veyra-snippets
Code snippet storage for AI agents with language tags and full-text search. Reads are free, writes require Veyra commit mode.
README
veyra-snippets
A persistent code snippet manager MCP tool for AI agents, with language filtering, tag search, and full-text code search. Reads are always free. Write operations require Veyra commit mode authorization.
Overview
veyra-snippets gives AI agents a reliable code library backed by SQLite. Agents can freely browse and search snippets. Saving, updating, and deleting snippets is protected by Veyra commit mode — ensuring intentional, accountable writes.
Installation
npm install
npm run build
Snippets are stored at ~/.veyra-snippets/data.db, created automatically on first run.
MCP Configuration (Claude Desktop)
Add the following to your claude_desktop_config.json:
{
"mcpServers": {
"veyra-snippets": {
"command": "node",
"args": ["/absolute/path/to/veyra-snippets/dist/index.js"]
}
}
}
Tools
| Tool | Input | Class | Price |
|---|---|---|---|
list_snippets |
{ language?, tag? } |
— | FREE |
get_snippet |
{ id } |
— | FREE |
search_snippets |
{ query } |
— | FREE |
save_snippet |
{ title, code, language, tags?, veyra_token? } |
A | €0.005 |
update_snippet |
{ id, code?, title?, veyra_token? } |
A | €0.005 |
delete_snippet |
{ id, veyra_token? } |
B | €0.02 |
Examples
Read (no token needed)
// List all snippets
{ "tool": "list_snippets", "arguments": {} }
// List TypeScript snippets
{ "tool": "list_snippets", "arguments": { "language": "typescript" } }
// List snippets by tag
{ "tool": "list_snippets", "arguments": { "tag": "auth" } }
// Get a specific snippet
{ "tool": "get_snippet", "arguments": { "id": "1712345678-abc1234" } }
// Search across title, code, language, and tags
{ "tool": "search_snippets", "arguments": { "query": "debounce" } }
Write (Veyra token required)
// Save a new snippet
{
"tool": "save_snippet",
"arguments": {
"title": "Debounce utility",
"code": "function debounce(fn, ms) {\n let timer;\n return (...args) => {\n clearTimeout(timer);\n timer = setTimeout(() => fn(...args), ms);\n };\n}",
"language": "javascript",
"tags": "utility,performance",
"veyra_token": "vt_..."
}
}
// Update snippet code
{
"tool": "update_snippet",
"arguments": {
"id": "1712345678-abc1234",
"code": "// updated code here",
"veyra_token": "vt_..."
}
}
// Delete a snippet
{
"tool": "delete_snippet",
"arguments": {
"id": "1712345678-abc1234",
"veyra_token": "vt_..."
}
}
Error response when token is missing
{
"error": "VeyraCommitRequired",
"message": "Write operations require Veyra commit mode.",
"currentMode": "open",
"requiredMode": "commit",
"transitionStrategy": "authorize_then_retry_with_x_veyra_token",
"provider": "veyra",
"authorize_endpoint": "https://api.veyra.to/v1/authorize-action",
"docs_url": "https://veyra.to"
}
How Veyra Works
Veyra is a commit-mode authorization layer for AI agents. When an agent attempts a write operation:
- The agent calls the tool without a
veyra_tokenand receives aVeyraCommitRequirederror with anauthorize_endpoint. - The agent (or the user on its behalf) calls the authorize endpoint to obtain a token.
- The agent retries the tool call with
veyra_tokenset. veyra-snippetsverifies the token via@veyrahq/sdk-nodebefore executing the write.
See veyra.to for full documentation.
License
MIT
Hosted Pack (recommended)
Prefer the hosted pack for one-URL integration:
{
"mcpServers": {
"veyra": {
"url": "https://mcp.veyra.to/sse"
}
}
}
One URL. 48 tools. 24 free reads. 24 protected writes.
Hosted pack: https://mcp.veyra.to/sse
Pack manifest: https://mcp.veyra.to/.well-known/veyra-pack.json
Use the hosted pack when you want the fastest MCP integration path across all Veyra tool families. Use this standalone package when you specifically want this tool on its own.
Part of the Veyra Ecosystem
Veyra is commit mode for production AI agent actions. All tools: reads free, writes require Veyra commit mode.
| Tool | Description | Install |
|---|---|---|
| veyra-memory | Key-value memory store | npm i -g veyra-memory |
| veyra-notes | Note-taking with tags | npm i -g veyra-notes |
| veyra-tasks | Task management | npm i -g veyra-tasks |
| veyra-bookmarks | Bookmark manager | npm i -g veyra-bookmarks |
| veyra-contacts | Contact management | npm i -g veyra-contacts |
| veyra-forms | Form builder | npm i -g veyra-forms |
| veyra-webhooks | Webhook sender | npm i -g veyra-webhooks |
SDK: npm install @veyrahq/sdk-node Website: veyra.to
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。