Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
HOSTNoHost for HTTP server (HTTP only).127.0.0.1
PORTNoPort for HTTP server (HTTP only).3000
LOG_LEVELNoLog level: debug, info, warn, error.info
BOOKMARKS_FILENoPath to the bookmarks JSON file../data/bookmarks.json

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": true
}
prompts
{
  "listChanged": true
}
resources
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
add_bookmarkA

Save a URL to the user's reading list. Rejects duplicate URLs. Returns the created bookmark including its generated id.

search_bookmarksA

Search the reading list by free text, tag, and/or read status. Call without arguments to list the most recent bookmarks.

mark_readA

Mark a bookmark as read. Safe to call repeatedly.

delete_bookmarkA

Permanently delete a bookmark from the reading list.

Prompts

Interactive templates invoked by user choice

NameDescription
reading_digestBuild a prioritized digest of unread bookmarks, optionally scoped to one tag.

Resources

Contextual data attached and managed by the client

NameDescription
all-bookmarksThe complete reading list as JSON, newest first.
bookmark-statsTotals and per-tag counts for the reading list.

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/privatenesk/playground_mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server