veyra-bookmarks
Provides persistent bookmark storage using SQLite database, enabling AI agents to maintain a structured link library with tag filtering, categories, and full-text search capabilities.
Supports bookmark management for TypeScript documentation and resources, allowing AI agents to save, search, and organize TypeScript-related links with tagging and categorization.
veyra-bookmarks
A bookmark and link manager MCP tool for AI agents, with tag filtering, categories, and full-text search. Reads are always free. Write operations require Veyra commit mode authorization.
Overview
veyra-bookmarks gives AI agents a persistent link library backed by SQLite. Agents can freely browse and search bookmarks. Saving, updating, and deleting requires Veyra commit mode.
Installation
npm install
npm run buildData is stored at ~/.veyra-bookmarks/data.db, created automatically on first run.
MCP Configuration (Claude Desktop)
{
"mcpServers": {
"veyra-bookmarks": {
"command": "node",
"args": ["/absolute/path/to/veyra-bookmarks/dist/index.js"]
}
}
}Tools
Tool | Input | Class | Price |
|
| — | FREE |
|
| — | FREE |
|
| — | FREE |
|
| A | €0.005 |
|
| A | €0.005 |
|
| B | €0.02 |
Examples
Read (no token needed)
// List all bookmarks
{ "tool": "list_bookmarks", "arguments": {} }
// Filter by category
{ "tool": "list_bookmarks", "arguments": { "category": "research" } }
// Search by keyword
{ "tool": "search_bookmarks", "arguments": { "query": "typescript" } }Write (Veyra token required)
// Save a bookmark
{
"tool": "save_bookmark",
"arguments": {
"url": "https://www.typescriptlang.org/docs/",
"title": "TypeScript Docs",
"tags": "typescript,docs,reference",
"category": "development",
"veyra_token": "vt_..."
}
}
// Update tags/category
{
"tool": "update_bookmark",
"arguments": {
"id": "1712345678-abc1234",
"tags": "typescript,docs,pinned",
"veyra_token": "vt_..."
}
}
// Delete
{
"tool": "delete_bookmark",
"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",
"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:
The agent calls the tool without
veyra_token→ receivesVeyraCommitRequiredwithauthorize_endpoint.The agent/user calls the authorize endpoint to obtain a token.
The agent retries with
veyra_tokenset.veyra-bookmarksverifies the token via@veyrahq/sdk-nodebefore executing the action.
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 |
Key-value memory store |
| |
Note-taking with tags |
| |
Task management |
| |
Code snippet storage |
| |
Contact management |
| |
Form builder |
| |
Webhook sender |
|
SDK: npm install @veyrahq/sdk-node Website: veyra.to
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Aquariosan/veyra-bookmarks'
If you have feedback or need assistance with the MCP directory API, please join our Discord server