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.
git clone --depth 1 https://github.com/multiversx/mx-sdk-dapp-mcpWrote 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.
[](https://agentmods.dev/mcp/multiversx/mx-sdk-dapp-mcp/mx-dev-mcp)<a href="https://agentmods.dev/mcp/multiversx/mx-sdk-dapp-mcp/mx-dev-mcp"><img src="https://agentmods.dev/badge/mcp/multiversx/mx-sdk-dapp-mcp/mx-dev-mcp/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.
<a href="https://agentmods.dev/mcp/multiversx/mx-sdk-dapp-mcp/mx-dev-mcp"><img src="https://agentmods.dev/badge/mcp/multiversx/mx-sdk-dapp-mcp/mx-dev-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
mx-dev-mcp 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 1mo 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.
What it actually says
{ "mx-dev-mcp": { "command": "npx", "args": [ "-y", "mx-dev-mcp" ] } }
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.
- 1mo ago First seen · 9 lines scan A 2072742ad6d0
mx-dev-mcp is an MCP server published in the GitHub repository multiversx/mx-sdk-dapp-mcp (0 stars, last pushed 1y ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. 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.
Other mcp servers, from other repositories
multiversx-sc
MCP server for MultiversX blockchain and smart contract interaction — 41 tools for querying, deploying, verifying contracts, managing wallets, issuing tokens, batch transfers, and more. ABI-aware with auto-discovery. Runs locally from the multiversx-sc-mcp npm package. Needs 3 environment variables to run.
iroha-taira
MCP server "iroha-taira", hosted remotely at taira.sora.org, as configured in hyperledger-iroha/iroha.
evm-mcp-http
MCP server for interacting with EVM-compatible blockchains - supports 22 tools and 10 prompts across 60+ networks. Runs locally from the @mcpdotdirect/evm-mcp-server npm package.
mcp
Liteserver access to TON: balances, account state, transactions and get-methods over native ADNL. Runs locally from the @tonnode/mcp npm package. Needs 2 environment variables to run.
bsv-wallet
MCP server "bsv-wallet" as configured in Calhooon/bsv-wallet-cli. Launched with cargo run --release --manifest-path mcp/Cargo.toml. Needs 1 environment variable to run.
alchemy
MCP server "alchemy", hosted remotely at mcp.alchemy.com, as configured in alchemyplatform/alchemy-claude-plugin.