agentmods.dev

algorand-mcp-lite

algorand-mcp-lite is a skill for Claude Code, Codex from GoPlausible/algorand-remote-mcp-lite. It costs 202 tokens per session (7,045 once invoked), scanned A, original, MIT.

A guide for using Algorand blockchain tools for wallets, ALGO and token transactions, account lookups, swaps, and prediction markets. Algorand is a blockchain network, and the connection can sign transactions on the server.

In plain words
What is it for?
Use it for Algorand wallet work, blockchain queries, asset transfers, grouped transactions, decentralised-exchange swaps, prediction markets, and related account or asset tasks.
Why use it?
It provides procedures for carrying out blockchain operations and handling the interactive tool responses correctly.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

not rated 5repo 1mo ago A scan 202 tokens original MIT

Good fit Use it for Algorand wallet work, blockchain queries, asset transfers, grouped transactions, decentralised-exchange swaps, prediction markets, and related account or asset tasks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/goplausible/algorand-remote-mcp-lite/algorand-mcp-lite
View source ↗ GoPlausible/algorand-remote-mcp-lite
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add GoPlausible/algorand-remote-mcp-lite --skill algorand-mcp-lite
Clone the repo
git clone --depth 1 https://github.com/GoPlausible/algorand-remote-mcp-lite

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for algorand-mcp-lite

README.md
[![agentmods](https://agentmods.dev/badge/skills/goplausible/algorand-remote-mcp-lite/algorand-mcp-lite/github.svg)](https://agentmods.dev/skills/goplausible/algorand-remote-mcp-lite/algorand-mcp-lite)
Your own site
<a href="https://agentmods.dev/skills/goplausible/algorand-remote-mcp-lite/algorand-mcp-lite"><img src="https://agentmods.dev/badge/skills/goplausible/algorand-remote-mcp-lite/algorand-mcp-lite/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for algorand-mcp-lite

Your own site · 80×15
<a href="https://agentmods.dev/skills/goplausible/algorand-remote-mcp-lite/algorand-mcp-lite"><img src="https://agentmods.dev/badge/skills/goplausible/algorand-remote-mcp-lite/algorand-mcp-lite.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 202 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,045 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00202 $0.07045
Opus 5 $0.00101 $0.03522
Sonnet 5 $0.00040 $0.01409
Haiku 4.5 $0.00020 $0.00705

Measured 12d ago against content hash c33be3833a10, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

algorand-mcp-lite scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/algorand-mcp-lite/SKILL.md · 663 lines

How it starts

The opening of the file, as written. The whole thing — 663 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Algorand Remote MCP Lite (Wallet Edition)

This skill defines capabilities, workflows, and best practices for interacting with the Algorand blockchain using Algorand Remote MCP Lite (Wallet Edition). The server provides 55 MCP tools for wallet management, transactions, blockchain queries, DEX swaps, prediction markets, and more — all with server-side signing via HashiCorp Vault.

Response Handling — MCP Apps UI Widgets

Algorand Remote MCP Lite uses the MCP Apps SDK (@modelcontextprotocol/ext-apps) to register tools with interactive UI widgets via registerAppTool(). Widget resources are registered via registerAppResource().

How it works

  • 55 tools are registered as App tools with _meta.ui.resourceUri linking each tool to an HTML widget resource.
  • Each tool returns both content (text fallback) and structuredContent (typed data for the widget).
  • The host detects _meta.ui.resourceUri on the tool and renders the widget inline — the widget IS the complete response.
  • 4 plain utility tools (sdk_encode_address, sdk_decode_address, algorand_mcp_skill, haystack_needs_optin) have no UI and return text only.

Agent behavior rules

  1. When the host supports MCP Apps UI: The widget renders inline as the complete response. Do NOT repeat, reformat, or summarize the content text — the user already sees the widget. Simply confirm the action succeeded.
  2. For text-only clients: The host shows the content text fallback automatically. No special agent handling is needed.
  3. If the user explicitly asks for raw data, display the content text.

Security Rules

  1. Mainnet Warning: All operations use real assets with real value. Exercise extreme caution.
  2. Transaction Verification: Always verify parameters before submission. Mainnet transactions are irreversible.
  3. Double-Check Recipients: Confirm addresses with user before sending.
  4. Simulation: Simulate critical transactions before submitting when possible.
  5. Wallet Reset: wallet_reset_account is destructive — all funds and assets will be permanently lost. Always transfer funds first and warn the user.
  6. Signing: Server-side signing via HashiCorp Vault — never request private keys or mnemonics unless the user explicitly asks.
  7. Wallet Role UUID: Retrieved only via wallet_get_role — this is sensitive information. Always warn users to protect it and never share it.
  8. Asset Verification: Check pera_verified_asset_query before interacting with unknown assets. Warn about suspicious/unverified tiers.
  9. Spending Limits: If a transaction is rejected due to wallet limits, inform the user rather than bypassing.

Read the full file on GitHub · 663 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 663 lines · 202 tokens per session scan A c33be3833a10

Subscribe to this mod's changes

algorand-mcp-lite is a skill published in the GitHub repository GoPlausible/algorand-remote-mcp-lite (5 stars, last pushed 1mo ago), licensed MIT. It adds 202 tokens to every session and 7,045 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Web3 and blockchain
Related

Other skills, from other repositories

signature-replay

Signature replay attacks — missing nonces, missing chain ID, ecrecover zero address, signature malleability, cross-chain replay.

PurpleAILAB/Decepticon · 31 tokens

official-sui-skills

Pointer to the official Mysten Labs skills for building on Sui — language fundamentals, object model, PTBs, SDKs, publishing, upgrades, frontend integration, accessing on-chain data. Maintained upstream at github.com/MystenLabs/skills; pinned to the same ref the audit catalog derives from (see…

MystenLabs/sui · 116 tokens

bridge

Cross-chain token transfers using Wormhole and CCTP.

alsk1992/CloddsBot · 13 tokens

onchainkit

Build onchain apps with Coinbase's OnchainKit React components - wallets, swaps, NFTs, payments.

alsk1992/CloddsBot · 24 tokens

marginfi

MarginFi — Solana lending and borrowing.

alsk1992/CloddsBot · 11 tokens

crypto-market-rank

Crypto market rankings and leaderboards. Query trending tokens, top searched tokens, Binance Alpha tokens, tokenized stocks, social hype sentiment ranks, smart money inflow token rankings, top meme token rankings from Pulse launchpad, and top trader PnL leaderboards. Use this skill when users ask about token rankings…

tradecatlabs/tradecat-public · 85 tokens