# KARTA — spend control for AI agents

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

- name: lat.rta.karta/guard
- version: 0.1.0
- connection class: R0 (autonomous)
- trust: 92/100
- quality: 90/100 (strong)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/lat.rta.karta%2Fguard
- tools: https://api.protogrid.dev/v1/servers/lat.rta.karta%2Fguard/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

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


## Trust

- hygiene: 100
- liveness: 97
- freshness: 100
- provenance: 75
- drivers: +repository +dns-namespace +reachable +uptime-93% +updated-13d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 90/100 (strong)

### protocol: 88 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- warn `protocol.list_ttl`: tools/list declares ttlMs 0, so clients re-fetch it on every use

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 6 of 6 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 844 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 75 (weight 15)

- warn `stability.changes`: 6 tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 6, about 844 tokens to load them all
- tool set hash: df1a288a4c45e43dc906eb53d5daa301
- tools last changed: 2026-10-27T11:37:14.165Z
- badge: [![protogrid quality](https://protogrid.dev/badge/lat.rta.karta/guard.svg)](https://protogrid.dev/servers/lat.rta.karta/guard)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-27 `policy_rules` added
  - 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.
- 2026-10-27 `envelope_evidence` added
  - 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.
- 2026-10-27 `kill_envelope` added
  - Stop one task envelope immediately: no further spend is approved for it, the reason is recorded with a timestamp. Idempotent — the first reason wins.
- 2026-10-27 `get_envelope` added
  - Return an envelope's state: budget, per-call cap, calls used, spent, remaining, allowlist and expiry. Read-only.
- 2026-10-27 `open_envelope` added
  - 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.
- 2026-10-27 `check_spend` changed (title, annotations)

Full history: https://api.protogrid.dev/v1/servers/lat.rta.karta%2Fguard/changes

## Remotes

- https://karta.rta.lat/mcp (streamable-http, auth none, reachable true, uptime30d 0.9347826)

## Packages

_none_

## Tools (6)

- `check_spend`: Check whether a proposed agent spend is inside a task envelope. Returns verdict, rule, reason, counterfactual and next. No state is stored.
- `envelope_evidence`: 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`: Return an envelope's state: budget, per-call cap, calls used, spent, remaining, allowlist and expiry. Read-only.
- `kill_envelope`: 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`: 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`: 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.