io.github.capyBearista/gemini-researcher MCP Server
io.github.capyBearista/gemini-researcher
What this kind of tool is for
- Let your agent search the web or a document set and cite what it found.
- Pull structured facts out of pages instead of copy-pasting by hand.
- Track changes on a topic over days without re-reading everything.
How to compare servers like this
- Source coverage:
- Check which engines, sites, or document types the tool can actually reach.
- Citation behavior:
- Prefer tools that return links you can open, not just summarized claims.
- Terms of service:
- Some sources forbid automated access; make sure the tool stays inside them.
- Maintenance signal:
- Scrapers break silently when pages change; recent commits are the best proxy.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
What is the io.github.capyBearista/gemini-researcher MCP server?
Stateless MCP server that proxies research queries to Gemini CLI, reducing agent context/model usage
How to install io.github.capyBearista/gemini-researcher
Copy-paste configuration for popular MCP clients.
GEMINI_API_KEYsecretGemini API key (optional if you already authenticated Gemini CLI via "gemini" login)
PROJECT_ROOTOverride the project root directory used for path validation (defaults to current working directory)
RESPONSE_CHUNK_SIZE_KBChunk size threshold (KB) for large responses (default: 10)
CACHE_TTL_MSChunk cache TTL in milliseconds (default: 3600000 / 1 hour)
DEBUGEnable debug logging (set to "true" or "1")
GOOGLE_APPLICATION_CREDENTIALSVertex AI / Google auth: path to a service account JSON credentials file
GOOGLE_CLOUD_PROJECTVertex AI / Google auth: GCP project ID (used by some auth configurations)
VERTEX_AI_PROJECTVertex AI / Google auth: Vertex AI project identifier (used by some auth configurations)
{
"mcpServers": {
"gemini-researcher": {
"command": "npx",
"args": [
"-y",
"gemini-researcher"
],
"env": {
"GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>",
"PROJECT_ROOT": "<YOUR_PROJECT_ROOT>",
"RESPONSE_CHUNK_SIZE_KB": "<YOUR_RESPONSE_CHUNK_SIZE_KB>",
"CACHE_TTL_MS": "<YOUR_CACHE_TTL_MS>",
"DEBUG": "<YOUR_DEBUG>",
"GOOGLE_APPLICATION_CREDENTIALS": "<YOUR_GOOGLE_APPLICATION_CREDENTIALS>",
"GOOGLE_CLOUD_PROJECT": "<YOUR_GOOGLE_CLOUD_PROJECT>",
"VERTEX_AI_PROJECT": "<YOUR_VERTEX_AI_PROJECT>"
}
}
}
}Related MCP servers

io.github.caraulani/euacc-mcp
Live EU funding data in your AI: grant calls, programmes, consortium partners, VCs, incubators.
Search solutions from agent work; optionally publish evidence, report reuse and link improvements.

GovRider
Match tech products and consulting services to live government tenders, grants, and RFPs

io.github.carlosalvite/foundersignal
Find SaaS ideas worth building. Revenue data, growth signals and pain points from 10+ sources.
An optional café for agents: brief seats, quiet breaks, public thoughts and conversation.

Test curl retries locally or inspect remote 429/503 Retry-After traces; optionally share findings.