Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
rememb_readA

Read all memory entries or filter by section. Safe, read-only operation with no side effects. Use this at the start of every session to load context. Prefer rememb_search when looking for specific information by keyword or topic.

rememb_read_pageA

Read a paginated slice of entries with server-side truncation. Best for browsing large stores without flooding the context window.

rememb_searchA

Search memory entries by content or tags using semantic similarity. Safe, read-only operation with no side effects. Use instead of rememb_read when you need to find specific entries by topic rather than loading all entries. Returns the top_k most relevant results ranked by similarity.

rememb_writeA

Save a new memory entry. Creates a new entry and returns its ID — does not overwrite existing entries. Use when you learn something new worth remembering across sessions. Use rememb_edit instead to update an existing entry by ID. semantic_scope controls whether semantic duplicate blocking checks globally or only inside the target section.

rememb_editA

Update an existing memory entry in-place by its ID. Modifies only the fields provided (content, section, or tags) — omitted fields are unchanged. Non-destructive: the entry is updated, not deleted and recreated. Use rememb_write to create new entries, rememb_delete to permanently remove one.

rememb_deleteA

Permanently delete a single memory entry by its ID. Deletion is irreversible — the entry cannot be recovered. No cascading side effects. Use rememb_edit to update instead. Use rememb_clear to delete all entries at once.

rememb_clearA

Permanently delete ALL memory entries at once. Irreversible — no recovery is possible after this operation. Requires confirm=true as a safety guard. Use rememb_delete to remove a single entry by ID instead. Only use this to fully reset the memory store.

rememb_statsA

Return memory usage statistics: total entries, size in KB, oldest and newest entry dates, and count per section. Safe, read-only operation with no side effects. Use to give the user an overview of their memory store or to decide if cleanup is needed.

rememb_consolidateA

Consolidate duplicate entries and merge metadata (tags and access data). Supports exact mode (default, normalized content match) and semantic mode (cosine similarity threshold). This mutates storage by removing redundant entries and keeping one consolidated record per duplicate group.

rememb_initA

Initialize rememb memory storage. Useful for explicit setup and recovery flows. Home-first root resolution also auto-initializes ~/.rememb when needed, and this tool remains idempotent and safe to call repeatedly.

rememb_list_skillsA

List bundled rememb skills discovered from the installed package contents. Safe, read-only operation.

rememb_use_skillA

Load one bundled rememb skill by identifier or exact declared name and return its instructions. Safe, read-only operation. Use rememb_list_skills first to inspect available skills.

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/LuizEduPP/Rememb'

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