Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add ahmed3elshaer/everything-claude-code-mobile/plugin install everything-claude-code-mobileWrote 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/ahmed3elshaer/everything-claude-code-mobile/mobile-memory)<a href="https://agentmods.dev/mcp/ahmed3elshaer/everything-claude-code-mobile/mobile-memory"><img src="https://agentmods.dev/badge/mcp/ahmed3elshaer/everything-claude-code-mobile/mobile-memory.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
mobile-memory 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 5d 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- ios-memory — 97% identical, 4 lines differ
- kmp-context — 94% identical, 4 lines differ
What it actually says
{
"mobile-memory": {
"command": "node",
"args": [
"-e",
"const p=require('node:path'),f=require('node:fs'),o=require('node:os'),e=process.env,a=process.argv[1],rel='mcp-servers/start.js';let r=a&&!a.startsWith('${')?a:e.CLAUDE_PLUGIN_ROOT||e.PLUGIN_ROOT||e.CODEX_PLUGIN_ROOT||process.cwd();if(!f.existsSync(p.join(r,rel))){const hs=(e.PATH||'').split(p.delimiter).filter(x=>x.includes(p.join('tmp','arg0'))).map(x=>p.dirname(p.dirname(p.dirname(x))));hs.push(e.CODEX_HOME,p.join(o.homedir(),'.codex'));for(const h of hs.filter(Boolean)){const c=p.join(h,'plugins','cache');for(const m of f.existsSync(c)?f.readdirSync(c):[]){const d=p.join(c,m,'everything-claude-code-mobile');for(const v of f.existsSync(d)?f.readdirSync(d).sort().reverse():[]){const x=p.join(d,v);if(f.existsSync(p.join(x,rel))){r=x;break}}if(f.existsSync(p.join(r,rel)))break}if(f.existsSync(p.join(r,rel)))break}}require(p.join(r,rel))",
"${CLAUDE_PLUGIN_ROOT}",
"mobile-memory"
]
}
}What else .mcp.json configures
This page is one entry in a file that holds 3. Installing the file brings all of them; each is measured and scanned on its own page.
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.
- 5d ago First seen · 11 lines scan A e1a5b59a80b7
mobile-memory is an MCP server published in the GitHub repository ahmed3elshaer/everything-claude-code-mobile (65 stars, last pushed 2mo 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 2026-08-30.
Other mcp servers, from other repositories
sceneview
MCP server for SceneView — cross-platform 3D & AR SDK for Android and iOS. Give Claude the full SceneView SDK so it writes correct, compilable code. Runs locally from the sceneview-mcp npm package.
sceneview
3D & AR SDK for Android, iOS, Web — API docs, samples, validation, and code generation. Runs locally from the sceneview-mcp npm package.
lazy_mobile_mcp
Local MCP server for Android/iOS device automation and performance telemetry (ADB, simctl, devicectl, WDA). Runs locally from the lazy_mobile_mcp npm package.
docs-langchain
MCP server "docs-langchain", hosted remotely at docs.langchain.com, as configured in langchain-ai/langchain.
reference-langchain
MCP server "reference-langchain", hosted remotely at reference.langchain.com, as configured in langchain-ai/langchain.
playwright-test
A high-level API to automate web browsers. Runs locally from the playwright npm package.