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 Abstract-Foundation/abstract-skills --skill using-agw-mcpgit clone --depth 1 https://github.com/Abstract-Foundation/abstract-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/abstract-foundation/abstract-skills/using-agw-mcp)<a href="https://agentmods.dev/skills/abstract-foundation/abstract-skills/using-agw-mcp"><img src="https://agentmods.dev/badge/skills/abstract-foundation/abstract-skills/using-agw-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/abstract-foundation/abstract-skills/using-agw-mcp"><img src="https://agentmods.dev/badge/skills/abstract-foundation/abstract-skills/using-agw-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 | $0.00074 | $0.00464 |
| Opus 5 | $0.00037 | $0.00232 |
| Sonnet 5 | $0.00015 | $0.00093 |
| Haiku 4.5 | $0.00007 | $0.00046 |
Grade A, and why
using-agw-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.
What it actually says
Using AGW MCP
The agw-mcp server gives AI agents wallet capabilities on Abstract via the Model Context Protocol. This is the counterpart to the abstract-global-wallet skill — AGW is for end-user facing apps, agw-mcp is for AI agent access.
When to Use What
| Scenario | Tool |
|---|---|
| Building a React app where users log in and transact | abstract-global-wallet skill (AGW React SDK) |
| AI agent needs to read chain data / balances | agw-mcp (this skill) |
| AI agent needs to execute transactions on user's behalf | agw-mcp (read+write coming soon) |
| AI agent needs to trade on Myriad | myriad-on-abstract skill (API) + agw-mcp for wallet ops |
Current Status
v1 — read-only. The MCP server currently provides read access to Abstract chain data. Write capabilities (sending transactions, signing messages) are in active development.
Setup
agw-mcp is an MCP server. Configure it in your Claude Code settings, AI agent framework, or any MCP-compatible client.
Since the repo is currently private, refer to the README in the agw-mcp repository for installation and configuration instructions.
Complementary Skills
agw-mcp handles wallet execution. Pair it with these skills for domain knowledge:
| Need | Skill |
|---|---|
| Understand Abstract network config | connecting-to-abstract |
| Deploy contracts | deploying-contracts-on-abstract |
| Understand AGW architecture | abstract-global-wallet |
| Trade on Myriad markets | myriad-on-abstract |
| Understand gas sponsorship | abstract-global-wallet |
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 · 40 lines · 74 tokens per session scan A dd18e8382f6a
using-agw-mcp is a skill published in the GitHub repository Abstract-Foundation/abstract-skills (10 stars, last pushed 6mo ago), licensed MIT. It adds 74 tokens to every session and 464 once invoked, about $0.0004 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
bridge
Cross-chain token transfers using Wormhole and CCTP.
hyperliquid
Hyperliquid L1 perps DEX (69% market share).
mpp-agent
Pay HTTP 402 APIs via Machine Payments Protocol (MPP).
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…
trading-signal
Subscribe and retrieve on-chain Smart Money signals. Monitor trading activities of smart money addresses, including buy/sell signals, trigger price, current price, max gain, and exit rate. Use this skill when users are looking for investment opportunities — smart money signals can serve as valuable references for…