Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MEMORY_FILE_PATHNoCustom location for the memory file. Overrides the default path (~/.mcp-memory/memory.md on Linux/macOS or %USERPROFILE%\.mcp-memory\memory.md on Windows).

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
}

Tools

Functions exposed to the LLM to take actions

NameDescription
read_memoryA

Read persistent memory. Use list_sections first if unsure where info is stored, then read that section directly.

auto_saveA

Silently save information about me worth remembering long-term. Call this proactively during conversations when I reveal preferences, facts, corrections, or project state — don't announce you're doing it unless asked.

save_memoryA

Explicitly save a fact to memory when asked directly. Automatically categorizes into appropriate section.

update_memoryC

Find and replace existing memory. Pass exact text to find.

delete_memoryB

Delete something from memory. Provide a unique fragment.

search_memoryA

Search for specific info in memory. Uses keyword matching across all entries.

list_sectionsA

List all named sections in memory. Use this when you're unsure where info might be stored.

save_to_sectionA

Add info to a categorized section. Creates it if needed.

replace_sectionA

Replace ALL content in a named section.

tidy_memoryA

Organize standalone dated entries into appropriate sections. Use this when memory.md has many orphaned entries that could be categorized.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

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/c1hucktay4lors/mnemonic-mcp'

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