Skip to content

KARTA — spend control for AI agents MCP server

lat.rta.karta/guardkarta.rta.latstreamable-httpv0.1.0Scanned

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

6 tools: 1 can delete or cancel things, 2 change things and 3 only read.

Tools: 1 delete, 0 irreversible, 2 write, 3 read.
  • Reads private data · 0
  • Reads text others write · 0
  • Can send data out · 0
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here can delete or cancel things. Govern it.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the KARTA — spend control for AI agents MCP server can do

The KARTA — spend control for AI agents MCP server is published by karta.rta.lat, a domain the MCP Registry verified. It has 6 tools. It can delete or cancel things (1 tool: kill_envelope) and create or change data (2 tools: check_spend and open_envelope). 3 tools only read.

None of its tools reads private data, brings in text other people write, or sends data out.

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.

Last scanned Nov 9, 2026, version 0.1.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

6 tools

Deletes or cancels 1Claude Code: deny
  • kill_envelopeStop one task envelope immediately: no further spend is approved for it, the reason is recorded with a timestamp.No findings

    Why it is in this group

    • The name "kill_envelope" says "kill": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Stop one task envelope immediately: no further spend is approved for it, the reason is recorded with a timestamp. Idempotent — the first reason wins.

    Annotations the server declares

    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: false
Changes things 2Claude Code: ask
  • check_spendCheck whether a proposed agent spend is inside a task envelope.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Check whether a proposed agent spend is inside a task envelope. Returns verdict, rule, reason, counterfactual and next. No state is stored.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
  • open_envelopeCreate a signed budget envelope for one task: total budget, per-call cap, call count, allowlisted payees, subscription rule, expiry.No findings

    Why it is in this group

    • The name "open_envelope" says "open": a word for a change.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • readOnlyHint: false
Only reads 3Show 3 read-only tools
  • envelope_evidenceReturn an evidence bundle for one envelope: state, every recorded spend, the stop record and a sha256 of the whole pack that anyone can recompute.No findings

    Why it is in this group

    • The description's first verb is "return": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
  • get_envelopeReturn an envelope's state: budget, per-call cap, calls used, spent, remaining, allowlist and expiry.No findings

    Why it is in this group

    • The name "get_envelope" says "get": a word for reading.
    Description, as the server wrote it
    Return an envelope's state: budget, per-call cap, calls used, spent, remaining, allowlist and expiry. Read-only.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
  • policy_rulesList the deterministic rules a spend is checked against (E01-E08) with the order they are applied and the meaning of each.No findings

    Why it is in this group

    • The description's first verb is "list": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 17, 2026, 15:24 UTC, unchanged since Nov 3, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
3
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 3 tools that change things (1 destructive, 2 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://karta.rta.lat/mcp: tools/list returned 6 tools to an anonymous client, including kill_envelope (destructive), check_spend (write), open_envelope (write)

    What this check looks for

Posture changes

  1. Nov 3, 2026
    • Tools that change things, listed without credentials: 1 to 3

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools5 added, 1 changed.+5 added~1 changedView diff
  2. PostureRemote posture changed. Tools that change things, listed without credentials: 1 -> 3.View diff
    • Tools that change things, listed without credentials: 1 to 3

Install

Pinned to version 0.1.0. Values in angle brackets are yours to fill in.

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

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__guard__get_envelope",
      "mcp__guard__envelope_evidence",
      "mcp__guard__policy_rules"
    ],
    "ask": [
      "mcp__guard__check_spend",
      "mcp__guard__open_envelope"
    ],
    "deny": [
      "mcp__guard__kill_envelope"
    ]
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as guard. Review it before you use it.

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/lat.rta.karta/guard/verify?hash=af052d6a643cc0eb424cc656bf98cdf3afba7eadd4c4f1901c00bbadc761e705" | jq -e '.changed == false'

Pinned hash af052d6a643c, from Nov 9, 2026, 08:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/lat.rta.karta/guard/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for lat.rta.karta/guard
[![Anlyon Radar](https://radar.anlyon.com/badge/lat.rta.karta/guard.svg)](https://radar.anlyon.com/servers/lat.rta.karta/guard)

Source: MCP Registry · repository. Synced Oct 26, 2026, 05:17 UTC.

KARTA — spend control for AI agents MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

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

No scan can promise that. What its definitions show: 6 tools, 3 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the KARTA — spend control for AI agents MCP server delete data?

Yes. 1 tool can delete, cancel or revoke something: kill_envelope.

Can the KARTA — spend control for AI agents MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

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

6 tools: 1 destructive, 2 write, 3 read. kill_envelope, check_spend, open_envelope, get_envelope, envelope_evidence and policy_rules.

Does the KARTA — spend control for AI agents MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the KARTA — spend control for AI agents MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the KARTA — spend control for AI agents MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 9, 2026. Every change is on this page and in its Atom feed.