grade D

4 days ago

mcp_so

MCP Gemini Server

This project provides a dedicated MCP (Model Context Protocol) server that wraps the @google/genai SDK. It exposes Google's Gemini model capabilities as standard MCP tools, allowing other LLMs (like Cline) or MCP-compatible systems to leverage Gemini's features as a backend workhorse.

→ bsmi021/mcp-gemini-server · listed on mcp_so

Install from

mcp.so

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: GITHUB_API_TOKEN, GOOGLE_GEMINI_API_KEY, MCP_CONNECTION_TOKEN

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.

configALLOWED_OUTPUT_PATHS— "": "/var/opt/mcp-gemini-server/outputs,/tmp/mcp-gemini-outputs" // Optional: Comma-separated list of allowed output directories for mcpCallServerTool and writeToFileTool

configENABLE_HEALTH_CHECK— Enable health check server (options: true, false; default: true)

configEXAMPLE_ENABLE_LOGS

configEXAMPLE_GREETING

configGEMINI_SAFE_FILE_BASE_DIR

🔐 secretGITHUB_API_TOKEN— Personal Access Token for GitHub API access (required for GitHub code review features). For public repos, token needs 'public_repo' and 'read:user' scopes. For private repos, token needs 'repo' scope.

🔐 secretGOOGLE_GEMINI_API_KEY— "": "YOUR_API_KEY",

configGOOGLE_GEMINI_CODE_MODELS

configGOOGLE_GEMINI_DEFAULT_MODEL

configGOOGLE_GEMINI_DEFAULT_THINKING_BUDGET— Default thinking budget in tokens (0-24576) for controlling model reasoning

configGOOGLE_GEMINI_ENABLE_URL_CONTEXT— Enable URL context features (options: true, false; default: false)

configGOOGLE_GEMINI_IMAGE_MODELS

configGOOGLE_GEMINI_IMAGE_RESOLUTION

configGOOGLE_GEMINI_MAX_IMAGE_SIZE_MB

configGOOGLE_GEMINI_MODEL— "": "gemini-1.5-flash", // Optional: Set a default model

configGOOGLE_GEMINI_MODELS

configGOOGLE_GEMINI_ROUTING_PREFER_COST

configGOOGLE_GEMINI_ROUTING_PREFER_QUALITY

configGOOGLE_GEMINI_ROUTING_PREFER_SPEED

configGOOGLE_GEMINI_SUPPORTED_IMAGE_FORMATS

configGOOGLE_GEMINI_URL_ALLOWED_DOMAINS— Comma-separated list or JSON array of allowed domains (default: for all domains)

configGOOGLE_GEMINI_URL_BLOCKLIST— Comma-separated list or JSON array of blocked domains (default: empty)

configGOOGLE_GEMINI_URL_CONVERT_TO_MARKDOWN— Convert HTML content to markdown (options: true, false; default: true)

configGOOGLE_GEMINI_URL_ENABLE_CACHING— Enable URL content caching (options: true, false; default: true)

configGOOGLE_GEMINI_URL_FETCH_TIMEOUT_MS— Fetch timeout per URL in milliseconds (default: 10000)

configGOOGLE_GEMINI_URL_INCLUDE_METADATA— Include URL metadata in context (options: true, false; default: true)

configGOOGLE_GEMINI_URL_MAX_CONTENT_KB— Maximum content size per URL in KB (default: 100)

configGOOGLE_GEMINI_URL_MAX_COUNT— Maximum URLs per request (default: 20)

configGOOGLE_GEMINI_URL_USER_AGENT— Custom User-Agent header for URL requests (default: MCP-Gemini-Server/1.0)

configHEALTH_CHECK_PORT— Port for health check HTTP server (default: 3000)

configMCP_CLIENT_ID— Default client ID used when this server acts as a client to other MCP servers (defaults to "gemini-sdk-client")

🔐 secretMCP_CONNECTION_TOKEN— "": "YOUR_GENERATED_CONNECTION_TOKEN", // Required: Use the token from step 4

configMCP_ENABLE_STREAMING— Enable SSE streaming for HTTP transport (options: true, false; default: false)

configMCP_LOG_LEVEL— Log level for MCP operations (options: debug, info, warn, error; default: info)

configMCP_SERVER_HOST— "": "localhost", // Required: Server host

configMCP_SERVER_PORT— "": "8080", // Required: Server port

configMCP_SESSION_TIMEOUT— Session timeout in seconds for HTTP transport (default: 3600 = 1 hour)

configMCP_TRANSPORT— Transport to use for MCP server (options: stdio, sse, streamable, http; default: stdio)

configMCP_TRANSPORT_TYPE— Deprecated - Use MCP_TRANSPORT instead

configMCP_WS_PORT— Deprecated - Use MCP_SERVER_PORT instead

configPORT

configSESSION_STORE_TYPE— Session storage backend (memory or sqlite; default: memory)

configSQLITE_DB_PATH— Path to SQLite database file when using sqlite store (default: ./data/sessions.db)

// 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 6 concrete improvements 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/bsmi021-mcp-gemini-server-1rdvif)](https://m8ven.ai/mcp/bsmi021-mcp-gemini-server-1rdvif)

commit: 8e449d13adb13a4e8de5b1d27a125921a4eb7eb2

code hash: 24d2cbd4eccd2ce27b5abd28967a6754f4e9a9beec0c00b73fa1d5552214316e

verified: 4/18/2026, 7:16:54 PM

view raw JSON →