ton-cli
Call TON MCP tools directly from the command line. Use when you want to query wallet info, check balances, send transactions, or run any TON wallet tool without starting an MCP server session. Works via `npx @ton/mcp@alpha <tool_name> [--arg value ...]`.
What this skill does
# TON MCP Raw CLI Mode
Run any TON wallet MCP tool directly from the command line. The binary invokes the tool, prints the JSON result to stdout, and exits.
## Invocation Modes
| Command | Description |
| ------- | ----------- |
| `npx @ton/mcp@alpha` | stdio MCP server (for Claude Desktop / MCP clients) |
| `npx @ton/mcp@alpha --http [port]` | HTTP MCP server |
| `npx @ton/mcp@alpha <tool_name> [--arg value ...]` | **Raw CLI: call one tool and exit** |
Use exactly one mode for a given workflow: either MCP server mode (`stdio`/`--http`) or raw CLI. Do not combine them in the same task/session.
## Raw CLI Usage
```bash
# No arguments
npx @ton/mcp@alpha get_balance
# Named arguments (--key value)
npx @ton/mcp@alpha get_transactions --limit 5
npx @ton/mcp@alpha get_jetton_balance --jettonAddress EQAbc...
# All values are passed as plain strings; JSON objects/arrays are also accepted
npx @ton/mcp@alpha get_transactions --limit 10
npx @ton/mcp@alpha send_ton --toAddress UQA... --amount 0.1 --comment "hi"
npx @ton/mcp@alpha generate_ton_proof --domain getgems.io --payload getgems-llm
```
Arguments are passed as `--key value` pairs. Objects/arrays (`{...}` / `[...]`) are JSON-parsed; everything else is kept as a plain string.
## Output
All tools print JSON to **stdout**. Errors are printed to **stderr** and the process exits with code `1`.
```bash
# Capture output for scripting
BALANCE=$(npx @ton/mcp@alpha get_balance)
echo $BALANCE | jq '.balance'
```
## Environment Variables
The CLI respects the same environment variables as the server:
| Variable | Description |
| -------- | ----------- |
| `NETWORK` | `mainnet` (default) or `testnet` |
| `MNEMONIC` | 24-word mnemonic for single-wallet mode |
| `PRIVATE_KEY` | Hex-encoded private key (alternative to mnemonic) |
| `WALLET_VERSION` | `v5r1` (default), `v4r2`, or `agentic` |
| `TONCENTER_API_KEY` | Optional Toncenter API key |
| `TON_CONFIG_PATH` | Path to config file (default: `~/.config/ton/config.json`) |
Without `MNEMONIC` or `PRIVATE_KEY`, the CLI uses the local config registry at `~/.config/ton/config.json` (registry mode). In registry mode, wallet-scoped tools accept an optional `--walletSelector` to target a specific wallet by id, name, or address.
## Tool Reference
### Wallet & Balance
| Tool | Required args | Optional args |
| ---- | ------------- | ------------- |
| `get_wallet` | — | `--walletSelector` |
| `get_balance` | — | `--walletSelector` |
| `get_balance_by_address` | `--address` | `--walletSelector` |
| `get_jetton_balance` | `--jettonAddress` | `--walletSelector` |
| `get_jettons` | — | `--walletSelector` |
| `get_jettons_by_address` | `--address` | `--limit`, `--offset`, `--walletSelector` |
| `get_jetton_info` | `--jettonAddress` | `--walletSelector` |
| `get_transactions` | — | `--limit`, `--walletSelector` |
| `get_transaction_status` | `--normalizedHash` | `--walletSelector` |
| `get_known_jettons` | — | — |
### Wallet Registry (config-registry mode only)
| Tool | Required args | Optional args |
| ---- | ------------- | ------------- |
| `list_wallets` | — | — |
| `get_current_wallet` | — | — |
| `set_active_wallet` | `--walletSelector` | — |
| `remove_wallet` | `--walletSelector` | — |
### Transfers
| Tool | Required args | Optional args |
| ---- | ------------- | ------------- |
| `send_ton` | `--toAddress`, `--amount` | `--comment`, `--walletSelector` |
| `send_jetton` | `--toAddress`, `--jettonAddress`, `--amount` | `--comment`, `--walletSelector` |
| `send_nft` | `--nftAddress`, `--toAddress` | `--comment`, `--walletSelector` |
| `send_raw_transaction` | `--messages` | `--validUntil`, `--fromAddress`, `--walletSelector` |
| `emulate_transaction` | `--messages` | `--validUntil`, `--walletSelector` |
### Swaps
| Tool | Required args | Optional args |
| ---- | ------------- | ------------- |
| `get_swap_quote` | `--fromToken`, `--toToken`, `--amount` | `--slippageBps`, `--walletSelector` |
### NFTs
| Tool | Required args | Optional args |
| ---- | ------------- | ------------- |
| `get_nfts` | — | `--limit`, `--offset`, `--walletSelector` |
| `get_nfts_by_address` | `--address` | `--limit`, `--offset`, `--walletSelector` |
| `get_nft` | `--nftAddress` | `--walletSelector` |
### DNS
| Tool | Required args | Optional args |
| ---- | ------------- | ------------- |
| `resolve_dns` | `--domain` | `--walletSelector` |
| `back_resolve_dns` | `--address` | `--walletSelector` |
### Authentication
| Tool | Required args | Optional args |
| ---- | ------------- | ------------- |
| `generate_ton_proof` | `--domain`, `--payload` | `--walletSelector` |
## Example Session
```bash
# Check wallet address and network
npx @ton/mcp@alpha get_wallet
# Check TON balance
npx @ton/mcp@alpha get_balance
# List all tokens
npx @ton/mcp@alpha get_jettons
# Last 10 transactions
npx @ton/mcp@alpha get_transactions --limit 10
# Get balance of a specific jetton
npx @ton/mcp@alpha get_jetton_balance --jettonAddress EQCxE6mUtQJKFnGfaROTKOt1lZbDiiX1kCixRv7Nw2Id_sDs
# Resolve a .ton domain
npx @ton/mcp@alpha resolve_dns --domain foundation.ton
# In registry mode: check balances for a named wallet
npx @ton/mcp@alpha get_balance --walletSelector "my-hot-wallet"
# In registry mode: list all registered wallets
npx @ton/mcp@alpha list_wallets
# Send TON (always confirm with user first)
npx @ton/mcp@alpha send_ton --toAddress UQA... --amount 0.5 --comment "payment"
# Swap quote
npx @ton/mcp@alpha get_swap_quote --fromToken TON --toToken EQCxE6mUtQJKFnGfaROTKOt1lZbDiiX1kCixRv7Nw2Id_sDs --amount 1
# Generate a TonProof for a service challenge
npx @ton/mcp@alpha generate_ton_proof --domain getgems.io --payload getgems-llm
```
## Notes
- Use `emulate_transaction` to dry-run any transaction before sending — it returns expected balance changes, fees, and high-level actions
- Use `generate_ton_proof` only with the exact domain and payload supplied by the user or verifying service; do not alter the payload before signing
- `generate_ton_proof` requires signing access even though it does not broadcast a transaction
- Always confirm with the user before running `send_ton`, `send_jetton`, `send_nft`, or `send_raw_transaction`;
- For confirmations and small option sets, prefer the host client's structured confirmation/choice UI when available; otherwise use a short natural-language yes/no prompt and never require an exact magic word;
- After sending, poll `get_transaction_status --normalizedHash <hash>` until status is `completed` or `failed` (unless the user asks to skip).
- In registry mode the active wallet from `~/.config/ton/config.json` is used by default.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.