Mirage is a virtual terminal for AI agents that presents files, command-line tools, and configurable runtimes through one interface. It helps agents access data and run computations across services with controlled visibility and actions, and the catalogue entries provide related integrations.
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/strukto-ai/mirageWrote 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/strukto-ai/mirage/mirage-mirage)<a href="https://agentmods.dev/mcp/strukto-ai/mirage/mirage-mirage"><img src="https://agentmods.dev/badge/mcp/strukto-ai/mirage/mirage-mirage/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/strukto-ai/mirage/mirage-mirage"><img src="https://agentmods.dev/badge/mcp/strukto-ai/mirage/mirage-mirage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
mirage 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.
What it actually says
{
"mirage": {
"command": "npx",
"args": [
"-y",
"@struktoai/mirage-cli",
"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.
- 12d ago First seen · 10 lines scan A c7488da5df85
mirage is an MCP server published in the GitHub repository strukto-ai/mirage (3,617 stars, last pushed yesterday), licensed Apache-2.0. 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 2026-08-30.
Other mcp servers, from other repositories
gopls
MCP server "gopls" as configured in fredrikaverpil/dotfiles. Launched with gopls mcp.
url-manager-mcp
URL Manager MCP Server — Agent-first web link collection & knowledge management. Runs locally from the url-manager-mcp Python package. Needs 2 environment variables to run.
local-gpu-imagegen
MCP server "local-gpu-imagegen" as configured in ChevalGrand520/local-gpu-imagegen. Runs scripts/mcp_server.py with python.
zerodust
Recover stranded native gas: empty a chain's balance to exactly zero on 25 EVM chains. Runs locally from the @zerodust/mcp-server npm package. Needs 10 environment variables to run.
domain-search-king-mcp
Domain search MCP: .com names verified available live via Verisign RDAP - not AI guess lists. Remote server at domainsearchking.com.
mcp-server
Pay-per-call AI + web + on-chain tools over x402 (USDC on Base): LLM, SEO, extract, token safety. Runs locally from the @true402.dev/mcp-server npm package. Needs 3 environment variables to run.