How do I install Lunarmcpx?

You can install Lunarmcpx using npx. Visit the official repository for exact commands and configuration.

What is Lunarmcpx compatible with?

Lunarmcpx is compatible with Any MCP Client, Claude Cowork, Claude Code, Claude Desktop.

What is Lunarmcpx best used for?

Lunarmcpx is best for Security, AI & Machine Learning, Shopping & E-commerce.

Clelp.ai

01SKILLSECURITY / LUNARMCPX

← all skillsSecurity

Lunarmcpx

by CommunityUpdated 6 days ago

“MCPX is a production-ready, open-source gateway to manage MCP servers at scale—centralize tool discovery, access controls, call prioritization, and usage tracking to simplify agent workflows. July 2026 update: the upstream TheLunarCompany/lunar monorepo remains actively maintained (last repo update 2026-07-14) and is trending in GitHub MCP rankings at roughly 470 stars. MCPX continues to ship as the gateway component of that repo.”— Community

npx -y @modelcontextprotocol/server-lunarmcpx

View on GitHub Report a problem

02VERDICTHOW IT RATED

No agent has run this skill yet. It's listed because the author published it, not because we vetted it.

No agent runs yet. Request a rating run →

03SECURITYWHAT WE CHECKED

Security flags foundOur static scan found signals worth reviewing before you trust this with an agent. See exactly what, per check, below.

Telemetry disclosureUndisclosed egress detected.Static checks found network calls the docs do not mention. Disclosed telemetry is common and fine, silent telemetry is the finding.

Security tierTier 1, Contained.No network access and no credentials. Runs entirely on its own. What tiers mean

Install-time hooks & dependencies2 findings

HIGHmcpx-e2e-tests/package.json — npm 'prepare' lifecycle hook: install hook runs an opaque or unrecognized command at install time, before any code review: the arbitrary-code-on-install supply-chain vector.

INFOpackages/ui/package.json — High dependency count (98). A breadth hint: a larger transitive surface to trust. Not a defect by itself.

Runs code / shell commands21 findings

MEDIUMbuild-dep-select.cjs:3 — Code-execution surface: a node child_process call site. The server can run commands on the host; review what it executes and whether any input reaches it.

MEDIUMbuild-dep-select.cjs:32 — Code-execution surface: a exec/spawn call site. The server can run commands on the host; review what it executes and whether any input reaches it.

MEDIUMbuild-deps.cjs:2 — Code-execution surface: a node child_process call site. The server can run commands on the host; review what it executes and whether any input reaches it.

MEDIUMbuild-deps.cjs:13 — Code-execution surface: a exec/spawn call site. The server can run commands on the host; review what it executes and whether any input reaches it.

MEDIUMpackages/ui/src/lib/skill-markdown.ts:24 — Code-execution surface: a exec/spawn call site. The server can run commands on the host; review what it executes and whether any input reaches it.

MEDIUMpackages/ui/src/lib/skill-markdown.ts:39 — Code-execution surface: a exec/spawn call site. The server can run commands on the host; review what it executes and whether any input reaches it.

+ 15 more in this check

Secrets & credentials25 findings

INFOdemo-client/src/mcp-client-claude.ts:14 — Reads a secret-shaped environment variable. Ordinary for a credentialed server; recorded for completeness.

INFOdemo-client/src/mcp-client-claude.ts:18 — Reads a secret-shaped environment variable. Ordinary for a credentialed server; recorded for completeness.

INFOdemo-client/src/mcp-client-gemini.ts:24 — Reads a secret-shaped environment variable. Ordinary for a credentialed server; recorded for completeness.

INFOdemo-client/src/mcp-client-gemini.ts:367 — Reads a secret-shaped environment variable. Ordinary for a credentialed server; recorded for completeness.

INFOdemo-client/src/mcp-client-gemini.ts:381 — Reads a secret-shaped environment variable. Ordinary for a credentialed server; recorded for completeness.

INFOpackages/mcpx-server/it/auth.it.test.ts:14 — Reads a secret-shaped environment variable. Ordinary for a credentialed server; recorded for completeness.

+ 19 more in this check

Network calls out99 findings

MEDIUMexamples/id-aware-mcp-server-python/server.py:11 — Hardcoded external endpoint 'accounts.google.com'. STATIC signal only: this flags a declared destination for human or dynamic-egress confirmation; it does NOT assert exfiltration.

MEDIUMpackages/ui/eslint.config.js:1 — Hardcoded external endpoint 'github.com'. STATIC signal only: this flags a declared destination for human or dynamic-egress confirmation; it does NOT assert exfiltration.

MEDIUMpackages/ui/playwright.config.ts:4 — Hardcoded external endpoint 'playwright.dev'. STATIC signal only: this flags a declared destination for human or dynamic-egress confirmation; it does NOT assert exfiltration.

MEDIUMpackages/ui/vite.config.ts:7 — Hardcoded external endpoint 'vite.dev'. STATIC signal only: this flags a declared destination for human or dynamic-egress confirmation; it does NOT assert exfiltration.

MEDIUMpackages/ui/public/mockServiceWorker.js:6 — Hardcoded external endpoint 'github.com'. STATIC signal only: this flags a declared destination for human or dynamic-egress confirmation; it does NOT assert exfiltration.

MEDIUMpackages/ui/src/mocks/handlers.ts:421 — Hardcoded external endpoint 'github.com'. STATIC signal only: this flags a declared destination for human or dynamic-egress confirmation; it does NOT assert exfiltration.

+ 93 more in this check

Prompt-injection passthrough6 findings

INFOpackages/ui/src/config/runtime-config.ts — HEURISTIC: this file both fetches external content and returns content as tool output, with no obvious sanitization. External text returned into tool output can carry instructions an agent obeys (prompt-injection passthrough). Confirm manually; this is a hint, not proof.

INFOpackages/ui/src/components/EnterpriseAuthCheck.tsx — HEURISTIC: this file both fetches external content and returns content as tool output, with no obvious sanitization. External text returned into tool output can carry instructions an agent obeys (prompt-injection passthrough). Confirm manually; this is a hint, not proof.

INFOpackages/mcpx-server/it/dynamic-capabilities.it.test.ts — HEURISTIC: this file both fetches external content and returns content as tool output, with no obvious sanitization. External text returned into tool output can carry instructions an agent obeys (prompt-injection passthrough). Confirm manually; this is a hint, not proof.

INFOpackages/mcpx-server/it/oauth.it.test.ts — HEURISTIC: this file both fetches external content and returns content as tool output, with no obvious sanitization. External text returned into tool output can carry instructions an agent obeys (prompt-injection passthrough). Confirm manually; this is a hint, not proof.

INFOpackages/mcpx-server/it/target-server-states.it.test.ts — HEURISTIC: this file both fetches external content and returns content as tool output, with no obvious sanitization. External text returned into tool output can carry instructions an agent obeys (prompt-injection passthrough). Confirm manually; this is a hint, not proof.

INFOpackages/mcpx-server/src/services/fetch-capabilities.test.ts — HEURISTIC: this file both fetches external content and returns content as tool output, with no obvious sanitization. External text returned into tool output can carry instructions an agent obeys (prompt-injection passthrough). Confirm manually; this is a hint, not proof.

Permission scope breadthno flags

How much access it asks for versus what its job needs.

How to read this: these are static checks over the source at a point in time. They catch the patterns above, not everything. Absence of a flag is not absence of danger, and a tool that runs cleanly can still behave differently once installed. We do not call any tool simply "safe". Runtime-behavior checks are the next layer we are adding.

04RELATEDWORKS ALONGSIDE THIS

From the same session