io.github.hampsterx/gemini-mcp-bridge

io.github.hampsterx/gemini-mcp-bridge·v0.6.0·AI & LLMs

MCP server wrapping Gemini CLI: query, review, search, structured output, and diff assessment.

Trust verdict · v1 advisory · method

NOT YET SCREENEDno verdict on file

Verdict not yet evaluated for this tool. The semantic screen takes adversarial cases first; coverage rolls out as the corpus expands (15/150 labels to graduation). The deterministic conformance probe is built but has not yet run on the public corpus, so a recorded verdict here is REVIEW or UNVERIFIED, never a clearing ALLOW. Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: the eval, four-state verdict, honest limits.

Own this server? Screen its description →

Environment variables

GEMINI_CLI_PATH

Path to the gemini CLI binary. Defaults to 'gemini' on PATH.

GEMINI_DEFAULT_MODEL

Default Gemini model for query/review/search.

GEMINI_FALLBACK_MODEL

Model to use when the primary model hits a quota or availability error.

GEMINI_MAX_CONCURRENT

Maximum concurrent Gemini CLI subprocesses (default 3).

GEMINI_MIN_INVOCATION_GAP_MS

Minimum milliseconds between consecutive CLI spawns, used to avoid rate-limit bursts.

GEMINI_SPAWN_JITTER_MAX_MS

Upper bound of random jitter added to each CLI spawn to spread load.

GEMINI_API_KEY

secret

API key for Gemini. Alternative to GOOGLE_API_KEY or OAuth login.

GOOGLE_API_KEY

secret

Google API key for Gemini. Alternative to GEMINI_API_KEY or OAuth login.

MCP quality score · maturity, not trust · methodology

freshness

completeness

installability

documentation

stability

Alternatives in AI & LLMs

OpenAI Tools MCP Server

ai.com.mcp/openai-tools

Focused MCP server for OpenAI image/audio generation (v2.0.0). Wraps endpoints via HAPI CLI.

ai.llmse/mcp

Public MCP server for the LLM Search Engine

Ninar AI

ai.ninar/ninar

Audit your brand's visibility across ChatGPT, Gemini, Claude, Perplexity + 6 more engines.

Install

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "gemini-mcp-bridge": {
      "command": "npx",
      "args": [
        "-y",
        "gemini-mcp-bridge"
      ],
      "env": {
        "GEMINI_CLI_PATH": "gemini",
        "GEMINI_DEFAULT_MODEL": "<gemini_default_model>",
        "GEMINI_FALLBACK_MODEL": "<gemini_fallback_model>",
        "GEMINI_MAX_CONCURRENT": "3",
        "GEMINI_MIN_INVOCATION_GAP_MS": "5000",
        "GEMINI_SPAWN_JITTER_MAX_MS": "200",
        "GEMINI_API_KEY": "<your-gemini_api_key>",
        "GOOGLE_API_KEY": "<your-google_api_key>"
      }
    }
  }
}

Cursor (.cursor/mcp.json)

{
  "mcpServers": {
    "gemini-mcp-bridge": {
      "command": "npx",
      "args": [
        "-y",
        "gemini-mcp-bridge"
      ],
      "env": {
        "GEMINI_CLI_PATH": "gemini",
        "GEMINI_DEFAULT_MODEL": "<gemini_default_model>",
        "GEMINI_FALLBACK_MODEL": "<gemini_fallback_model>",
        "GEMINI_MAX_CONCURRENT": "3",
        "GEMINI_MIN_INVOCATION_GAP_MS": "5000",
        "GEMINI_SPAWN_JITTER_MAX_MS": "200",
        "GEMINI_API_KEY": "<your-gemini_api_key>",
        "GOOGLE_API_KEY": "<your-google_api_key>"
      }
    }
  }
}

Cline (cline_mcp_settings.json)

npx -y gemini-mcp-bridge

Verdict API

curl -s mcpindex.ai/api/v1/trust/server/io-github-hampsterx-gemini-mcp-bridge

Free-tier verdict as JSON: decision + dimensions + severity. Call it from your agent before it invokes a tool it just discovered.

Details

version: v0.6.0
category: AI & LLMs
quality: 78 / 100
operator: hampsterx

Provenance

Verdict history is anchored to Bitcoin via OpenTimestamps. The free tier returns the current verdict only; the anchored record is served on the authenticated tier.

Links

Repository →