Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
CORS_ORIGINSYesComma-separated allowed CORS origins
SUPABASE_URLYesSupabase project URL
DASHBOARD_URLYesDash-AIMemory URL for login redirect
MCP_PUBLIC_URLYesPublic URL of this server (no trailing slash)
OPENAI_API_KEYNo(Optional) Vector search embeddings
OAUTH_CLIENT_IDYesOAuth client ID
ALLOWED_REDIRECT_URISYesComma-separated allowed redirect URIs
SUPABASE_SERVICE_ROLE_KEYYesSupabase service role key

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{}
prompts
{}
resources
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
rememberA

Save important information to long-term memory. Always set collection when the topic is clear: project work → project:, personal tastes → personal:preferences. Use append_to to extend an existing memory instead of creating duplicates. Vector search indexing completes asynchronously within a few seconds after save.

recallA

Search long-term memory. Call list_collections when scope is unclear. For GitHub/Notion synced content use collection project: (unified per project) or tags github/notion. Connect at dashboard.memxus.com/integrations. After this tool returns, show the user the pre-rendered block at the end of the tool result verbatim (user_facing_template). Do not repeat the raw context_block. Expand context: if count < total, recall/get_context with exclude_memory_ids + higher max_memories; if count === total, say no more memories without calling the server. Skills: use N → use_skill_in_chat, install N → install_skill, skip N → skip_skill.

get_contextA

Build a formatted context block for the current topic. Omit topic and collection to show the text collection picker (Memxus menu flow). Call list_collections when unsure of the exact slug. Partial collection names are resolved server-side. If the user's first message appears to be a coding task, technical question, or project-related request, call get_context with the detected topic BEFORE responding — do not wait for the user to ask. After this tool returns, show the user the pre-rendered block at the end of the tool result verbatim (user_facing_template). Do not repeat the raw context_block. Expand context: if count < total, recall/get_context with exclude_memory_ids + higher max_memories; if count === total, say no more memories without calling the server. Skills: use N → use_skill_in_chat, install N → install_skill, skip N → skip_skill.

list_memoriesB

List recent memories. Filter by collection, tags, or type to browse one group.

get_memoryA

Get the full content of a single memory by its UUID (from list_memories or recall).

list_collectionsA

List memory collections (folders/scopes) for this user. GitHub/Notion syncs appear under project: when unified collections are enabled. Call before scoped recall/get_context when the user mentions a project name.

forgetB

Delete a specific memory by ID.

memory_statsA

Show statistics about stored memories (by type and collection).

updateA

Update an existing memory by ID. Use mode replace (default) to patch fields, or append to extend content. Re-embeds only when content changes.

Prompts

Interactive templates invoked by user choice

NameDescription
memxus-contextLoad context from a Memxus collection
memxus-context-skillsLoad context + skill suggestions from a Memxus collection

Resources

Contextual data attached and managed by the client

NameDescription
Recent MemoriesYour most recent memories (count capped per plan)
Memxus Skill CardInteractive MCP Apps card for suggested skills
Memxus CollectionsCollection picker for Memxus context

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/gpitrella/memxus-remote-mcp'

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