By stakewise
Ask natural-language questions in any language about StakeWise V3 staking data on Mainnet and Gnosis — APY, vault TVL, your stake or earnings, exit-queue ETA, osETH/osGNO mint capacity or health factor, boost position, leverage borrow LTV, distributor claims, vesting positions, transaction history, exchange rates, or sub-vaults. Read-only; talks to public StakeWise subgraphs and backend GraphQL via WebFetch / curl. No SDK install or local server required.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Real-time StakeWise protocol data for AI assistants. Query vault APYs, user balances, staking rewards, osETH positions, withdrawal queues, and more — directly from the model.
This repo ships two ways to query StakeWise from an LLM:
MCP server (@stakewise/llm-tools on npm) — heavy path with 10 live tools, in-memory state, slash commands. Best when your environment has Node.js + a MCP-compatible client (Claude Code, Cursor, Codex, OpenClaw). Lives in mcp-server/.
stakewise-data-query skill — lightweight path. No Node, no npx, no local server. Just markdown that instructs any LLM to query the public StakeWise subgraphs directly via WebFetch / curl. Works in Claude Code (plugin install) and in browser ChatGPT, Perplexity, DeepSeek, Cursor without MCP, anywhere markdown can land in a context window. Lives in data-skill/.
Use this when you want any LLM to answer StakeWise questions, including environments without Node/MCP.
/plugin marketplace add stakewise/llm-tools
/plugin install stakewise-data-query@stakewise-llm-tools
The skill activates automatically when the user asks about StakeWise APY, balances, exit queue, osETH health, boost, claims, vesting, etc.
Paste this URL into the system prompt, Custom GPT instructions, Perplexity Space Source, or Cursor @-mention:
https://raw.githubusercontent.com/stakewise/llm-tools/main/data-skill/llm-context.md
That single file is the whole skill (operational rules plus full entity reference inline). The LLM gets everything it needs to build correct GraphQL queries against graphs.stakewise.io/{mainnet,gnosis}/... and read the response.
Use this when your environment has Node + an MCP-compatible client and you want the model to call typed tools with live state (saved address, slash commands).
OpenClaw's api.registerTool does not reliably expose MCP tools to the model. This plugin works around the issue by running a local HTTP server on port 5165 and using a skill file that instructs the model to call endpoints via curl.
Install the plugin:
openclaw plugins install clawhub:stakewise-llm-tools
Allow the model to execute curl against the local server:
openclaw config set tools.exec.security full
openclaw config set tools.exec.ask off
See openclaw#25652 for background on why this is required.
Restart the gateway and start a new conversation:
openclaw gateway restart
Then type /new in the chat to begin a fresh session with the plugin loaded.
Requires tsx installed globally:
npm i -g tsx
Create a .mcp.json file in the root of any project where you want to use these tools:
{
"mcpServers": {
"stakewise-llm-tools": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@stakewise/llm-tools"]
}
}
}
Restart Claude Code to apply.
Go to Settings → Tools & MCPs → New MCP Server, and add to the opened mcp.json:
{
"mcpServers": {
"stakewise-llm-tools": {
"command": "npx",
"args": ["-y", "@stakewise/llm-tools"]
}
}
}
Add to .codex/config.toml in your project root:
[mcp_servers.stakewise-llm-tools]
command = "npx"
args = ["-y", "@stakewise/llm-tools"]
| Tool | Description | Requires address |
|---|---|---|
save_address | Save user wallet for subsequent queries | No |
vaults_list | All StakeWise vaults sorted by APY | No |
vault_data | Public vault info (APY, fee, capacity, osETH config) | No |
vault_stats | Historical vault performance (daily APY, TVL, rewards) | No |
vault_whitelist | Whitelist for a private vault | No |
staked_vaults | All vaults where the user has a position | Yes |
vault_balance | User's detailed position in a specific vault | Yes |
vault_queue | Unstake & unboost queue status | Yes |
user_stats | User's personal earnings history in a vault | Yes |
created_vaults | Vaults administered by the user | Yes |
npx claudepluginhub stakewise/llm-tools --plugin stakewise-data-queryComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
UI/UX design intelligence. 67 styles, 161 palettes, 57 font pairings, 25 charts, 15 stacks (React, Next.js, Vue, Svelte, Astro, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Nuxt, Jetpack Compose). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.
This skill should be used when users need to generate ideas, explore creative solutions, or systematically brainstorm approaches to problems. Use when users request help with ideation, content planning, product features, marketing campaigns, strategic planning, creative writing, or any task requiring structured idea generation. The skill provides 30+ research-validated prompt patterns across 14 categories with exact templates, success metrics, and domain-specific applications.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.