PulseChain MCP server for AI agents: chain reads, markets, swap quotes, and encrypted wallets
An MCP server that lets AI agents work with PulseChain and encrypted agent wallets.
You can give your AI agent its own PLS and other tokens in a local wallet it controls.
Sending PLS and swaps on PulseX/Piteas have been successful.
Version 1.0.1 · MCP TypeScript SDK 2.0.0 (stable) · dual-era 2026-07-28 + 2025-11-25
- PulseChain data and market research - Smart contract reviews and creation - Swap quotes/prices and executions - Encrypted agent wallets — send PLS and other tokens to a wallet your agent can control
- AI Agent starts with zero PLS and is in "Research Only Mode" until you fund it's wallet. Sending PLS to your agent is optional, if you do be smart and start small. - Kill switch command can disable the wallet - Encrypted keys at rest (AES-256-GCM) - Unique wallet directory per process - Don't give your agent more coins than you are willing to lose, agents make mistakes just like humans
1. Install Node.js 20+ if needed or have your agent do it. 2. Clone this repo and open it in your AI app (Cursor, Claude, Grok, Codex, …) or have your agent do it. 3. Ask your AI agent to finish setup — paths, master key or research-only mode, reload, and smoke checks.
You do not need to learn MCP, RPC, or wallet cryptography. The agent does it for you.
Optional one-liner if the agent has not cloned yet:
Start here → docs/BOOTSTRAP.md (ordered checklist: build → client example → paths → wallets → reload → smoke → next docs)
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/DavidFeder--pulsechain-mcp.html)
Open-source control plane for Codex projects: Git-backed context, visible agent progress, scoped MCP access, resumable work, and safe handoffs.
abluva/mcp-remoteThe bridge for remote MCP — seamless OAuth, resilient auth recovery, production-grade reliability
anshupriyan/cli-bridgeMCP server for Claude Desktop and other Model Context Protocol clients — sandboxed filesystem access (read/write/edit/search) plus Dev Mode-gated shell command execution, scoped to a single workspace
sgateway/s-gwLocal credential control for AI coding agents.
luckeyfaraday/frontier-orchestratorMulti-agent orchestration for Claude Code: MCP server + skill that keeps Claude as lead engineer while delegating backend work to OpenAI Codex and frontend/design work to Kimi
xfloukiex-lab/pandaclipOne local-first MCP server for agent working state — clipboard history & snippets, TTL cache, file-organizer overlay, and a knowledge graph — plus a live desktop activity lens. 40 tools, SQLite everyw
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.