bilibili-huasheng-video
v0.5.0
MCP ServerMCP Registry
io.github.superlcr/bilibili-huasheng-video
Script to finished Bilibili video with Huasheng: storyboard, narration, footage, export, publish.
stdionpmregistry 收录
io.github.capyBearista/gemini-researcher · v1.0.2
Stateless MCP server that proxies research queries to Gemini CLI, reducing agent context/model usage
gemini-researcher 是一个MCP Server，收录自 官方 MCP Registry。支持 stdio 传输。本页提供 Cursor、Claude Code 等客户端的安装配置片段。
选择你的平台查看安装方式
{
"mcpServers": {
"gemini-researcher": {
"command": "npx",
"args": [
"-y",
"gemini-researcher"
]
}
}
}GEMINI_API_KEY可选secretGemini API key (optional if you already authenticated Gemini CLI via "gemini" login)
PROJECT_ROOT可选Override the project root directory used for path validation (defaults to current working directory)
RESPONSE_CHUNK_SIZE_KB可选Chunk size threshold (KB) for large responses (default: 10)
CACHE_TTL_MS可选Chunk cache TTL in milliseconds (default: 3600000 / 1 hour)
DEBUG可选Enable debug logging (set to "true" or "1")
GOOGLE_APPLICATION_CREDENTIALS可选Vertex AI / Google auth: path to a service account JSON credentials file
GOOGLE_CLOUD_PROJECT可选Vertex AI / Google auth: GCP project ID (used by some auth configurations)
VERTEX_AI_PROJECT可选Vertex AI / Google auth: Vertex AI project identifier (used by some auth configurations)
v0.5.0
io.github.superlcr/bilibili-huasheng-video
Script to finished Bilibili video with Huasheng: storyboard, narration, footage, export, publish.
v0.7.0
com.cromanion/cromanion
Raise conversion on a site you manage. No API key, no human to wake — you prove the domain.
v0.1.2
io.github.agentwares/agentguard
MCP policy proxy: spend caps, approvals for destructive tools, kill switch, dry-run, audit log.
v0.1.0
io.github.pipeworx-io/china-air-quality
China Air Quality MCP — nationwide hourly AQI from CNEMC (中国环境监测总站).
v0.7.0
io.github.conorbronsdon/substack-mcp
Substack drafts, Notes, analytics and consented subscribers. Long-form posts stay draft-only.
v0.4.2
io.github.lvlrSajjad/simframe
Always-warm iOS Simulator frames: agents read the screen in ~20ms instead of screenshotting
{
"id": "io.github.capyBearista/gemini-researcher",
"type": "mcp-server",
"version": "1.0.2",
"displayName": "gemini-researcher",
"description": "Stateless MCP server that proxies research queries to Gemini CLI, reducing agent context/model usage",
"repository": {
"url": "https://github.com/capyBearista/gemini-researcher",
"source": "github"
},
"distribution": {
"packages": [
{
"registryType": "npm",
"identifier": "gemini-researcher",
"version": "1.0.2",
"transport": "stdio",
"environmentVariables": [
{
"name": "GEMINI_API_KEY",
"description": "Gemini API key (optional if you already authenticated Gemini CLI via \"gemini\" login)",
"isSecret": true
},
{
"name": "PROJECT_ROOT",
"description": "Override the project root directory used for path validation (defaults to current working directory)"
},
{
"name": "RESPONSE_CHUNK_SIZE_KB",
"description": "Chunk size threshold (KB) for large responses (default: 10)"
},
{
"name": "CACHE_TTL_MS",
"description": "Chunk cache TTL in milliseconds (default: 3600000 / 1 hour)"
},
{
"name": "DEBUG",
"description": "Enable debug logging (set to \"true\" or \"1\")"
},
{
"name": "GOOGLE_APPLICATION_CREDENTIALS",
"description": "Vertex AI / Google auth: path to a service account JSON credentials file"
},
{
"name": "GOOGLE_CLOUD_PROJECT",
"description": "Vertex AI / Google auth: GCP project ID (used by some auth configurations)"
},
{
"name": "VERTEX_AI_PROJECT",
"description": "Vertex AI / Google auth: Vertex AI project identifier (used by some auth configurations)"
}
]
}
],
"remotes": []
},
"dependencies": [],
"installTargets": [
"claude-code",
"claude-desktop",
"cursor",
"vscode",
"trae",
"cherry-studio",
"lingma",
"windsurf",
"cline",
"workbuddy"
],
"keywords": [],
"provenance": {
"origin": "official-mcp-registry",
"originalId": "io.github.capyBearista/gemini-researcher",
"originalUrl": "https://registry.modelcontextprotocol.io/v0.1/servers/io.github.capyBearista%2Fgemini-researcher/versions/latest",
"isOfficial": true,
"status": "active"
}
}