OpenViSTAI · Agents · Blockchain · Crypto
Menu
MCP & Tooling

EmblemAI Agent Skills

EmblemAI Agent Skills is a public MIT-licensed repository of instructions and examples that help AI agents and developers build with EmblemAI’s crypto tools, including skills for swaps, portfolio tracking, DeFi, NFTs, agent wallets and application integrations.

Independent OpenViST project profile, based on linked sources.

EmblemAI Agent Skills — OpenViST project profile in MCP & Tooling.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use the repository when building with EmblemAI and you need skill-based guidance for a specific crypto workflow; consult its separate MCP instructions when the agent must call EmblemAI tools at runtime.

Who it is for

  • Developers adding EmblemAI capabilities to an application or agent.
  • Agent builders seeking guidance for crypto workflows across supported blockchains.
  • Users looking for the repository’s non-developer prompt and usage examples.

Documented uses

  • Install a focused skill or the full collection as agent authoring guidance.
  • Find instructions for crypto tasks such as token swaps, portfolio monitoring, DeFi yield and NFT workflows.
  • Connect a compatible agent client to EmblemAI’s hosted MCP server for runtime tool access.
  • Use React-focused guidance for authentication, wallet-enabled users and app integrations.
Before you choose

Requirements & limits

The repository is public and displays an MIT license. Its README provides `npx skills` installation instructions and separate hosted MCP setup instructions.

  • Skills are authoring guidance; runtime tool calls require a separate MCP server configuration.
  • The README lists seven networks: Solana, Ethereum, Base, BSC, Polygon, Hedera and Bitcoin.
  • The collection includes core integration skills and narrower workflow skills, including portfolio tracking, token swaps, market research and DeFi yield.
  • The README names Claude Code, Cursor, Codex and other agents following the Agent Skills specification as compatible with the collection.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install a selected EmblemAI skill

Add one skill from the repository to a local agent project.

Before you start

  • Node.js package runner npx
  • A project or agent workflow that uses Agent Skills

Steps

  1. Choose a skill name from the repository’s available skills list.

  2. Run the command below.

    Documented command
    npx skills add EmblemCompany/Agent-skills --skill 

Expected outcome

The selected skill is added through the skills installer for use as agent guidance.

Guide limitations

  • This installs authoring guidance, not runtime access to EmblemAI tools.
  • The repository does not document the local project’s subsequent agent-specific setup in the cited instructions.
Source-based practical guide

Connect Claude Code to EmblemAI through MCP

Configure Claude Code to connect to EmblemAI’s hosted MCP server.

Before you start

  • Claude Code
  • For the API-key route: an EmblemAI API key

Steps

  1. For browser OAuth, run claude mcp add --transport http EmblemAI https://emblemvault.ai/api/mcp.

  2. Follow the browser OAuth flow prompted by Claude Code; alternatively, configure the documented API-key route using the repository’s command and x-api-key header.

Expected outcome

Claude Code is configured to connect to the hosted EmblemAI MCP server using one of the documented authentication routes.

Guide limitations

  • The API-key command requires a key; the README describes the OAuth route as requiring no API key.
  • This configures MCP runtime access, separate from installing repository skills.
Evidence and transparency

Sources & review

Source record details
Source availability
Active
Sources checked
14 October 2026
Original website title
EmblemCompany/Agent-skills · Official homepage title · retained in its source language