# KARTA — spend control for AI agents (remote · karta.rta.lat)

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

- Trust score: 60/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

> **Recent critical change**: Authorization (2026-10-28). See the changelog below before you install this server.

## Components

- remote · `karta.rta.lat`: 60/100 (this document), [markdown](https://verifymcp.io/servers/lat-rta-karta-guard/karta.md), [page](https://verifymcp.io/servers/lat-rta-karta-guard/karta)

## Channel facts

- Endpoint: `https://karta.rta.lat/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 46/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (kill_envelope).
  - HTTPS enforcement could not be verified: the plaintext port answered with HTTP 406, which proves neither a plaintext path nor enforcement.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 63/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 447 tokens (~74/item across 6 items; 6 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 33/100
  - Stability observed for 10 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the KARTA — spend control for AI agents MCP server?

KARTA — spend control for AI agents is a hosted endpoint at https://karta.rta.lat/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

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

### Cursor

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

### VS Code

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

### Codex

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

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "lat-rta-karta-guard": {
      "type": "remote",
      "url": "https://karta.rta.lat/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add lat-rta-karta-guard --url 'https://karta.rta.lat/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  lat-rta-karta-guard:
    url: "https://karta.rta.lat/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "lat-rta-karta-guard": {
      "Transport": "http",
      "Url": "https://karta.rta.lat/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add lat-rta-karta-guard -t streamable-http -u 'https://karta.rta.lat/mcp'
```

### Other

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

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-04 (score 60, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 59, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-31 (score 58, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-29 (score 57, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-28 (score 56, +1)

- [critical regression] Authorization: unverified → fail
- [security] New tool “kill_envelope”, which the server declares destructive
- [functional improvement] Schema quality: 123 → 74
- [functional] Schema quality: fair → good
- [functional] Destructive annotations: pass → 100
- [functional] New tool “envelope_evidence”
- [functional] New tool “get_envelope”
- [functional] New tool “open_envelope”
- [functional] New tool “policy_rules”
- [cosmetic] Tool “check_spend” changed its title: Check a spend against a task envelope

### 2026-10-27 (score 55, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-26 (score 54)

First indexed and scored.

## MCP tools (6)

### `check_spend` (~87 tokens)

Check a spend against a task envelope

Check whether a proposed agent spend is inside a task envelope. Returns verdict, rule, reason, counterfactual and next. No state is stored.

Input parameters:

- `amount` (string, required)
- `calls_so_far` (integer)
- `envelope` (object, required)
- `is_subscription` (boolean)
- `payee` (string, required)
- `spent_so_far` (string)

Output parameters:

- `result` (string)

### `open_envelope` (~133 tokens)

Open a task 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.

Input parameters:

- `allow_new_payee` (boolean)
- `allow_subscriptions` (boolean)
- `allowlist`
- `approval_threshold`
- `budget_total` (string, required)
- `calls_max` (integer, required)
- `per_call_max` (string, required)
- `ttl_hours` (integer)

Output parameters:

- `result` (string)

### `get_envelope` (~44 tokens)

Read an envelope

Return an envelope's state: budget, per-call cap, calls used, spent, remaining, allowlist and expiry. Read-only.

Input parameters:

- `envelope_id` (string, required)

Output parameters:

- `result` (string)

### `kill_envelope` (~55 tokens)

Stop an 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.

Input parameters:

- `envelope_id` (string, required)
- `reason` (string)

Output parameters:

- `result` (string)

### `envelope_evidence` (~51 tokens)

Evidence pack for an envelope

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.

Input parameters:

- `envelope_id` (string, required)

Output parameters:

- `result` (string)

### `policy_rules` (~41 tokens)

List 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.

Output parameters:

- `result` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/lat-rta-karta-guard/karta#diagnostics

## Score history

- 2026-11-05: 60
- 2026-11-04: 60
- 2026-11-03: 59
- 2026-11-02: 59
- 2026-11-01: 58
- 2026-10-31: 58
- 2026-10-30: 57
- 2026-10-29: 57
- 2026-10-28: 56
- 2026-10-27: 55
- 2026-10-26: 54

## Common questions

### What is the KARTA — spend control for AI agents MCP server?

KARTA — spend control for AI agents is an MCP server listed in the public MCP registry as lat.rta.karta/guard. Task envelope, budget ledger, kill switch and signed receipts for agents that pay. This page covers its hosted endpoint (https://karta.rta.lat/mcp).

### Is the KARTA — spend control for AI agents MCP server safe to use?

KARTA — spend control for AI agents scores 60 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the KARTA — spend control for AI agents MCP server expose?

KARTA — spend control for AI agents exposes 6 tools: check_spend, open_envelope, get_envelope, kill_envelope, envelope_evidence, policy_rules. Their descriptions and schemas cost roughly 411 tokens of context every time the server is loaded.

### Does the KARTA — spend control for AI agents MCP server require authentication?

No. We connected to KARTA — spend control for AI agents without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the KARTA — spend control for AI agents MCP server still maintained?

KARTA — spend control for AI agents is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://karta.rta.lat/mcp
- Repository: https://github.com/mrpkk/onchain-ai-agent
- Changelog RSS feed: https://verifymcp.io/servers/lat-rta-karta-guard/karta.xml
- Changelog JSON feed: https://verifymcp.io/servers/lat-rta-karta-guard/karta.json
- HTML version of this page: https://verifymcp.io/servers/lat-rta-karta-guard/karta