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 PaulieB14/graph-uniswap-mcp --skill graph-uniswapgit clone --depth 1 https://github.com/PaulieB14/graph-uniswap-mcpWrote 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/paulieb14/graph-uniswap-mcp/graph-uniswap)<a href="https://agentmods.dev/skills/paulieb14/graph-uniswap-mcp/graph-uniswap"><img src="https://agentmods.dev/badge/skills/paulieb14/graph-uniswap-mcp/graph-uniswap/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/paulieb14/graph-uniswap-mcp/graph-uniswap"><img src="https://agentmods.dev/badge/skills/paulieb14/graph-uniswap-mcp/graph-uniswap.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 | $0.00120 | $0.01044 |
| Opus 5.5 | $0.00048 | $0.00418 |
| Sonnet 5.5 | $0.00024 | $0.00209 |
| Haiku 4.5 | $0.00012 | $0.00104 |
Grade A, and why
graph-uniswap 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 2mo 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Graph Uniswap
Answer Uniswap questions with live subgraph data — and, uniquely, answer "what would this trade actually cost me?" without an RPC, a node, or a private key.
Setup
Needs a free Graph API key (https://thegraph.com/studio, 100k queries/month free) in
GRAPH_API_KEY. The server runs over stdio via npx -y graph-uniswap-mcp.
Picking a tool
| The user is asking… | Use |
|---|---|
| "how much would I get for X", "what's the slippage/price impact", "is this pool deep enough" | quote_swap |
| "what's WETH worth", "price of X" | get_token_price |
| "best pools on ", "most active pools" | top_pools |
| "the USDC/WETH pool", "which fee tier" | find_pool |
| "stats for this pool" | pool_info |
| "recent trades", "who is trading" | recent_swaps |
| "what chains/versions are supported" | list_markets |
| anything the above cannot express | raw_query |
Typical flow for a trade question: find_pool → pick the pool → quote_swap.
quote_swap — the one to reach for
Simulates an exact-input swap against the pool's real tick liquidity.
quote_swap pool=0x8ad5…e6d8 tokenIn=WETH amountIn=100 chain=ethereum version=v3
→ amount_out 223661.14 USDC · effective_price 2236.61 · price_impact_pct 0.6291 · ticks_crossed 2
price_impact_pct is measured against the fee-adjusted spot, so it isolates depth rather than
restating the fee. fee_pct is reported separately.
Always check quotable. When it is false, report the reason — do not substitute a guess
or fall back to a TVL figure. It refuses on:
- V4 pools with a hook — hooks can override fee and curve, so vanilla math would be wrong. On Base the top V4 pools by volume are hook-driven.
- Trades bigger than the visible liquidity — you get
lower_bound_amount_out, not a quote. Suggest splitting the trade, or quoting on-chain. - Zero in-range liquidity, or a deployment exposing no
ticks(V3 on Base).
The number simulates the most recently indexed block. Real execution depends on state at inclusion — say so when the amount is material. It is single-pool: not a router, no multi-hop, no splitting.
What ships with it
1 file 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.
- 2mo ago First seen · 79 lines · 120 tokens per session scan A 8954b9dd342a
graph-uniswap is a skill published in the GitHub repository PaulieB14/graph-uniswap-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 120 tokens to every session and 1,044 once invoked, about $0.0005 per session on Opus 5.5. 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.
graph-uniswap compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| graph-uniswapPaulieB14/graph-uniswap-mcp | Skill | 0 | 2mo ago | MIT | A | 120 | Claude Code, Codex |
| hyperliquidalsk1992/CloddsBot | Skill | 3.1k | yesterday | MIT | A | 19 | Claude Code, Codex |
| bridgealsk1992/CloddsBot | Skill | 3.1k | yesterday | MIT | A | 13 | Claude Code, Codex |
| marginfialsk1992/CloddsBot | Skill | 3.1k | yesterday | MIT | A | 11 | Claude Code, Codex |
| agentic-streetLeoYeAI/openclaw-master-skills | Skill | 2.2k | 6d ago | MIT | A | 91 | Claude Code, Codex |
| token-pickaeonfun/aeon | Skill | 789 | 2d ago | MIT | A | 25 | Claude Code, Codex |
| airdrop-hunting-guidenirholas/three.ws | Skill | 269 | yesterday | Apache-2.0 | A | 54 | Claude Code, Codex |