MCP Server
MCP
io.github.capyBearista/gemini-researcher
Stateless MCP server that proxies research queries to Gemini CLI, reducing agent context/model usage
Install
npx -y [email protected]
Configuration Example
{
"remotes": [],
"packages": [
{
"registryType": "npm",
"identifier": "gemini-researcher",
"version": "1.0.2",
"transport": {
"type": "stdio"
},
"environmentVariables": [
{
"description": "Gemini API key (optional if you already authenticated Gemini CLI via \"gemini\" login)",
"format": "string",
"isSecret": true,
"name": "GEMINI_API_KEY"
},
{
"description": "Override the project root directory used for path validation (defaults to current working directory)",
"format": "string",
"name": "PROJECT_ROOT"
},
{
"description": "Chunk size threshold (KB) for large responses (default: 10)",
"format": "string",
"name": "RESPONSE_CHUNK_SIZE_KB"
},
{
"description": "Chunk cache TTL in milliseconds (default: 3600000 / 1 hour)",
"format": "string",
"name": "CACHE_TTL_MS"
},
{
"description": "Enable debug logging (set to \"true\" or \"1\")",
"format": "string",
"name": "DEBUG"
},
{
"description": "Vertex AI / Google auth: path to a service account JSON credentials file",
"format": "string",
"name": "GOOGLE_APPLICATION_CREDENTIALS"
},
{
"description": "Vertex AI / Google auth: GCP project ID (used by some auth configurations)",
"format": "string",
"name": "GOOGLE_CLOUD_PROJECT"
},
{
"description": "Vertex AI / Google auth: Vertex AI project identifier (used by some auth configurations)",
"format": "string",
"name": "VERTEX_AI_PROJECT"
}
]
}
]
}
mcp
model-context-protocol
npm
By
Comments
Sign in to leave a comment