SolidInvoice
Create and send invoices and quotes, manage clients, and track payments in SolidInvoice.
Task envelope, budget ledger, kill switch and signed receipts for agents that pay.
This one is in the “Apps that connect to AI” tab, which is ordered without stars, in this order
| 1. In Claude’s connector directory | No | |
|---|---|---|
| 2. Tried by our team | No | |
| 3. Works for Thai users | No | |
| 4. Usage without stars | 20/100 | Popularity 0 · Freshness 12 · Still answering 8 · Likes from users +0 |
| 5. Listed on | 2026-10-26 |
Likes from users: 0 · Adds at most 5 points to the order (1 per person). It cannot be bought.
Quality: Passed 3/5 basic checks (shown, not used for ordering)
Pick the AI app you use, then copy the settings.
Let your AI install it with one sentence
Please install KARTA — spend control for AI agents. Follow https://mcp.popnx.com/i/lat-rta-karta-guard.md, show me the commands and wait for my OK before running them.Paste it into an AI that can work on your computer (such as Claude Code or Cursor). It reads our steps, shows you the commands and waits for your OK. No key, no sign-up. · See the full text your AI reads
Passed 3/5 checks · What you ask goes through the maker’s server (karta.rta.lat) · ✓ Commands checked Nov 13, 2026
First: which AI do you use?
Pick your app and the steps appear below.
Works with Claude · about 2 min
No key, nothing to install · Set it up once on claude.ai or the desktop app, then use it in chat · free accounts can add 1 · on Team/Enterprise an Owner adds it
CustomizeConnectors
Copy each value into the field with the same name in Claude, then click Continue
KARTA — spend control for AI agentshttps://karta.rta.lat/mcpClick Continue past the sign-in settings Claude detected · under Authentication choose what the maker says (Sign in now, Sign in when needed or No sign in), then click Add
+ConnectorsKARTA — spend control for AI agents
Use KARTA — spend control for AI agents and tell me what you can do for me, then show me one thing✓ If Claude says it is using KARTA — spend control for AI agents or shows a KARTA — spend control for AI agents tool in the answer, you are connected
Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version
Works with ChatGPT, depending on your plan
Full MCP: ChatGPT Business, Enterprise or Edu on the web · Pro: connects with read/fetch permissions, so tools that change data may not work · Plus: not confirmed in OpenAI’s docs; if you see an add-custom-MCP option on the Plugins page you can try these steps · web only
Plugins+Add custom MCP server
Enter a name, paste the address under Connection, tick the risk warning and click Create as a plugin
KARTA — spend control for AI agentshttps://karta.rta.lat/mcpStart a new chat and pick KARTA — spend control for AI agents from your plugins before typing
Use KARTA — spend control for AI agents and tell me what you can do for me, then show me one thing✓ If ChatGPT says it is using KARTA — spend control for AI agents or shows a KARTA — spend control for AI agents tool in the answer, you are connected
Menu names checked against OpenAI’s help page on Nov 11, 2026 · your screen may differ slightly by app version
Works with Claude Code · about 2 min
No key, nothing to install
Mac: press Command+Space and type Terminal · Windows: open PowerShell
claude mcp add --transport http --scope user guard https://karta.rta.lat/mcpYou should see KARTA — spend control for AI agents listed as connected
Use KARTA — spend control for AI agents and tell me what you can do for me, then show me one thing✓ If Claude Code says it is using KARTA — spend control for AI agents or shows a KARTA — spend control for AI agents tool in the answer, you are connected
Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version
Works with Cursor · about 2 min
No key, nothing to install
Use KARTA — spend control for AI agents and tell me what you can do for me, then show me one thing✓ If Cursor says it is using KARTA — spend control for AI agents or shows a KARTA — spend control for AI agents tool in the answer, you are connected
Menu names checked against Cursor’s help page on Nov 11, 2026 · your screen may differ slightly by app version
Works with VS Code · about 2 min
No key, nothing to install
Use KARTA — spend control for AI agents and tell me what you can do for me, then show me one thing✓ If VS Code says it is using KARTA — spend control for AI agents or shows a KARTA — spend control for AI agents tool in the answer, you are connected
Menu names checked against VS Code’s help page on Nov 11, 2026 · your screen may differ slightly by app version
Other apps that use MCP, such as Windsurf, Zed or Gemini CLI, each add servers differently. See how in the app list.
Address for apps that connect over the web
https://karta.rta.lat/mcpJSON settings are under “For developers” below
Claude Code
claude mcp add --transport http --scope user guard https://karta.rta.lat/mcpCursor (~/.cursor/mcp.json)
{
"mcpServers": {
"guard": {
"url": "https://karta.rta.lat/mcp"
}
}
}VS Code (mcp.json)
{
"servers": {
"guard": {
"type": "http",
"url": "https://karta.rta.lat/mcp"
}
}
}These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Based on how this server connects and on each app’s own docs, checked Nov 10, 2026.
Connect over the internet in
ClaudeChatGPTGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatOpen WebUIRaycast
Tool names and descriptions exactly as the server reported them on Nov 18, 2026. The maker wrote them, not us; we show them as plain text.
check_spendCheck whether a proposed agent spend is inside a task envelope. Returns verdict, rule, reason, counterfactual and next. No state is stored.
open_envelopeCreate 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.
get_envelopeReturn an envelope's state: budget, per-call cap, calls used, spent, remaining, allowlist and expiry. Read-only.
kill_envelopeStop one task envelope immediately: no further spend is approved for it, the reason is recorded with a timestamp. Idempotent — the first reason wins.
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. Read-only.
policy_rulesList 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.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 19, 2026
The publisher (karta.rta.lat) is not the repo owner (mrpkk); someone else may have listed it
Code last changed 12 days ago
No licence file found in the repo
No sign-in needed
Read 6 tool descriptions and found no hidden instructions to the AI
If you made this, paste this code into your README. The badge links back to this page.
[](https://mcp.popnx.com/en/servers/lat-rta-karta-guard)Ask, share a tip or report that it does not work. Sorted by what people marked helpful.
No posts yet. Be the first to ask or share.
Posts here are written by users, not the PopNx team.
No reviews yet
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 3 of 5 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed 12 days ago, and the latest version (0.1.0) reached the registry 24 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT on the web (full MCP on Business and above; Pro read-only).
In the same category: SolidInvoice, Signal8, Journalit, Beancount.io, Tapetide - Indian Stock Market MCP
Same category, other makers, commands already checked. Official ones first, then by stars.
Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Create and send invoices and quotes, manage clients, and track payments in SolidInvoice.
SEC filings, dilution, insider & institutional ownership, and political-trade data for AI agents.
Trading journal in Obsidian. Ask Claude or ChatGPT about your trades; edits are previewed first.
Query, edit, and reconcile a hosted Beancount ledger: BQL, reports, files, and bank imports.
48 tools for ~8,000 NSE & BSE stocks: quotes, screener, financials, filings, FII/DII, options
| This one KARTA — spend control for AI agents | SolidInvoice | Signal8 | Journalit | Beancount.io | Tapetide - Indian Stock Market MCP | |
|---|---|---|---|---|---|---|
| Runs where | Runs in the cloud, nothing to install | Runs in the cloud, nothing to install | Cloud or install on your computer | Runs in the cloud, nothing to install | Runs in the cloud, nothing to install | Cloud or install on your computer |
| Needs a key | No | No | Yes | No | No | Yes |
| Add with + in Claude | No | No | No | No | No | No |
| Basic checks | 3/5 | 4/6 | 5/5 | 4/4 | 4/4 | 5/5 |
| License | – | MIT | MIT | NOASSERTION | MIT | MIT |
| Price | No cost listed in the registry | No cost listed in the registry | No cost listed in the registry | No cost listed in the registry | No cost listed in the registry | No cost listed in the registry |
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
Trust layer между AI и ончейн-действием. Агент предлагает → детерминированная политика
(Dharma Engine) разрешает → симуляция подтверждает → человек аппрувит → Karma Engine
исполняет → Sakshi Log доказывает.
Статус: v2 в разработке (ветка
feature/v2-modernization). Тесты: 116 backend + 56 контрактов.
Канон-спека:
Документы/work/projectBooks/OnChainKartaSPEC.md.
| Область | Статус | |
|---|---|---|
| Auth | Argon2id; JWT access 15 мин + refresh 7 дней (ротация, reuse-detection → отзыв семьи, revoke-all); rate-limit логина 5/мин; legacy-sha256-миграция | |
| Хранилище | PostgreSQL 16 (14 таблиц, Alembic-миграции); данные переживают рестарт (тест «engine reset = restart») | |
| Dharma Engine | 15 правил (лимиты per-tx/daily/velocity, газ-кап, slippage, black/whitelist, окно, breakers, approve-гигиена); вердикты allow/deny/require_approval; гейт в ОБОИХ путях исполнения; DHARMA_ENFORCE=off для отката | |
| Approve | Только точные суммы; 2^256-1 заблокирован (INFINITE_APPROVE_BLOCKED); revoke_approve | |
| KeyVault | Ключ только через vault (lazy-init), core.py не читает ключ из конфига (guard-тест) | |
| Безопасность исполнения | Simulation-mode (дефолт); реальное исполнение — за флагом (READ+SIMULATE+PROPOSE) | |
| Kill switch | soft/hard, терминальный (без auto-resume), drill-тесты | |
| Sakshi Log | HMAC-цепочка (prev_hash‖canonical(payload)), append-only (PG-триггер), экспорт `json\ | csv` |
| Decision Diary | Каждое решение (action/reasoning/confidence/risk/policy_verdict) пишется в БД | |
| Live-события | WS /ws?token= — agent.status, decision.proposed (fan-out, 4401 при невалидном токене) | |
| LLM | Цепочка GigaChat → DeepSeek → Qwen → агрегатор → Ollama; structured output (pydantic) + repair + circuit breaker 3×60с; fail-safe ask_human | |
| Mempool | Реальный сканер блоков: watch-фильтр адресов + газ-тренд; честный rpc_unavailable без выдумок | |
| Health | /health + /health/deep: реальные TCP/RPC/LLM/KeyVault-проверки → ok/degraded/down | |
| Контракты | AgentRegistry + Escrow + RicardianAgreement: 56 hardhat-тестов, Slither (fail-on: high) в CI |
refresh_tokens готова — миграция слоем позже)docs/API.md)| Метод | Путь | Назначение | |
|---|---|---|---|
| POST | /api/v1/auth/register · /token · /refresh · /revoke-all · /logout | Argon2id, JWT-пара с ротацией и reuse-detection | |
| POST/GET | /api/v1/agents | Создать / список агентов (тиры 0–3, авто-политика тира) | |
| GET | /api/v1/agents/{id} | Карточка агента | |
| POST | /api/v1/agents/{id}/start · /stop · /heartbeat | Жизненный цикл (+ dead-man switch) | |
| POST | /api/v1/agents/{id}/goal · /intent · /intent/confirm | Цель; чат-задача NL→intent с Dharma-превью | |
| GET/PUT | /api/v1/agents/{id}/policy · POST /policy/from-text · /policy/simulate | Версии Dharma-политики; правила словами; impact-симулятор | |
| GET | /api/v1/agents/{id}/decisions · /pending · /audit · /drift | Decision Diary; undo-очередь; Sakshi; дрейф | |
| GET | /api/v1/agents/{id}/reports/summary · /export.csv | Health/Trust/дрейф-сводка; CSV (decisions/transactions/audit) | |
| GET/POST | /api/v1/approvals · `/approvals/{id}/approve | reject · /pending/{id}/cancel` | Approvals-inbox (web=Telegram, единый путь) |
| GET/POST/PUT | /api/v1/decisions/{id} | Replay: текущий вердикт vs сохранённый | |
| POST | /api/v1/agents/{id}/kill-switch | Экстренная остановка (soft/hard, терминальная) | |
| GET | /api/v1/agents/{id}/transactions | История транзакций | |
| GET/POST/DELETE | /api/v1/api-keys | API-ключи karta_ для MCP (scope mcp:read) | |
| POST | /mcp | MCP-сервер (streamable HTTP, stateless, read-only v1) — см. docs/MCP.md | |
| GET/POST | /api/v1/ricardian/* | Ricardian 2-of-3: соглашения, подписи, вехи, споры (Sepolia) | |
| GET/POST | /api/v1/agents/{id}/registry | ERC-8004-паспорт: регистрация/верификация/репутация + бейджи | |
| GET | /api/v1/registry/agents/{id}/metadata | Публичный паспорт агента (metadataURI, без auth) | |
| GET/POST | /api/v1/escrow/* | Аренда агентов: эскроу-оплата, release/refund/dispute/resolve (Sepolia) | |
| GET | /api/v1/x402/demo/premium | x402-демо: 402 → EIP-3009-подпись → сеттлмент (Sepolia, токен без ценности) | |
| GET | /api/v1/chains | Multi-chain реестр: 6 сетей (ETH/Sepolia/Base/Base Sepolia/BSC/Polygon) + health | |
| GET/POST | /api/v1/swap/* | Swap: котировка, slippage-guard, исполнение (MockDEX/Uniswap-V2, Sepolia) | |
| GET/POST | /api/v1/bridge/* | Bridge: реальные котировки LI.FI (AcrossV4), статус; исполнение gated | |
| GET/POST | /api/v1/erc4337/* | ERC-4337: smart account, session keys (TTL/лимит/цель), guardians | |
| GET | /api/v1/health · /health · /health/deep | Честные проверки компонентов | |
| WS | /ws?token= | Live-события | |
| GET | /docs · /openapi.json | OpenAPI/Swagger |
# 1) PostgreSQL (dev): контейнер на 5433 (системный PG занимает 5432)
docker compose up -d postgres # или: docker run -d --name karta-postgres \
python3 -m venv backend/.venv && backend/.venv/bin/pip install -r backend/requirements.txt
cd backend && DATABASE_URL=postgresql+asyncpg://agent:agent@127.0.0.1:5433/onchain_ai \ .venv/bin/alembic upgrade head
DEBUG=true .venv/bin/uvicorn src.api.main:app --port 8000 # из backend/
~/.env, chmod 600)| Переменная | Назначение |
|---|---|
DATABASE_URL | postgresql+asyncpg://agent:agent@127.0.0.1:5433/onchain_ai |
JWT_SECRET_KEY | openssl rand -hex 32 (обязательно в prod) |
ONCHAIN_MASTER_KEY | мастер-ключ KeyVault |
SAKSHI_AUDIT_KEY | ключ HMAC-цепочки аудита |
GIGACHAT_AUTH_KEY | GigaChat (первичный LLM) |
DEEPSEEK_API_KEY_* | DeepSeek (fallback) |
# Backend: 338 тестов + coverage-гейт 80%
backend/.venv/bin/python -m pytest backend/tests -q --cov=src --cov-fail-under=80
cd smart-contracts && npx hardhat test
python3 scripts/e2e_live.py # KARTA_E2E_BASE/USER/PASS — при необходимости
Human → REST /api/v1 + WS /ws → [Dharma Engine] → [Simulation] → [Timelock/Approval] → [Karma Engine] → Chain*
↓ ↓ Sakshi Log (HMAC, append-only) ← Decision Diary (decisions)
Инварианты: LLM не получает ключ; tx не подписывается без policy-вердикта и симуляции; любая ошибка → hold + ask_human; ни один слой не контролирует pipeline единолично.
PROGRESS.md — мега-контекст, реестр слайсов, журналdocs/AUDIT_REPORT.md — actual-vs-claimed аудитdocs/THREAT_MODEL.md — STRIDE T1–T12docs/ARCHITECTURE_CURRENT.md — фактическая архитектура (до модернизации)docs/ARCHITECTURE.md · docs/SECURITY.md — as-built архитектура и security-posturedocs/API.md — перечень API (генератор docs/generate_api_md.py)docs/MCP.md · docs/MCP_TOOL_CONTRACTS.md — MCP-сервер: подключение и контракты (генератор docs/generate_mcp_contracts.py)docs/X402.md — x402-демо (тестнет): поток, запуск, честные ограниченияdocs/DEPLOYMENT.md — развёртывание (dev/prod, env, адреса Sepolia)CHANGELOG.md — релизы v2.0-alpha / v2.0-betasmart-contracts/ — Solidity 0.8.20 + HardhatДисклеймер: не является финансовой рекомендацией. Автономный агент действует в границах
политик владельца; реальное исполнение — только после отдельного решения (STOP-GATE).