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/melaya-labs/melaya-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/plugins/melaya-labs/melaya-mcp/gemini-extension)<a href="https://agentmods.dev/plugins/melaya-labs/melaya-mcp/gemini-extension"><img src="https://agentmods.dev/badge/plugins/melaya-labs/melaya-mcp/gemini-extension/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/melaya-labs/melaya-mcp/gemini-extension"><img src="https://agentmods.dev/badge/plugins/melaya-labs/melaya-mcp/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
melaya 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 13d 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": "melaya",
"version": "1.2.0",
"description": "Create and run any AI agents systems from 8k+ tools. Give your AI hands access to your Android.",
"mcpServers": {
"melaya": {
"httpUrl": "https://api.melaya.org/mcp",
"authProviderType": "dynamic_discovery",
"oauth": {
"enabled": true
}
}
}
}
What ships with it
43 files beside gemini-extension.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/brand/melaya_fire.webp 26 KB
- assets/brand/melaya_got_an_idea.webp 54 KB
- assets/brand/melaya_happy.webp 18 KB
- assets/brand/melaya_horizontal_dark.webp 19 KB
- assets/brand/melaya_horizontal_light.webp 24 KB
- assets/brand/melaya_mark_transparent.svg 2.7 KB
- assets/brand/melaya_party.webp 62 KB
- assets/brand/melaya_sneaky.webp 52 KB
- assets/brand/melaya_studying.webp 54 KB
- assets/brand/melaya_sunglasses.webp 17 KB
- assets/brand/melaya_surprise.webp 18 KB
- assets/brand/melaya_thumbs_up.webp 21 KB
- assets/brand/melaya_wondering.webp 15 KB
- assets/brand/melaya_zen.webp 34 KB
- assets/clients/anthropic.webp 4.7 KB
- assets/clients/claude-code.svg 4.0 KB
- assets/clients/codex.svg 1.3 KB
- assets/clients/cursor.webp 14 KB
- assets/clients/mistral.webp 3.1 KB
- assets/clients/openai.webp 5.6 KB
- assets/providers/anthropic.webp 4.7 KB
- assets/providers/cerebras.webp 34 KB
- assets/providers/cohere.webp 1.9 KB
- assets/providers/deepseek.webp 8.7 KB
- assets/providers/gemini.webp 19 KB
- assets/providers/grok.webp 8.1 KB
- assets/providers/groq.webp 6.7 KB
- assets/providers/lmstudio.webp 22 KB
- assets/providers/mistral.webp 3.1 KB
- assets/providers/moonshot.webp 42 KB
- assets/providers/nvidia.webp 6.1 KB
- assets/providers/ollama.webp 91 KB
- assets/providers/openai.webp 5.6 KB
- assets/providers/qwen.webp 13 KB
- assets/providers/sambanova.webp 15 KB
- assets/screens/agent-builder.webp 52 KB
- assets/screens/app-permissions.jpeg 112 KB
- assets/screens/app-playbooks.webp 74 KB
- assets/screens/device-agent-overlay.webp 66 KB
- assets/screens/live-session.webp 33 KB
- assets/screens/on-device-approval.webp 58 KB
- assets/screens/sleeping-phone.webp 53 KB
- assets/screens/three-pillars.webp 65 KB
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.
- 13d ago Changed aa6ca9d90910
- 22d ago Changed 55a92c6e4998
- 1mo ago First seen · 15 lines scan A 7ec88902ef8b
melaya is a plugin published in the GitHub repository melaya-labs/melaya-mcp (1 stars, last pushed 5d ago), licensed Apache-2.0. 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 2026-09-08.
Other plugins, from other repositories
alethia
Patent-pending agent-native software runtime for executing and verifying real application workflows. Drive browser interactions and E2E checks in plain English, enforce the VITRON-EA1 fail-closed safety gate, audit accessibility and security controls, and export signed evidence packs. Local-first, zero telemetry.
cortex
Persistent local-first memory MCP server: remember/recall with thermodynamic heat and decay, knowledge graph, autonomous wiki, local SQLite store by default. Requires uv (uvx) on PATH; hooks-based auto-capture is Claude Code-only — on Gemini CLI memory is manual-tool-driven.
secedgar-mcp-server
Query SEC EDGAR filings, XBRL financials, and company data via MCP. STDIO or Streamable HTTP.
football-charts
Football (soccer) statistics for 93 leagues in 42 countries, including lower divisions and women's leagues: results with half-time scores, league tables, fixtures, goal timing and season projections. Read-only, no API key needed.
cdc-health-mcp-server
Search and query CDC public health data — mortality, vaccinations, surveillance, behavioral risk (Socrata SODA API) via MCP. STDIO or Streamable HTTP.
promptspeak
Pre-execution governance for AI agents. Intercepts MCP tool calls with deterministic blocking, human-in-the-loop holds, and behavioral drift detection.