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 agentmods add commands/nirholas/three.ws/setup-mcpgit clone --depth 1 https://github.com/nirholas/three.wsWrote 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/commands/nirholas/three.ws/setup-mcp)<a href="https://agentmods.dev/commands/nirholas/three.ws/setup-mcp"><img src="https://agentmods.dev/badge/commands/nirholas/three.ws/setup-mcp.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00033 | $0.01152 |
| Opus 5 | $0.00016 | $0.00576 |
| Sonnet 5 | $0.00007 | $0.00230 |
| Haiku 4.5 | $0.00003 | $0.00115 |
Grade A, and why
setup-mcp 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are helping the user add the @three-ws/mcp-server to their MCP client config. Follow these steps precisely:
Step 1 — Detect OS and find the config file
Check the user's platform:
- macOS Claude Desktop:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows Claude Desktop:
%APPDATA%\Claude\claude_desktop_config.json - Claude Code (project):
.mcp.jsonin the current working directory - Claude Code (global):
~/.claude/claude_desktop_config.json - Cursor:
~/.cursor/mcp.json
Use uname -s or $OS to detect the platform. Check which of these files already exists with the shell.
Step 2 — Collect wallet addresses
Ask the user (in a single message) for:
- EVM wallet address (Base USDC payouts) —
0x...format - Solana wallet address (Solana USDC payouts) — base58 format
- Helius API key (optional, improves pump_snapshot data — get free at helius.dev)
- CDP API key ID + secret (optional, enables Coinbase Bazaar discovery — get at portal.cdp.coinbase.com)
If the user skips any optional field, omit that env var from the config.
Step 3 — Generate the config snippet
Produce the exact JSON block to add to their config file under "mcpServers":
{
"mcpServers": {
"3d-agent": {
"command": "npx",
"args": ["-y", "@three-ws/mcp-server"],
"env": {
"MCP_EVM_PAYMENT_ADDRESS": "<their EVM address>",
"MCP_SVM_PAYMENT_ADDRESS": "<their Solana address>"
}
}
}
}
Add optional env vars only if the user supplied them:
"HELIUS_API_KEY": "<key>"— better pump.fun token data"CDP_API_KEY_ID": "<id>"and"CDP_API_KEY_SECRET": "<secret>"— Coinbase Bazaar discovery"SOLANA_RPC_URL": "https://mainnet.helius-rpc.com/?api-key=<key>"— if Helius key provided
If the config file already exists, read it first and merge the "3d-agent" entry into the existing "mcpServers" object rather than replacing the whole file.
Step 4 — Write or show
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.
- 2d ago First seen · 94 lines · 33 tokens per session scan A fcd525f64050
setup-mcp is a command published in the GitHub repository nirholas/three.ws (110 stars, last pushed today), licensed Apache-2.0. It adds 33 tokens to every session and 1,152 once invoked, about $0.0002 per session on Opus 5. 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 2026-09-03.
Other commands, from other repositories
pr
Generate a pull request description for the current branch.
reskin
Extract a measured design signature (type ramp, accent + its budget, grid unit, radius, layout) from a reference image or site, write it to signature.json, and drive the build to match it — "steal this vibe" as a spec, not pixels.
assign
Assign a tiny.place agent to this session and remember it across restarts.
pay
Universal Crypto MCP API Reference v1.0.0.
kh_auth
Command "kh_auth" from KeeperHub/keeperhub, covering kh auth, examples, options, options inherited from parent commands and see also.
kh_config_list
Command "kh_config_list" from KeeperHub/keeperhub, covering kh config list, examples, options, options inherited from parent commands and see also.