veyra-notes
Uses SQLite as the persistent storage backend for note data, providing reliable data persistence and query capabilities for the note-taking system.
veyra-notes
A persistent note system MCP tool for AI agents, with tag filtering and full-text search. Reads are always free. Write operations require Veyra commit mode authorization.
Overview
veyra-notes gives AI agents a reliable note-taking layer backed by SQLite. Agents can freely read, list, and search notes. Creating, updating, and deleting notes is protected by Veyra commit mode — ensuring intentional, accountable writes.
Installation
npm install
npm run buildNotes are stored at ~/.veyra-notes/data.db, created automatically on first run.
MCP Configuration (Claude Desktop)
Add the following to your claude_desktop_config.json:
{
"mcpServers": {
"veyra-notes": {
"command": "node",
"args": ["/absolute/path/to/veyra-notes/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 notes
{ "tool": "list_notes", "arguments": {} }
// List notes by tag
{ "tool": "list_notes", "arguments": { "tag": "project-x" } }
// Get a specific note
{ "tool": "get_note", "arguments": { "id": "1712345678-abc1234" } }
// Search across title, content, and tags
{ "tool": "search_notes", "arguments": { "query": "meeting notes" } }Write (Veyra token required)
// Create a note
{
"tool": "create_note",
"arguments": {
"title": "Sprint Planning",
"content": "Goals for this sprint: ...",
"tags": "work,planning",
"veyra_token": "vt_..."
}
}
// Update a note
{
"tool": "update_note",
"arguments": {
"id": "1712345678-abc1234",
"content": "Updated content...",
"veyra_token": "vt_..."
}
}
// Delete a note
{
"tool": "delete_note",
"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-notesverifies the token via@veyrahq/sdk-nodebefore executing the write.
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-notes'
If you have feedback or need assistance with the MCP directory API, please join our Discord server