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.
git clone --depth 1 https://github.com/Haiku-Trading/haiku-mcp-serverWrote 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/mcp/haiku-trading/haiku-mcp-server/haiku)<a href="https://agentmods.dev/mcp/haiku-trading/haiku-mcp-server/haiku"><img src="https://agentmods.dev/badge/mcp/haiku-trading/haiku-mcp-server/haiku/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/mcp/haiku-trading/haiku-mcp-server/haiku"><img src="https://agentmods.dev/badge/mcp/haiku-trading/haiku-mcp-server/haiku.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
haiku scanned grade A with 0 findings 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 12d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"haiku": {
"command": "npx",
"args": [
"haiku-mcp-server"
],
"env": {
"HAIKU_API_KEY": ""
}
}
}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.
- 12d ago First seen · 11 lines scan A 8f73ff650135
haiku is an MCP server published in the GitHub repository Haiku-Trading/haiku-mcp-server (2 stars, last pushed 4mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other mcp servers, from other repositories
base-transaction-decoder
Decode any Base tx: plain English, strict JSON, risk flags, no LLM. 50 free/day per IP, then $0.02. Remote server at api.0200project.com.
base-intel-mcp
Read-only on-chain intel for AI agents on Base: balances, tokens, gas, tx status. No API keys. Remote server at base.datakoot.com.
abi-to-mcp
UCAI — The ABI-to-MCP Server Generator. Convert smart contract ABIs to AI-ready MCP servers. Runs locally from the abi-to-mcp Python package. Needs 3 environment variables to run.
mcp-blockchain
MCP server "mcp-blockchain" as configured in shubhamdusane/mcp-blockchain. Runs locally from the mcp-blockchain npm package.
orbis-mcp
8,000+ pay-per-call APIs via x402 USDC micropayments on Base. No API keys needed. Runs locally from the @orbisapi/mcp npm package. Needs 1 environment variable to run.
base-price-oracle-mcp
MCP server for real-time token prices on Base from on-chain DEX pools. Runs locally from the base-price-oracle-mcp npm package. Needs 1 environment variable to run.