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 tranfu-labs/tranfu-skills --skill privy-mcpgit clone --depth 1 https://github.com/tranfu-labs/tranfu-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/tranfu-labs/tranfu-skills/privy-mcp)<a href="https://agentmods.dev/skills/tranfu-labs/tranfu-skills/privy-mcp"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/privy-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/tranfu-labs/tranfu-skills/privy-mcp"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/privy-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 | $0.00126 | $0.01886 |
| Opus 5 | $0.00063 | $0.00943 |
| Sonnet 5 | $0.00025 | $0.00377 |
| Haiku 4.5 | $0.00013 | $0.00189 |
Grade A, and why
privy-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 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.
How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Privy MCP
Use current official Privy documentation as evidence, reconcile it with the target project's installed SDK and architecture, then implement and verify the requested integration. Prefer an MCP server already exposed by the runtime. If the project configures Privy only for another editor, use the bundled read-only client without changing Codex configuration.
Required outcome
Produce a named PRIVY_EVIDENCE_PACKET containing:
- the question and detected project context;
- official Privy claims with exact documentation URLs;
- project constraints and conflicts kept separate from vendor claims;
- the implementation or recommendation derived from both;
- deterministic checks run, results, and unverified items.
For implementation requests, MUST edit only files authorized by the user and the project rules. For research-only requests, NEVER edit project files.
Workflow
CREATE A TODO LIST FOR THE TASKS BELOW:
- Read project agent rules, package manifests, relevant source/tests, architecture decisions, and MCP config candidates such as
.cursor/mcp.json,.mcp.json,.vscode/mcp.json, and Codex MCP registrations. If the request is ambiguous about the desired behavior, ask one focused question and stop. - Record the target runtime, installed Privy package names and versions, authentication boundary, wallet ownership model, chains, and requested outcome. Never infer an API shape solely from prior knowledge.
- Select the documentation path:
- If a Privy MCP tool is already exposed, use it.
- Otherwise run
python3 <skill-dir>/scripts/privy_mcp.py server-info, then use the same client for the remaining calls. - If the endpoint is unavailable, use
https://docs.privy.io/llms.txt,https://docs.privy.io/llms-full.txt, and the linked official pages as read-only fallbacks. Mark the MCP path unverified.
- Read the MCP resource
mintlify://skills/privyonce per task when available. Treat it as navigation guidance, not sufficient evidence for version-sensitive code. - Search broadly with
search_privy_docs, then read the most relevant.mdxpages withquery_docs_filesystem_privy_docs. For REST details, inspect the official OpenAPI material exposed in the documentation filesystem. Read migration pages when installed SDK major versions or examples conflict. - Build an evidence table before editing. Label each row
official_doc,project_constraint, orinference; include a precise URL for everyofficial_docrow. If official pages conflict, prefer the page matching the installed SDK/platform and report the conflict. - For an implementation request, make the smallest change consistent with both the evidence table and project architecture. Never let a vendor recipe silently override an accepted ADR, ownership boundary, or server trust boundary.
- Run deterministic verification in repository-defined order: targeted tests, type check, lint, build, then any manual or live check explicitly authorized by the user. A documentation result is not runtime verification.
- Emit
PRIVY_EVIDENCE_PACKETand end. State changed files, every verification command and result, exact citations, and all unverified behavior.
What ships with it
8 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 · 116 lines · 126 tokens per session scan A 070fe0960327
privy-mcp is a skill published in the GitHub repository tranfu-labs/tranfu-skills (2 stars, last pushed 2d ago), licensed MIT. It adds 126 tokens to every session and 1,886 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
signature-replay
Signature replay attacks — missing nonces, missing chain ID, ecrecover zero address, signature malleability, cross-chain replay.
official-sui-skills
Pointer to the official Mysten Labs skills for building on Sui — language fundamentals, object model, PTBs, SDKs, publishing, upgrades, frontend integration, accessing on-chain data. Maintained upstream at github.com/MystenLabs/skills; pinned to the same ref the audit catalog derives from (see…
bridge
Cross-chain token transfers using Wormhole and CCTP.
onchainkit
Build onchain apps with Coinbase's OnchainKit React components - wallets, swaps, NFTs, payments.
marginfi
MarginFi — Solana lending and borrowing.
crypto-market-rank
Crypto market rankings and leaderboards. Query trending tokens, top searched tokens, Binance Alpha tokens, tokenized stocks, social hype sentiment ranks, smart money inflow token rankings, top meme token rankings from Pulse launchpad, and top trader PnL leaderboards. Use this skill when users ask about token rankings…