MCP server

KARTA — spend control for AI agents

lat.rta.karta/guard

Checked 26 Oct 2026, 08:29 UTC · Connected to it and listed its tools

Task envelope, budget ledger, kill switch and signed receipts for agents that pay.

Working at last checkVerified publisher: rta.latAbout 890 tokens per request once connected6 tools

https://karta.rta.lat/mcp

At a glance

Type: MCP server
Publisher: rta.lat (verified by the MCP Registry)
Status: Working at last check
Tools: 6
Token cost: About 890 tokens per request
Sets up in: Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok
Last checked: 26 Oct 2026, 08:29 UTC

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

claude mcp add --transport http guard https://karta.rta.lat/mcp

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

[mcp_servers.guard]
url = "https://karta.rta.lat/mcp"

Gemini CLI

{"mcpServers":{"guard":{"httpUrl":"https://karta.rta.lat/mcp"}}}

Cursor

{"mcpServers":{"guard":{"url":"https://karta.rta.lat/mcp"}}}

VS Code

{"servers":{"guard":{"type":"http","url":"https://karta.rta.lat/mcp"}}}

Antigravity

agy mcp add guard https://karta.rta.lat/mcp

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"guard","server_url":"https://karta.rta.lat/mcp","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"guard","server_url":"https://karta.rta.lat/mcp"}

check_spend ~194 tokens
Check whether a proposed agent spend is inside a task envelope. Returns verdict, rule, reason, counterfactual and next. No state is stored.
envelope_evidence ~106 tokens
Return an evidence bundle for one envelope: state, every recorded spend, the stop record and a sha256 of the whole pack that anyone can recompute. Read-only.
get_envelope ~90 tokens
Return an envelope's state: budget, per-call cap, calls used, spent, remaining, allowlist and expiry. Read-only.
kill_envelope ~120 tokens
Stop one task envelope immediately: no further spend is approved for it, the reason is recorded with a timestamp. Idempotent — the first reason wins.
open_envelope ~304 tokens
Create a signed budget envelope for one task: total budget, per-call cap, call count, allowlisted payees, subscription rule, expiry. Stores it in this server's local ledger (no funds move, no keys). Returns the envelope id. Capped at 30 envelopes/hour per server.
policy_rules ~76 tokens
List the deterministic rules a spend is checked against (E01-E08) with the order they are applied and the meaning of each. Read-only, no state.

Run Budget Guard
Hard dollar, token, call and time caps shared by every sub-agent in one agent run.
AstraNL Crossing
Look before work, claim it, check a spend, mark the outcome. For agents sharing tasks. No key.
Privi Quantum Ledger
Quantum-sealed audit logs for AI agents (ML-DSA-87, SHA3-512), plus Privi Guard and trust passports.
Agent Spend Guard — owner-set purchasing guardrails
Free spend guardrails for AI agents: approve/deny/ask_user, caps, dupes.
Relayzero
Agent economy on Solana — USDC via x402. Ships a BuyerAgent SDK + relayzero pay CLI.
ZeroWidth Workbench
Build, run and publish Workbench flows, tasks, shims and knowledge bases.
AgentLedger
Meter, cap, and block AI agent spend before the provider is charged.
Vino & Views
Free reports, EVM/Solana token payment links and capped zero-fee EVM USDC escrow. Wallet signatures.

[![AptLynx](https://aptlynx.net/badge/lat.rta.karta/guard.svg)](https://aptlynx.net/servers/lat.rta.karta/guard)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents