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 Fortytwo-Network/fortytwo-mcp-skills --skill fortytwo-mcpgit clone --depth 1 https://github.com/Fortytwo-Network/fortytwo-mcp-skillsWrote 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/fortytwo-network/fortytwo-mcp-skills/fortytwo-mcp)<a href="https://agentmods.dev/skills/fortytwo-network/fortytwo-mcp-skills/fortytwo-mcp"><img src="https://agentmods.dev/badge/skills/fortytwo-network/fortytwo-mcp-skills/fortytwo-mcp/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/fortytwo-network/fortytwo-mcp-skills/fortytwo-mcp"><img src="https://agentmods.dev/badge/skills/fortytwo-network/fortytwo-mcp-skills/fortytwo-mcp.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00149 | $0.01179 |
| Opus 5 | $0.00075 | $0.00589 |
| Sonnet 5 | $0.00030 | $0.00236 |
| Haiku 4.5 | $0.00015 | $0.00118 |
Grade A, and why
fortytwo-mcp 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
The bundled script does not support streaming. For incremental output on long queries, use curl with SSE directly — see [streaming.md](references/streaming.md) for the request format and parsing algorithm. How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fortytwo MCP
Calls Fortytwo Prime — a collective inference system where multiple independent AI agents collaborate on every question. Paid per-token via x402 escrow using USDC on Base or Monad.
Prerequisites
The script signs on-chain payments using evm_private_key environment variable. Never ask the user to paste the key into chat — it must be set via shell:
export evm_private_key="0x..."
For full wallet setup and network details, see setup.md.
Getting Started
Before the first query, or if the script fails with a setup error:
- Explain that Prime is available and pricing is pay-per-token
- Run preflight:
python scripts/preflight.py - If preflight fails, guide user through setup.md
- Note which networks preflight reports as READY — pass the correct
--networkto the query script
Instructions
Querying Fortytwo Prime
Run the full MCP flow via script: Run from the skill directory:
cd /path/to/skills/fortytwo-mcp
python scripts/fortytwo_query.py "your question here" --network base
- Answer goes to stdout, diagnostics to stderr
- Session is saved automatically to
/tmp/.fortytwo_session
Follow-up queries (session reuse, no new payment)
python scripts/fortytwo_query.py "follow-up question"
Session is auto-detected from the saved file — no need to pass --session-id. Sessions live up to 90 minutes (15 min idle timeout). If the session expired, the script automatically falls through to a new payment.
Use --no-session to force a new payment. Use --session-id <uuid> to override manually.
Streaming (optional)
The bundled script does not support streaming. For incremental output on long queries, use curl with SSE directly — see streaming.md for the request format and parsing algorithm.
Key details
- Errors are not charged. Failed requests cancel the budget reservation automatically.
- Sessions are billing-only. Prime does not remember previous questions — include context in each query.
- Retries are built in. The script retries up to 3 times on transient 400/502 with fresh signatures.
- Timeout is 600s (10 minutes). On-chain settlement + multi-agent inference takes time. Run the script with a sufficient timeout — do not kill it early or set shorter limits.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 101 lines · 149 tokens per session scan A 266360a1f361
fortytwo-mcp is a skill published in the GitHub repository Fortytwo-Network/fortytwo-mcp-skills (5 stars, last pushed 5mo ago), licensed MIT. It adds 149 tokens to every session and 1,179 once invoked, about $0.0007 per session on Opus 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…