io.github.capyBearista/gemini-researcher

io.github.capyBearista/gemini-researcherv1.0.2AI & LLMs

Stateless MCP server that proxies research queries to Gemini CLI, reducing agent context/model usage

In-path gate · all MCP tools

Using io.github.capyBearista/gemini-researcher in Claude, Cursor, Gemini CLI, Cline, or Zed?

MCP tool contracts can change remotely with no version bump. The mcpindex gate pins each contract and HOLDs the call when it drifts-before your agent acts. Zero credentials. This is not the package install for this server itself (use Install this server for that).

Install the mcpindex gate (one command)

Rewrites your MCP host config so each server launches behind the gate. Inspect first: curl -fsSL https://mcpindex.ai/install.sh | less

uv tool install mcpindex-gate && mcpindex-config-wire

Auditable install path →Watch it hold a drift →

Trust verdict · v1 advisory · method

REVIEWstatus: STALEfresh until 2026-07-01 10:12 UTC

screened 2026-06-01tier: scannedgranularity: description-levelsource: registry

Semantic screen found no manipulation pattern in the description. Conformance probe not yet run.

mcpindex.integrity.descriptionpassINFO

evidence“No hidden actions”via static_description

Limits of this verdict

- Semantic screen only - the deterministic conformance probe has not run on this server
- Confidence is reported but not yet calibrated (v1)
- Screen reads the tool description, not the live behavior
- advisory
- registry description only no input schema
- Past its expiry date - awaiting re-screen

Semantic screen: an LLM judge reads the tool description for hidden instructions (status PARTIAL). A pass means the description is not lying, not that the tool is safe: a high-capability tool with an honest description still warrants caution. The deterministic conformance probe has not been run on this server yet, so the screen here is semantic-only. Posture: advisory. Confidences are reported but not yet calibrated (calibrated=false at v1). Full verdict history is not shown on this page.

Own this server? Screen its description →

That verdict was true at screening time (snapshot 2026-07-31).

Contracts can change after screening, with no version bump. The gate pins io.github.capyBearista/gemini-researcher’s tool contracts on first sight and holds any silent change before your agent acts - the check that keeps being true on Tuesday.

See your first HOLD in 2 minutes →

Embed this badge

A live verdict badge for your README or listing. It reflects the current screen, links back here, and updates when the verdict does.

Markdown

[![mcpindex](https://mcpindex.ai/api/v1/badge/io-github-capybearista-gemini-researcher)](https://mcpindex.ai/server/io-github-capybearista-gemini-researcher)

HTML

<a href="https://mcpindex.ai/server/io-github-capybearista-gemini-researcher"><img src="https://mcpindex.ai/api/v1/badge/io-github-capybearista-gemini-researcher" alt="mcpindex verdict" height="20" /></a>

Environment variables

GEMINI_API_KEY

secret

Gemini API key (optional if you already authenticated Gemini CLI via "gemini" login)

PROJECT_ROOT

Override the project root directory used for path validation (defaults to current working directory)

RESPONSE_CHUNK_SIZE_KB

Chunk size threshold (KB) for large responses (default: 10)

CACHE_TTL_MS

Chunk cache TTL in milliseconds (default: 3600000 / 1 hour)

DEBUG

Enable debug logging (set to "true" or "1")

GOOGLE_APPLICATION_CREDENTIALS

Vertex AI / Google auth: path to a service account JSON credentials file

GOOGLE_CLOUD_PROJECT

Vertex AI / Google auth: GCP project ID (used by some auth configurations)

VERTEX_AI_PROJECT

Vertex AI / Google auth: Vertex AI project identifier (used by some auth configurations)

MCP quality score · maturity, not trust · methodology

freshness

completeness

installability

documentation

stability

Alternatives in AI & LLMs

Gemini FAF

one.faf/gemini-faf-mcp

Persistent project context for Google Gemini. Python/FastMCP. IANA-registered .faf format.

GPT55 Model Gateway

xyz.558686.gpt55/token-gateway

Remote MCP gateway for GPT-5.6 Luna, Soul, Terra, and x402-paid agent tools with no API key.

io.github.cerebrixos/tuning-engines

Domain-specific LLM fine-tuning — sovereign models trained on your data, zero infrastructure.

Install this server

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "gemini-researcher": {
      "command": "npx",
      "args": [
        "-y",
        "--",
        "gemini-researcher"
      ],
      "env": {
        "GEMINI_API_KEY": "<your-gemini_api_key>",
        "PROJECT_ROOT": "<project_root>",
        "RESPONSE_CHUNK_SIZE_KB": "<response_chunk_size_kb>",
        "CACHE_TTL_MS": "<cache_ttl_ms>",
        "DEBUG": "<debug>",
        "GOOGLE_APPLICATION_CREDENTIALS": "<google_application_credentials>",
        "GOOGLE_CLOUD_PROJECT": "<google_cloud_project>",
        "VERTEX_AI_PROJECT": "<vertex_ai_project>"
      }
    }
  }
}

Cursor (.cursor/mcp.json)

{
  "mcpServers": {
    "gemini-researcher": {
      "command": "npx",
      "args": [
        "-y",
        "--",
        "gemini-researcher"
      ],
      "env": {
        "GEMINI_API_KEY": "<your-gemini_api_key>",
        "PROJECT_ROOT": "<project_root>",
        "RESPONSE_CHUNK_SIZE_KB": "<response_chunk_size_kb>",
        "CACHE_TTL_MS": "<cache_ttl_ms>",
        "DEBUG": "<debug>",
        "GOOGLE_APPLICATION_CREDENTIALS": "<google_application_credentials>",
        "GOOGLE_CLOUD_PROJECT": "<google_cloud_project>",
        "VERTEX_AI_PROJECT": "<vertex_ai_project>"
      }
    }
  }
}

Cline (cline_mcp_settings.json)

npx -y -- gemini-researcher

Claude Code (claude mcp add)

claude mcp add --scope user gemini-researcher -- npx -y -- gemini-researcher

Gemini CLI (gemini mcp add)

gemini mcp add -s user gemini-researcher npx -y -- gemini-researcher

Verdict API

curl -s mcpindex.ai/api/v1/trust/server/io-github-capybearista-gemini-researcher

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

Details

version: v1.0.2
category: AI & LLMs
verdict expires: 2026-07-01
quality: 73 / 100
operator: capyBearista

Listing

Listed from the official MCP registry. Unclaimed by its maintainer. Maintainer? Email us →

Provenance

Each verdict is bound to a hash of the exact description it judged, so a re-crawl that changes the text produces a new record rather than silently inheriting this one. Verdict history is hash-chained and anchored to Bitcoin via OpenTimestamps (latest confirmed at block 960,209). Verify it yourself.

Links

Repository →