Kill switch + spend guard for AI agents that spend money, across every wallet vendor at once.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
We haven't yet run this listing's install command through our automated sandbox check. This isn't a red flag β we're steadily working through the catalog.
π‘ Paste the JSON block into your client's configuration file under mcpServers, then restart the application.
A neutral, cross-vendor control plane for AI agents that spend money. Countersign holds the policy, the freeze, and the audit ledger across multiple agent-wallet backends at once β the one thing no single wallet vendor can do, because each only governs its own rail. That aggregation is the moat.
Live version of this loop: countersign.network/demo.html Β· 60s video
One falsifiable test defines it: can Countersign freeze agents across many backends at once, in under a second, with a unified tamper-evident ledger of every attempt? Proven LIVE across four rails (Coinbase, Turnkey, Openfort, and a Lithic Visa card) in ~432ms on testnet.
This repository is the open-core front door β the Apache-2.0 packages you build against: the integration contract, the typed client, the MCP tools, and the x402 guard. The control-plane "brain" (the policy compiler, the hash-chained ledger, the vendor adapters, and the hosted Core) is separate and proprietary; you reach it over the network via the SDK/MCP, hosted at app.countersign.network.
Drop the kill switch + spend guard into any MCP client (Claude, Cursor, β¦) β one line:
Or wire it into your own agent with the SDK:
Get a free testnet key at https://app.countersign.network/start?ref=gh-readme.
Agents paying agents? See examples/guarded-payee β the A2A/AP2
pattern where a payee advertises it is governed and the payer verifies that (and guards its own
payment) before any mandate is signed.
| Package | Role |
|---|---|
@countersign/core | the EnforcementProvider interface, branded ids, the unified policy schema, the fail-closed freeze controller β the integration contract every backend implements |
@countersign/api-contract | OpenAPI + typed REST/ws schema β the single source of truth for the ClientβCore wire interface |
@countersign/sdk | typed client over the Core API + live ledger subscribe |
@countersign/mcp | Countersign as MCP tools β kill switch + spend guard inside any MCP client |
@countersign/x402 | govern x402 (HTTP-402 machine payments) β guard a payment before it pays |
@countersign/verify | verify a ledger entry offline β hash chain, RFC 6962 Merkle inclusion, Ed25519 signatures |
@countersign/ap2 | govern AP2 (Agent Payments Protocol) β guard an agent-payment mandate before it executes |
The proprietary brain (policy compiler to each backend's native controls, ledger, Coinbase / Turnkey / Openfort / Lithic adapters, the hosted Core) lives in a separate private repository.
EnforcementProvider interface.@countersign/sdk Β·
@countersign/mcp Β·
@countersign/x402 Β·
@countersign/ap2docs/architecture.md Β· Security: SECURITY.mdApache-2.0. Countersign holds policy, freeze, and a tamper-evident ledger β it never takes custody of funds.
No reviews yet β be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/countersign)<a href="https://allmcps.com/mcp/countersign"><img src="https://allmcps.com/api/badge/countersign?style=directory" alt="Countersign on AllMCPs" /></a>