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
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