Gemini MCP Server

Integrates Google Gemini 3.1 with Claude Code to provide web search, large codebase analysis, multimodal image understanding, and creative brainstorming, leveraging Gemini's 1M token context and Google Search grounding.

→ LKbaba/Gemini-mcp · listed on glama

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find.

Install from

Glama

M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.

// key findings

⚠️

Known vulnerabilities in dependencies: 3 high

Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.

✅

No credential exfiltration, no sensitive file access, no obfuscation

Static analysis found nothing flowing your secrets to unexpected places.

✅

Open source with a license and README

Anyone can audit the code, the license is declared, and the publisher documents what it does.

🔐

You'll be asked for 3 credentials: GEMINI_API_KEY, GOOGLE_API_KEY, private_key

These are read from process.env at runtime. Make sure you trust where they’ll be sent.

// required environment variables

This server reads these from process.env. You'll be asked to provide them before it can run.

🔐 secretGEMINI_API_KEY— "": "your-api-key"

🔐 secretGOOGLE_API_KEY

configGOOGLE_APPLICATION_CREDENTIALS— Advanced options: You can also use GOOGLE_GENAI_USE_VERTEXAI=true + GOOGLE_CREDENTIALS_JSON, (file path), or gcloud auth application-default login. See the environment variables reference below.

configGOOGLE_CLOUD_LOCATION— No Region (default: global)

configGOOGLE_CLOUD_PROJECT— The server auto-detects service account credentials from env vars — no GOOGLE_GENAI_USE_VERTEXAI or needed. Just paste and go.

configGOOGLE_CREDENTIALS_JSON— No Entire service account JSON as a single string

configGOOGLE_GENAI_USE_VERTEXAI— The server auto-detects service account credentials from env vars — no or GOOGLE_CLOUD_PROJECT needed. Just paste and go.

configHTTPS_PROXY— "": "http://127.0.0.1:7897"

configHTTP_PROXY

configauth_provider_x509_cert_url— "": "https://www.googleapis.com/oauth2/v1/certs",

configauth_uri— "": "https://accounts.google.com/o/oauth2/auth",

configclient_email— "": "your-sa@your-project.iam.gserviceaccount.com",

configclient_id— "": "123456789",

configclient_x509_cert_url— "": "https://www.googleapis.com/robot/v1/metadata/x509/your-sa%40your-project.iam.gserviceaccount.com",

confighttp_proxy

confighttps_proxy

🔐 secretprivate_key— "": "-----BEGIN PRIVATE KEY-----\nMIIEv...\n-----END PRIVATE KEY-----\n",

configprivate_key_id— "": "key-id-here",

configproject_id— "": "your-project-id",

configtoken_uri— "": "https://oauth2.googleapis.com/token",

configtype— "": "service_account",

configuniverse_domain— "": "googleapis.com"

// full audit trail

The full breakdown of what we checked, the deductions that landed, the network hosts, the dependency advisories, and concrete fix guidance is available to verified publishers.

// improvement guidance — verified publishers only

We have 1 concrete improvement we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.

// embed badge in your README

[![M8ven Score](https://m8ven.ai/badge/mcp/lkbaba-gemini-mcp-1jf7au)](https://m8ven.ai/mcp/lkbaba-gemini-mcp-1jf7au)

commit: a17d8295704f4bc13dc8ac504f13fce6d9d82dcf

code hash: 011744030c3ca8506e1a1a73a7dda41fe95689a09d973d66a180e002c042229f

verified: 6/18/2026, 11:24:20 AM

view raw JSON →