RFP.ai
v1.0.1
ai.rfp/rfp-ai
Draft cited RFP and security questionnaire answers from your knowledge base, with human review
io.github.qmediat/gemini-code-context-mcp · v1.16.3
Gemini 2M context cache for Claude Code — persistent; repeat queries ~8x faster, ~4x cheaper.
gemini-code-context-mcp 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-code-context-mcp": {
"command": "npx",
"args": [
"-y",
"@qmediat.io/gemini-code-context-mcp"
]
}
}
}GEMINI_CREDENTIALS_PROFILE可选Profile name in ~/.config/qmediat/credentials (chmod 0600). Created by `npx @qmediat.io/gemini-code-context-mcp init`. Recommended; keeps your API key out of ~/.claude.json.
GEMINI_API_KEY可选secretFallback Tier 3 auth. Your Gemini API key. Emits a warning at startup recommending you move it to the credentials profile via the init command.
GEMINI_USE_VERTEX可选Set to `true` to use Vertex AI backend via Application Default Credentials. Requires GOOGLE_CLOUD_PROJECT.
GOOGLE_CLOUD_PROJECT可选GCP project ID when using Vertex AI backend. Only read when GEMINI_USE_VERTEX=true.
GEMINI_DAILY_BUDGET_USD可选Hard daily USD cap enforced locally. Server refuses calls after the cap until UTC midnight. Unlimited if unset. Honoured by `ask`, `code`, and per-iteration by `ask_agentic`.
GEMINI_CODE_CONTEXT_DEFAULT_MODEL可选Model alias (`latest-pro`, `latest-pro-thinking`, `latest-flash`, `latest-lite`, `latest-vision`) or literal model ID. Default: `latest-pro`.
GEMINI_CODE_CONTEXT_CACHE_TTL_SECONDS可选Context Cache TTL in seconds. Default: 3600 (1 hour). Hot workspaces (<10 min since last use) auto-refresh via background watcher.
GEMINI_CODE_CONTEXT_LOG_LEVEL可选`debug` | `info` | `warn` | `error`. Default: `info`.
v1.0.1
ai.rfp/rfp-ai
Draft cited RFP and security questionnaire answers from your knowledge base, with human review
v1.1.0
io.github.xenarch-ai/xenarch-mcp
Xenarch — x402 MCP server for AI agent payments. Non-custodial, USDC on Base L2.
v1.0.0
com.docimprint/api
AI document intelligence: extract, summarize, claim-check, and notarize with on-chain proofs.
v0.14.0
io.github.blackwell-systems/agent-lsp
Stateful LSP runtime for AI agents — 50+ tools across 30+ languages via MCP.
v0.2.13
io.github.hostinger/hostinger-api-mcp
MCP server for Hostinger API
v0.41.0
io.github.zhitongblog/unterm
The terminal AI agents can drive: spawn panes, run commands, read screens, scrolling screenshots.
{
"id": "io.github.qmediat/gemini-code-context-mcp",
"type": "mcp-server",
"version": "1.16.3",
"displayName": "gemini-code-context-mcp",
"description": "Gemini 2M context cache for Claude Code — persistent; repeat queries ~8x faster, ~4x cheaper.",
"repository": {
"url": "https://github.com/qmediat/gemini-code-context-mcp",
"source": "github"
},
"distribution": {
"packages": [
{
"registryType": "npm",
"identifier": "@qmediat.io/gemini-code-context-mcp",
"version": "1.16.3",
"transport": "stdio",
"environmentVariables": [
{
"name": "GEMINI_CREDENTIALS_PROFILE",
"description": "Profile name in ~/.config/qmediat/credentials (chmod 0600). Created by `npx @qmediat.io/gemini-code-context-mcp init`. Recommended; keeps your API key out of ~/.claude.json."
},
{
"name": "GEMINI_API_KEY",
"description": "Fallback Tier 3 auth. Your Gemini API key. Emits a warning at startup recommending you move it to the credentials profile via the init command.",
"isSecret": true
},
{
"name": "GEMINI_USE_VERTEX",
"description": "Set to `true` to use Vertex AI backend via Application Default Credentials. Requires GOOGLE_CLOUD_PROJECT."
},
{
"name": "GOOGLE_CLOUD_PROJECT",
"description": "GCP project ID when using Vertex AI backend. Only read when GEMINI_USE_VERTEX=true."
},
{
"name": "GEMINI_DAILY_BUDGET_USD",
"description": "Hard daily USD cap enforced locally. Server refuses calls after the cap until UTC midnight. Unlimited if unset. Honoured by `ask`, `code`, and per-iteration by `ask_agentic`."
},
{
"name": "GEMINI_CODE_CONTEXT_DEFAULT_MODEL",
"description": "Model alias (`latest-pro`, `latest-pro-thinking`, `latest-flash`, `latest-lite`, `latest-vision`) or literal model ID. Default: `latest-pro`."
},
{
"name": "GEMINI_CODE_CONTEXT_CACHE_TTL_SECONDS",
"description": "Context Cache TTL in seconds. Default: 3600 (1 hour). Hot workspaces (<10 min since last use) auto-refresh via background watcher."
},
{
"name": "GEMINI_CODE_CONTEXT_LOG_LEVEL",
"description": "`debug` | `info` | `warn` | `error`. Default: `info`."
}
]
}
],
"remotes": []
},
"dependencies": [],
"installTargets": [
"claude-code",
"claude-desktop",
"cursor",
"vscode"
],
"keywords": [],
"provenance": {
"origin": "official-mcp-registry",
"originalId": "io.github.qmediat/gemini-code-context-mcp",
"originalUrl": "https://registry.modelcontextprotocol.io/v0.1/servers/io.github.qmediat%2Fgemini-code-context-mcp/versions/latest",
"isOfficial": true,
"status": "active"
}
}