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/seashail/seashailWrote 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/seashail/seashail/claude-desktop-seashail)<a href="https://agentmods.dev/mcp/seashail/seashail/claude-desktop-seashail"><img src="https://agentmods.dev/badge/mcp/seashail/seashail/claude-desktop-seashail/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/seashail/seashail/claude-desktop-seashail"><img src="https://agentmods.dev/badge/mcp/seashail/seashail/claude-desktop-seashail.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
seashail 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 10d 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
{
"seashail": {
"command": "seashail",
"args": [
"mcp"
]
}
}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.
- 10d ago First seen · 8 lines scan A 643009d4bd07
seashail is an MCP server published in the GitHub repository seashail/seashail (7 stars, last pushed 4mo ago), licensed Apache-2.0. 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
x402-bridge
Pay any x402 endpoint on the open web: auto-paying bridge with Bazaar discovery and spend caps. Runs locally from the @three-ws/mcp-bridge npm package. Needs 13 environment variables to run.
three-token-mcp
Price, hold, and burn $THREE on Solana — the first MCP server whose actions burn a token. Runs locally from the @three-ws/three-token-mcp npm package. Needs 5 environment variables to run.
agent-sniper
Self-custodial pump.fun sniper: arm strategies, snipe, manage positions. Simulate by default. Runs locally from the @three-ws/agent-sniper npm package. Needs 4 environment variables to run.
agentcore-payments-mcp
Governed x402 payment sessions: pay any endpoint with budget, allowlist & per-tx caps, no key. Runs locally from the @three-ws/agentcore-payments-mcp npm package. Needs 4 environment variables to run.
x402-mcp
Self-custodial x402 wallet for AI agents: pay any service in USDC or $THREE from your own key. Runs locally from the @three-ws/x402-mcp npm package. Needs 5 environment variables to run.
intel-mcp
Coin smart-money scores, wallet reputation, signal feeds, and KOL leaderboards. Runs locally from the @three-ws/intel-mcp npm package. Needs 2 environment variables to run.