Eclipse Agent Wallet MCP runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 29 Oct 2026.
Policy-scoped agent wallet: caps, recipient allowlist, human approvals, kill switch, audit trail.
What the code does
We read the source, 2 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
self.p = subprocess.Popen(
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Alternatives to Eclipse Agent Wallet MCP
same job, measured the same wayMCP policy proxy: spend caps, approvals for destructive tools, kill switch, dry-run, audit log.
Secure agent purchasing with human-approved virtual cards, receipts, and audit trails.
Governance proxy for MCP servers — policy evaluation, human approval, audit trails.
Human-in-the-loop review and approval for AI agents. Audit trail, approval policies, native MCP.
Intent-bound action authorization for AI agents: policy, human approval, and a signed audit trail.
Human-in-the-loop for AI agents over MCP: durable approvals with a hosted review page & audit trail
Run MCP tool calls through Runestone Gatekeeper — policy enforcement, human approval, audit.
Governed AI workflows with human approval gates and audit trails for Claude and MCP clients.
Eclipse Agent Wallet MCP — questions
Answers built from our own checks of this server.