mcp-gemini-server (bsmi021/mcp-gemini-server) is an MCP server listed on the M8ven Trust Index. It scores 53 out of 100, grade D. It declares 6 tools. No publisher has claimed this listing.

Caution

53/100

mcp-gemini-server

Item: mcp-gemini-server
Rating: 53
Author: M8ven

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

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every push why connect →

Who stands behind it

bsmi021

Source: mcp.so · also listed on github_topic

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. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

⚡ Connect GitHub for Live Monitored

Install from

mcp.sonot scored here GitHub

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings

🚨

Known vulnerabilities in dependencies: 1 critical, 3 high

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

🔐

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.

// known CVEs in dependencies1 critical3 high1 low

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

criticalvitest@3.1.4GHSA-5xrq-8626-4rwp

When Vitest UI server is listening, arbitrary file can be read and executed

high@modelcontextprotocol/sdk@1.11.5GHSA-345p-7cg4-v4c7

@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse

high@modelcontextprotocol/sdk@1.11.5GHSA-8r9q-7v3j-jr4g

Anthropic's MCP TypeScript SDK has a ReDoS vulnerability

high@modelcontextprotocol/sdk@1.11.5GHSA-w48q-cv73-mx4w

Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default

lowuuid@9.0.1GHSA-w5hq-g745-h8pq

uuid: Missing buffer bounds check in v3/v5/v6 when buf is provided

Depend on this server? Get alerted when its CVEs change.Watch this server free →

// environment variables

To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.

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

configEXAMPLE_ENABLE_LOGS

configEXAMPLE_GREETING

configGEMINI_SAFE_FILE_BASE_DIR

🔐 secretGITHUB_API_TOKENPersonal 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_BUDGETDefault thinking budget in tokens (0-24576) for controlling model reasoning

configGOOGLE_GEMINI_ENABLE_URL_CONTEXTEnable 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_DOMAINSComma-separated list or JSON array of allowed domains (default: for all domains)

configGOOGLE_GEMINI_URL_BLOCKLISTComma-separated list or JSON array of blocked domains (default: empty)

configGOOGLE_GEMINI_URL_CONVERT_TO_MARKDOWNConvert HTML content to markdown (options: true, false; default: true)

configGOOGLE_GEMINI_URL_ENABLE_CACHINGEnable URL content caching (options: true, false; default: true)

configGOOGLE_GEMINI_URL_FETCH_TIMEOUT_MSFetch timeout per URL in milliseconds (default: 10000)

configGOOGLE_GEMINI_URL_INCLUDE_METADATAInclude URL metadata in context (options: true, false; default: true)

configGOOGLE_GEMINI_URL_MAX_CONTENT_KBMaximum content size per URL in KB (default: 100)

configGOOGLE_GEMINI_URL_MAX_COUNTMaximum URLs per request (default: 20)

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

configHEALTH_CHECK_PORTPort for health check HTTP server (default: 3000)

configMCP_CLIENT_IDDefault 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_STREAMINGEnable SSE streaming for HTTP transport (options: true, false; default: false)

configMCP_LOG_LEVELLog 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_TIMEOUTSession timeout in seconds for HTTP transport (default: 3600 = 1 hour)

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

configMCP_TRANSPORT_TYPEDeprecated - Use MCP_TRANSPORT instead

configMCP_WS_PORTDeprecated - Use MCP_SERVER_PORT instead

configSESSION_STORE_TYPESession storage backend (memory or sqlite; default: memory)

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

// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

6/6 tools missing one or more hints — gemini_cache (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); gemini_chat (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); gemini_generate_content (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +3 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Shell command execution

1 child_process/subprocess call in production code — runs shell commands (src/services/mcp/McpClientService.ts:560)

Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.

Production dependencies are patched

0 critical, 3 high severity in production deps — @modelcontextprotocol/sdk@1.11.5 (high), @modelcontextprotocol/sdk@1.11.5 (high)

Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.

Dev dependencies

1 critical/high in dev-only deps (does not ship to users)

Upgrade dev dependencies when convenient.

Dependency freshness

2/19 production deps stale: gitdiff-parser@2023-03-14 (3.4y), node-fetch@2023-11-30 (2.7y)

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail

The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.

// improvement guidance — verified publishers only

We have 5 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 Verified](https://m8ven.ai/badge/mcp/bsmi021/mcp-gemini-server?variant=verified)](https://m8ven.ai/mcp/bsmi021/mcp-gemini-server)

Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.

commit: 8e449d13adb13a4e8de5b1d27a125921a4eb7eb2

code hash: 24d2cbd4eccd2ce27b5abd28967a6754f4e9a9beec0c00b73fa1d5552214316e

view raw JSON →

Check MCPs from inside your assistant

Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check

check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern

How to add it →Free · no account needed · works in any MCP client