szhygulin/vaultpilot-mcp
by Various
Safety first. Hardware-verified DeFi for AI agents — designed for when the AI can be compromised.
MCP
szhygulin/vaultpilot-mcp
Added 1 June 2026
Overview
An open-source TypeScript MCP server that provides hardware-verified DeFi operations for AI agents. It is designed to protect funds even if the AI agent itself is compromised, using hardware-level security guarantees.
Best for
Best for
Developers building AI agents for DeFi who need high-assurance security against agent compromise.
Use cases
- Secure automated DeFi trading and vault management by AI agents
- Reduce trust assumptions when delegating financial operations to LLM-based agents
- Protect protocol interactions against compromised or adversarial AI behavior
Notes
An open-source TypeScript MCP server that provides hardware-verified DeFi operations for AI agents. It is designed to protect funds even if the AI agent itself is compromised, using hardware-level security guarantees.
3 stars on GitHub. Last updated 2026-05-26.
Use cases
- Secure automated DeFi trading and vault management by AI agents
- Reduce trust assumptions when delegating financial operations to LLM-based agents
- Protect protocol interactions against compromised or adversarial AI behavior
Pros
- Hardware verification adds a strong security layer beyond typical software-only defenses
- Open source and written in TypeScript, making it accessible for integration
- Specifically designed for the scenario where the AI agent is compromised, addressing a key risk
Cons
- Very low community traction (3 stars) suggests limited testing and adoption
- Hardware verification may require specific trusted execution environment support, adding deployment complexity
- Likely narrow scope focused only on DeFi, not general agent security
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Hardware verification adds a strong security layer beyond typical software-only defenses
- Open source and written in TypeScript, making it accessible for integration
- Specifically designed for the scenario where the AI agent is compromised, addressing a key risk
Cons
- Very low community traction (3 stars) suggests limited testing and adoption
- Hardware verification may require specific trusted execution environment support, adding deployment complexity
- Likely narrow scope focused only on DeFi, not general agent security
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
Claude Code
Anthropic
Anthropic's terminal-native coding agent. Reads your repo, edits files, runs tests, ships PRs.
Cline
Cline
Open-source autonomous coding agent that lives inside VS Code. BYO model key, watch it work.
Cursor
Anysphere
The AI-first code editor. Tab to autocomplete, Composer to multi-file refactor, Agents for the long-running stuff.
Aider
Paul Gauthier
Terminal-first AI pair programmer. Edits files in your repo, commits with sensible messages, runs your tests.
FastMCP
Various
🚀 The fast, Pythonic way to build MCP servers and clients.
browsermcp/mcp
Various
Browser MCP is a Model Context Provider (MCP) server that allows AI applications to control your browser
agent-infra/mcp-server-browser
Various
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra