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/Dexter-DAO/opendexter-ideWrote 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/plugins/dexter-dao/opendexter-ide/mcp)<a href="https://agentmods.dev/plugins/dexter-dao/opendexter-ide/mcp"><img src="https://agentmods.dev/badge/plugins/dexter-dao/opendexter-ide/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/plugins/dexter-dao/opendexter-ide/mcp"><img src="https://agentmods.dev/badge/plugins/dexter-dao/opendexter-ide/mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
opendexter 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 3d 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
{
"name": "opendexter",
"displayName": "OpenDexter",
"version": "1.25.0",
"description": "Run the local proxy for OpenDexter's hosted governed x402 runtime: search, check, execute and reconcile OAuth-bound intents, and read wallet authority or portfolio state. No local payment fallback.",
"author": {
"name": "Dexter",
"email": "[email protected]"
},
"homepage": "https://dexter.cash/opendexter",
"repository": "https://github.com/Dexter-DAO/opendexter-ide",
"license": "MIT",
"logo": "assets/dexter-wordmark.svg",
"keywords": [
"x402",
"payments",
"crypto",
"solana",
"base",
"evm",
"dexter",
"opendexter",
"web3",
"stripe",
"agent-payments",
"mcp",
"machine-payments"
],
"category": "developer-tools",
"tags": [
"payments",
"web3",
"ai-agents",
"mcp"
],
"skills": "./skills/",
"rules": "./rules/",
"agents": "./agents/",
"commands": "./commands/"
}
What it installs
The manifest is a name and a version. 5 skills, 3 commands, 1 agent travel with it, and installing the plugin installs all of them — 460 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill x402-server A 66 tokens
- Skill instinct-advertiser A 74 tokens
- Skill x402-client A 60 tokens
- Skill x402-react A 56 tokens
- Skill x402-discoverable A 115 tokens
- Command setup-opendexter A 20 tokens
- Command setup-x402-client A 23 tokens
- Command setup-x402-server A 24 tokens
- Agent x402-engineer A 22 tokens
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.
- 3d ago Changed 74c8e406b37a
- 4d ago First seen · 41 lines scan A 4a88c002dd97
opendexter is a plugin published in the GitHub repository Dexter-DAO/opendexter-ide (2 stars, last pushed 3d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-17.
Other plugins, from other repositories
t2000-agent-wallet
The t2000 marketplace + wallet playbooks: hire and post Open jobs, claim and deliver work, settle in USDC; fund, check balance, send (gasless USDC/USDsui), swap via Cetus, discover Services, and pay x402 APIs. Includes the Passport Connect MCP wiring + the cross-cutting AGENTS.md ops layer.
ironwallet-mcp
The IronWallet MCP server gives AI agents a non-custodial hot wallet on the host machine. Seed phrases stay encrypted locally and never leave the host. Agents can check balances, transfer tokens, and swap across 10+ networks (EVM, Tron, Bitcoin, Litecoin, Dogecoin, Solana, XRP, TON).
trade-router
Non-custodial Solana swap & limit-order MCP server for AI agents. 21 tools (swap, limit, trailing, TWAP, DCA, combo orders) across Raydium, PumpSwap, Orca, Meteora. Jito MEV-protected. Ed25519 server-message verification. Private key never leaves the agent.
solana-finance
Expert Solana development with Claude: production-grade Anchor, Quasar, Rust, and TypeScript patterns with a focus on financial correctness — onchain math, escrows, AMMs, vaults, oracle freshness, and slippage. Made by Quicknode.
claude
Jupiter integration and documentation skills for Solana, crypto, and finance workflows.
bitbank-lab-mcp
Experimental MCP server for bitbank — botters lab community edition. Market data, technical analysis, charting, and Private API trading tools.