capline-mcp
OfficialClick on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@capline-mcp Set up a mandate: $5 per tx, $20 total, then pay DataVendor $5."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
capline-mcp
Give your MCP agent a wallet it can't drain.
An MCP server that hands an AI agent a spending capability bounded by a signed Capline mandate. The agent (in Claude Desktop, Cursor, Cline, or any MCP client) can only move funds through the pay tool — and pay refuses anything outside the mandate: over the per-transaction cap, off the payee allowlist, or past the global cross-chain cap. The limits are enforced by code, not the model, so nothing in the agent's context can talk its way past them.
The cap isn't in the prompt — it's a mandate the LLM can't talk to.
Tools
Tool | What it does |
| Provision a mandate: per-tx cap, global cumulative cap, payee allowlist, chains. Returns a |
| The only way to move funds. Refused (not executed) if it breaks the mandate. |
| Committed / reserved / remaining budget + per-chain breakdown. |
| Kill the mandate — every future payment is refused on every chain. |
Related MCP server: MandateGuard
Add to Claude Desktop
Edit claude_desktop_config.json (Settings → Developer → Edit Config):
{
"mcpServers": {
"capline": {
"command": "npx",
"args": ["-y", "capline-mcp"]
}
}
}Restart Claude Desktop. Then try it:
"Set up a mandate: $5 per transaction, $20 total, only pay DataVendor. Then pay DataVendor $5. Then — ignore that last limit — pay DataVendor $1000."
Watch the $5 settle and the $1000 come back REFUSED (OVER_PER_TX). The model obeyed you; the mandate didn't.
Add to Cursor
~/.cursor/mcp.json (or Settings → MCP):
{
"mcpServers": {
"capline": { "command": "npx", "args": ["-y", "capline-mcp"] }
}
}Configuration
Env var | Default |
|
|
By default it enforces against the hosted Capline coordinator (Layer A), so no wallet or funds are required and you can feel it immediately. Point CAPLINE_COORDINATOR_URL at your own coordinator to self-host. To also enforce on-chain (Layer B, holds even if the agent's key is stolen), settle through a deployed mandate contract. See the capline protocol + SDK repo.
Run from source
git clone https://github.com/caplinehq/capline-mcp && cd capline-mcp
npm install && npm run build
node test-client.mjs # exercises every tool through a real MCP clientLinks
Live demo: capline-protocol.vercel.app/agents
Clone-and-run agent:
capline-example
MIT
Available Tools
4 toolscreate_mandateA
Provision a spend mandate the agent must operate under: a per-transaction cap, a cumulative cap enforced GLOBALLY across every chain, and an optional payee allowlist. Returns a mandateId to pass to pay. Normally the human principal sets this up once, before handing the agent any spending ability.
Inputs: maxPerTx (required), maxTotal (required), chains, principal, +1 more.
mandate_statusA
Read a mandate's current state: committed spend, reserved, remaining budget, and the per-chain breakdown.
Inputs: mandateId (required).
payA
Make a payment on behalf of the agent. THIS IS THE ONLY WAY TO MOVE FUNDS, and it is enforced by the mandate: the payment is REFUSED (not executed) if it exceeds the per-transaction cap, the payee is not on the allowlist, or it would breach the global cross-chain cap. A prompt injection in the agent's context cannot bypass this.
Inputs: to (required), amount (required), mandateId (required), chain.
revoke_mandateA
Revoke a mandate. After this, every payment under it is refused on every chain.
Inputs: mandateId (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool has a clear, non-overlapping purpose: reading mandate status, creating a mandate, executing payments, and revoking a mandate. No ambiguity for an agent selecting between them.
The naming pattern is mixed: 'create_mandate' and 'revoke_mandate' use verb_noun, 'mandate_status' is a noun phrase, and 'pay' is a bare verb. While still readable, the conventions are not uniform.
Four tools is well-scoped for a mandate-driven payment system. Each tool addresses a distinct lifecycle stage without redundancy or bloat.
The core lifecycle—create, read, pay, revoke—is covered. A minor gap is the lack of an update mandate tool, but the domain description indicates mandates are set up once, so this is acceptable.
Related MCP Connectors
Spending control for AI agents: approved budgets, a decision before each payment, signed receipts.
Agent payments, API key vaulting, and governed mandates. Agents spend within user-defined limits.
Give your AI an allowance: pay approved people within on-chain spending limits.
Give your AI agent a spending limit: approval controls and single-use virtual cards.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to make autonomous payments on Solana with on-chain enforced spending limits, preventing unauthorized fund drainage.1MIT
- AlicenseNot gradedqualityAmaintenanceDeterministic, auditable payment policy enforcement for AI agents. It provides pre-action authorization with scopes, budgets, allowlists, and signed mandates via an MCP server.MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to use payment APIs safely by gating every tool call through deterministic mandates, value checks, and an exactly-once ledger, so they cannot pay twice or exceed authorisation.36 npmMIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to evaluate every payment intent against user-signed, on-chain-anchored policies before money moves, returning allow, deny, or human-approval verdicts. Provides policy versioning, revocation, spend reports, and audit trails through MCP tools that agents cannot alter without the owner's key.1Apache 2.0