchange/klines |
blockrun_price action:"price" / "history" category:"crypto" |
FREE |
| FX, gold, oil | market/price |
blockrun_price category:"fx" / "commodity" |
FREE |
| Fear & Greed, market ranking by cap | market/fear-greed, market/ranking |
blockrun_price action:"list" for the symbol universe; no sentiment index on BlockRun |
FREE / none |
| DEX pair, liquidity, volume, token by contract | token/dex-trades, search/project |
blockrun_dex |
FREE |
| Token price by contract address | market/price |
blockrun_defi path:"prices/{coins}" |
$0.001 + fee |
| Protocol / chain TVL, yield rankings | project/defi/ranking, onchain/yield/ranking |
blockrun_defi path:"protocols" / "chains" / "yields" |
$0.005 + fee |
| Polymarket / Kalshi markets, prices, positions | prediction-market/*, search/polymarket, search/kalshi |
blockrun_markets — see skills/prediction-markets/SKILL.md |
$0.0075 + fee |
| Who is this Polymarket wallet, and which wallets are theirs | wallet/detail, wallet/labels/batch (for Polymarket traders only) |
blockrun_markets polymarket/wallet/identity/{wallet} + polymarket/wallet/{address}/cluster |
$0.0075 + fee |
| Gas price, a transaction, a balance, a contract read | onchain/gas-price, onchain/tx |
blockrun_rpc (eth_gasPrice, eth_getTransactionByHash, eth_getBalance, eth_call) — see skills/rpc/SKILL.md |
$0.002 + fee |
| Web / news search | search/web, search/news, news/feed |
blockrun_exa (neural) or blockrun_search (Grok Live Search, web + X + news) |
$0.01 + fee / $0.08 + fee |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 16d ago Changed 4a1629efcdd5
- 1mo ago Changed · -167 lines · +18 tokens per session 7796259d819f
- 1mo ago First seen · 285 lines · 92 tokens per session scan A 39d42c40fd86
surf is a skill published in the GitHub repository BlockRunAI/blockrun-mcp (392 stars, last pushed 3d ago), licensed MIT. It adds 110 tokens to every session and 1,926 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
x402
HTTP 402 payment protocol for AI agent commerce — three-actor model (Client, Resource Server, Facilitator), ERC-3009 transferWithAuthorization, server middleware (@x402/express), client patterns in TypeScript and Python, facilitator integration, agent-to-agent payments, pricing strategies, and replay protection. Works…
x402-list
Discover x402 payment services and on-chain-verified facilitator settlement volume via the x402-list directory. Use when a user or agent needs to find an API/service that accepts x402 (HTTP 402 stablecoin) payments, compare services by reliability and price, check service uptime/health, see whether a service has…
x402-payments
Quote and settle OpenMesha x402 paywalled services (USDC on Base). Use when metering tool calls, outcome fees, or agent-to-agent settlement.
hyperliquid
Hyperliquid market data, account history, trade review.
solana
Query Solana wallets, tokens, txs, and NFTs in USD.
mpp-agent
Pay HTTP 402 APIs via Machine Payments Protocol (MPP).