Gemini (mintmcqueen) MCP Server
@mintmcqueen/gemini-mcp
npm
v0.4.0
Published by @mintmcqueen — no publish provenance, so origin is unverified, but the source is public: the repository link below is self-declared yet readable, so you can inspect the code before adopting it.
Enhanced MCP server for Google Gemini 3 with Image Generation, Batch API integration (50% cost, async processing), advanced file handling, and conversation management. Features Gemini 3 Pro (default) and Gemini 3 Pro Image models with state-of-the-art rea
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 7 = 93. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −6 | capability blast radius (high) — client exposure if the model is manipulated |
| −1 | publisher verification (public source) — no provenance, but the source is public and inspectable |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 3
critical Completed toxic-flow trifecta across toolsMTC-FLOW-002
This server (without client built-ins) exposes a complete data-exfiltration chain: batch_create → delete_file → batch_create_embeddings. Untrusted input is ingested, private data is read, and it can be sent to an external sink via the agent composing the tools (→). Static analysis proves the primitive exists, not that a specific run will occur.
Fix: Remove one leg of the trifecta: isolate untrusted-input tools from secret-reading tools and from egress tools, or require human approval between them.
Location: flow batch_create → delete_file → batch_create_embeddings
medium Tool "delete_file" can modify the filesystemMTC-CAP-002
Tool "delete_file" can write, overwrite or delete files (keyword "delete_file" in tool name). Verify it is scoped to a safe directory.
Fix: Constrain file operations to an explicit, non-sensitive root; reject path traversal.
Location: tool delete_file
low Mutating tool "delete_file" declares no destructiveHintMTC-CAP-005
Tool "delete_file" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool delete_file
Tools 24
Each tool and what it can reach — statically extracted from the published source.
batch_createingests untrusted inputnetwork egressbatch_create_embeddingsingests untrusted inputnetwork egressdelete_filereads sensitive datawrites filesbatch_deleteingests untrusted inputbatch_download_resultsingests untrusted inputbatch_processingests untrusted inputchatnetwork egressget_filereads sensitive datalist_filesreads sensitive dataupload_filenetwork egress
Show 14 more tools ↓
upload_multiple_filesnetwork egressActive Conversationsno sensitive capabilityAvailable Gemini Modelsno sensitive capabilitybatch_cancelno sensitive capabilitybatch_get_statusno sensitive capabilitybatch_ingest_contentno sensitive capabilitybatch_ingest_embeddingsno sensitive capabilitybatch_process_embeddingsno sensitive capabilitybatch_query_task_typeno sensitive capabilitycleanup_all_filesno sensitive capabilityclear_conversationno sensitive capabilitygenerate_imagesno sensitive capabilitystart_conversationno sensitive capabilityUploaded Filesno sensitive capability
Toxic flows 1
Cross-tool combinations that form a data-exfiltration primitive (untrusted input → sensitive source → external sink).
What this scan could not see
- Tools were statically extracted from the published source (24 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Versions 1
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v0.4.0 latest |
A 93/100 | 3 | 1.13.0 | 2026-09-07 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan @mintmcqueen/gemini-mcp --onlineOther implementations of Gemini 15
Independent packages implementing the same tool, scanned with the same engine. Compare all 16 side by side →
A thin, stdio Model Context Protocol (MCP) server exposing the Google Gemini API as composable primitives: chat, web search, role-based agents, multimodal analysis, image generation, code execution, and file management.
Gemini MCP Server
Model Context Protocol (MCP) server for Google Gemini 2.5 Pro with conversation context management
MCP server for Google Gemini API integration
MCP server for Gemini 3.1 Pro focused on UI generation and frontend development
Gemini image-generation MCP server for Claude — developed and maintained by AI (Claude Code)
More in AI, Memory & Reasoning
FDA device & vehicle recall risk for AI agents: recall history, MAUDE trend, risk score.
Open-source MCP server exposing Agent402.Tools' catalog — 500+ strong: 400+ self-hostable tools + 100 multi-tool skill packs (security-audit, trend-analysis, structured-scrape, decode-blob, forecasting-bake-off) for AI agents — browser, web search & answe
Zero-dependency MCP server that gives AI agents a self-updating project memory in AGENTS.md. Returns merge instructions instead of mutating state, so every change is a reviewable diff.
MCP Apps UI resources and server helpers for n8n
MCP server providing comprehensive access to BookStack knowledge management system
MCP server for tracking achievements with STAR methodology