Skip to main content
Glama
elvismdev

mem0-mcp-selfhosted

by elvismdev
OverviewSchemaRelated ServersScoreDiscussions
Python
Hybrid

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MEM0_USER_IDNoDefault user ID for memory scoping. Used to isolate memories between different users or projects.user
MEM0_PROVIDERNoTop-level provider ('anthropic' or 'ollama'). Cascades to MEM0_LLM_PROVIDER and MEM0_GRAPH_LLM_PROVIDER.anthropic
GOOGLE_API_KEYNoGoogle API key (required for 'gemini'/'gemini_split' graph providers).
MEM0_LLM_MODELNoModel for the selected LLM provider. Defaults to 'claude-opus-4-6' for Anthropic, 'qwen3:14b' for Ollama.claude-opus-4-6
MEM0_LOG_LEVELNoLogging level ('DEBUG', 'INFO', 'WARNING', 'ERROR').INFO
MEM0_NEO4J_URLNoNeo4j Bolt endpoint.bolt://127.0.0.1:7687
MEM0_TRANSPORTNoTransport mode: 'stdio', 'sse', or 'streamable-http'.stdio
MEM0_COLLECTIONNoQdrant collection name.mem0_mcp_selfhosted
MEM0_EMBED_DIMSNoEmbedding vector dimensions.1024
MEM0_NEO4J_USERNoNeo4j username.neo4j
MEM0_OLLAMA_URLNoShared Ollama base URL for LLM and embeddings.http://localhost:11434
MEM0_QDRANT_URLNoQdrant REST API URL.http://localhost:6333
MEM0_EMBED_MODELNoEmbedding model name.bge-m3
ANTHROPIC_API_KEYNoStandard Anthropic API key (priority 3).
MEM0_ENABLE_GRAPHNoEnable graph memory (entity extraction to Neo4j).false
MEM0_EMBED_PROVIDERNoEmbedding provider ('ollama' or 'openai').ollama
MEM0_NEO4J_PASSWORDNoNeo4j password.mem0graph
MEM0_QDRANT_API_KEYNoQdrant API key (for Qdrant Cloud).
MEM0_ANTHROPIC_TOKENNoAnthropic OAT or API token (priority 1). Overrides local credentials.
MEM0_HISTORY_DB_PATHNoSQLite path for memory change history.

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": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
add_memoryA

Store a new memory. Requires at least one of user_id, agent_id, or run_id.

search_memoriesC

Semantic search across existing memories.

get_memoriesA

Page through memories using filters instead of search.

get_memoryA

Fetch a single memory by its ID.

update_memoryA

Overwrite an existing memory's text. Re-embeds and re-indexes.

delete_memoryC

Delete a single memory.

delete_all_memoriesB

Bulk-delete all memories in the given scope. Requires at least one filter.

    NEVER calls memory.delete_all() — uses safe bulk-delete instead.
list_entitiesA

List which users/agents/runs currently hold memories.

Uses Qdrant Facet API (v1.12+) for server-side aggregation, with scroll+dedupe fallback for older versions.

delete_entitiesA

Delete an entity and cascade-delete all its memories.

    Functionally equivalent to delete_all_memories in self-hosted mode.
mcp_search_graphA

Search entities by name/id substring matching in Neo4j knowledge graph.

mcp_get_entityA

Get all relationships for a specific entity (bidirectional).

Prompts

Interactive templates invoked by user choice

NameDescription
memory_assistantQuick-start guide for using the mem0 memory server.

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/elvismdev/mem0-mcp-selfhosted'

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