Emblem AI

Emblem AI

Emblem Vault AI. Get a cross-chain wallet out of the box and do everything crypto with our terminal! Token discovery, swaps, cross-chain bridges, NFTs, prediction markets...

Category
访问服务器

README

EmblemAI Agent Skills

Official skill collection for AI agents building with EmblemAI. EmblemAI is open-source crypto infrastructure for both end users and AI agents: 200+ tools across 7 blockchains (Solana, Ethereum, Base, BSC, Polygon, Hedera, Bitcoin) for swaps, conditional orders, DeFi, NFTs, and cross-chain bridges, with x402 payment rails and A2A and MCP protocol support. Emblem is also the easiest way to add user management for apps that need wallet-native users: one integration can create authenticated users, give each user a full-featured crypto wallet, and support website login with wallets, email/password, and social sign-in. Compatible with Claude Code, Cursor, Codex, and other agents following the Agent Skills specification.

Available Skills

Core

Skill Description Install
emblem-ai EmblemAI developer tools for one-shot user management, wallet-enabled users, AI crypto tooling, React SDKs, and app introspection npx skills add EmblemCompany/Agent-skills --skill emblem-ai
emblem-ai-react React-focused EmblemAI integration skill for adding auth, wallet-enabled users, chat components, and Migrate.fun flows to an app npx skills add EmblemCompany/Agent-skills --skill emblem-ai-react
emblem-ai-agent-wallet Agent wallet CLI and browser auth across 7 blockchains, with wallet, email/password, and social sign-in options npx skills add EmblemCompany/Agent-skills --skill emblem-ai-agent-wallet
emblem-ai-prompt-examples Curated non-developer prompt and usage examples for EmblemAI wallet, market, trading, NFT, Bitcoin, prediction-market, vault, and assistant workflows npx skills add EmblemCompany/Agent-skills --skill emblem-ai-prompt-examples

Use Cases

Skill Description Install
emblem-portfolio-tracker Cross-chain portfolio monitoring, P&L tracking, and performance analytics npx skills add EmblemCompany/Agent-skills --skill emblem-portfolio-tracker
emblem-token-swap Guided token swapping with route optimization and slippage control npx skills add EmblemCompany/Agent-skills --skill emblem-token-swap
emblem-market-research Trending tokens, sentiment analysis, and market intelligence npx skills add EmblemCompany/Agent-skills --skill emblem-market-research
emblem-defi-yield DeFi yield farming, LP management, and staking across DEXs npx skills add EmblemCompany/Agent-skills --skill emblem-defi-yield
emblem-memecoin-scout Memecoin discovery, rug-pull detection, and trending new tokens npx skills add EmblemCompany/Agent-skills --skill emblem-memecoin-scout

Quick Install

# Install a specific skill
npx skills add EmblemCompany/Agent-skills --skill emblem-ai
npx skills add EmblemCompany/Agent-skills --skill emblem-ai-react
npx skills add EmblemCompany/Agent-skills --skill emblem-ai-agent-wallet
npx skills add EmblemCompany/Agent-skills --skill emblem-ai-prompt-examples

# Install all skills
npx skills add EmblemCompany/Agent-skills

# List available skills
npx skills add EmblemCompany/Agent-skills --list

Install EmblemAI as an MCP server

The skills above are authoring guidance. If you want your agent to actually call EmblemAI tools at runtime, install the hosted MCP server in your MCP-compatible client.

Claude Code (OAuth, no API key)

claude mcp add --transport http EmblemAI https://emblemvault.ai/api/mcp

Claude Code walks you through the hosted OAuth flow in your browser. No secret to paste.

Claude Code (API key, for headless / CI)

claude mcp add --transport http EmblemAI https://emblemvault.ai/api/mcp \
  --header "x-api-key: YOUR_API_KEY"

GitHub Copilot CLI / .mcp.json

{
  "mcpServers": {
    "emblemai": {
      "type": "http",
      "url": "https://emblemvault.ai/api/mcp",
      "headers": { "x-api-key": "YOUR_API_KEY" }
    }
  }
}

Full install matrix (Claude Desktop bridge, Cursor, Windsurf, Gemini CLI): https://emblemvault.ai/docs/mcp

What EmblemAI enables

For AI agents and developers:

  • 200+ tools across 7 blockchains covering swaps, conditional orders, DeFi positions, NFT operations, cross-chain bridges, and market intelligence.
  • x402 facilitator and per-call payment rails for agent-to-agent commerce without account setup.
  • Native MCP (Model Context Protocol) server for Claude Code, GitHub Copilot, Gemini CLI, and other MCP clients.
  • A2A (Agent-to-Agent) protocol support for direct agent interoperability.
  • Deterministic wallets — one password produces one persistent agent identity across all chains. Every wallet-modifying action requires explicit approval.

For end users and wallet-native apps:

  • The easiest way to do user management for wallet-native apps: one integration can create website users who also have full-featured crypto wallets.
  • Flexible login: users can sign in with many crypto wallets, email/password, or social login.
  • The easiest way to give an agent a crypto wallet: Emblem's agent wallet CLI can create or restore a wallet-enabled identity in one command.
  • One session, more capability: the same Emblem session can power authentication, wallet access, transaction signing, and AI-driven crypto workflows.

Skill Structure

Each skill follows the Agent Skills specification:

skills/<skill-name>/
├── SKILL.md              # Required — skill instructions + metadata (recommended <500 lines)
├── references/           # Optional — detailed documentation by topic
├── scripts/              # Optional — executable helpers
├── assets/               # Optional — config templates, schemas
└── examples/             # Optional — sample outputs

Adding Skills

See CONTRIBUTING.md for guidelines on adding new skills.

Registry Compatibility

The publishable SKILL.md files in this repo intentionally stay within the public Agent Skills frontmatter defined at agentskills.io/specification: name, description, and the optional license, compatibility, metadata, and allowed-tools fields.

That keeps these skills portable across agentskills.io / agentskills.to compatible tooling instead of relying on vendor-only top-level fields.

The public docs we found describe a repo-based sharing and install flow rather than a documented manual “add skill” form in the web UI. In practice, keep the skill in git, validate it with the official CLI, and share or install it from the repository.

Validation

# Install the official validator
python -m pip install skills-ref==0.1.1

# Validate one skill with the official CLI
agentskills validate skills/emblem-ai-agent-wallet

# Validate all skills in this repository
bash validate-all.sh

# Validate one skill with the repo wrapper
bash validate-skill.sh emblem-ai-agent-wallet

The upstream agentskills validate command validates one skill directory at a time, not the top-level ./skills folder. This repository's validate-all.sh wrapper loops through skills/*/, syncs shared EmblemAI reference sources into skill-local copies, and then runs repository-specific markdown/link checks.

The legacy --strict flag is still accepted by the wrapper scripts for backwards compatibility, but it no longer changes behavior because the official validator is spec-compatible by default.

Pull requests install the official skills-ref validator in CI and run the repository wrapper so public skill frontmatter stays spec-compatible.

CI also fails if the sync step rewrites generated files under skills/, which prevents uncommitted shared-reference updates from slipping through.

Shared Sources

Some reference docs are intentionally repeated across publishable skills. Those repeated files are not meant to be edited in place under skills/.../references/.

The rule is:

  • edit the canonical source under shared/
  • run bash validate-all.sh or bash validate-skill.sh ...
  • let the sync step regenerate the skill-local copies

Current shared sources:

  • shared/emblem-ai-prompt-examples.md
  • shared/emblem-ai-prompt-examples/
  • shared/emblem-ai-react-references/

Current generated skill-local copies:

  • prompt examples copied into emblem-ai, emblem-ai-react, emblem-ai-agent-wallet, and emblem-ai-prompt-examples
  • React references copied into emblem-ai and emblem-ai-react

The sync entrypoint is utils/sync-emblem-ai-shared-references.sh.

If a reference file is duplicated across multiple skills, move it into shared/ and sync it back into each standalone skill instead of maintaining separate manual copies.

Validation also runs automatically on every PR via GitHub Actions.

About EmblemAI

EmblemAI provides 200+ autonomous trading tools across 7 blockchains (Solana, Ethereum, Base, BSC, Polygon, Hedera, Bitcoin). Open source and available as an npm CLI, an MCP server, and an A2A-compatible agent.

License

MIT

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选