Atlas / MCP servers / elvismdev / Mem0

Mem0CAUTION

Name: Mem0
Author: elvismdev

mcp/elvismdev/mem0-12

MCP server by elvismdev · ai memory · anthropic · claude code · Audited 2026-10-07

Self-hosted mem0 MCP server for Claude Code. Run a complete memory server against self-hosted Qdrant + Neo4j + Ollama while using Claude as the main LLM.

Verdict

CAUTION

Grade

Trust score

79 /100

Exposed tools

5 4r · 0w · 1d

Transport

sse · stdio · streamable-http

License

MIT

Stars

109

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

Self-hosted mem0 MCP server for Claude Code. Run a complete memory server against self-hosted Qdrant + Neo4j + Ollama, with your choice of Anthropic (Claude) or Ollama as the main LLM.

Uses the mem0ai package directly as a library, supports both Claude's OAT token and fully local Ollama setups, and exposes 11 MCP tools for full memory management.

Prerequisites

Python >= 3.10 and uv.

Authentication: The default setup uses Claude (Anthropic) as the LLM for fact extraction. No API key needed, the server automatically uses your Claude Code session token. For fully local setups, set MEM0_PROVIDER=ollama. See Authentication for advanced options.

Quick Start

Default (Anthropic)

Add the MCP server globally (available across all projects):

claude mcp add --scope user --transport stdio mem0 \
--env MEM0_USER_ID=your-user-id \
-- uvx --from git+https://github.com/elvismdev/mem0-mcp-selfhosted.git mem0-mcp-selfhosted

All defaults work out of the box: Qdrant on localhost:6333, Ollama embeddings on localhost:11434 with bge-m3 (1024 dims). Override any default via --env (see Configuration).

uvx automatically downloads, installs, and runs the server in an isolated environment, no manual installation nee

Read from source at commit d67a3438492aOBSERVED · 2026-10-07

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code

claude mcp add mem0-mcp-selfhosted --env ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY} --env GOOGLE_API_KEY=${GOOGLE_API_KEY} --env MEM0_ANTHROPIC_TOKEN=${MEM0_ANTHROPIC_TOKEN} -- uvx mem0-mcp-selfhosted

claude-desktop

{
  "mcpServers": {
    "mem0-mcp-selfhosted": {
      "command": "uvx",
      "args": [
        "mem0-mcp-selfhosted"
      ],
      "env": {
        "ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}",
        "GOOGLE_API_KEY": "${GOOGLE_API_KEY}",
        "MEM0_ANTHROPIC_TOKEN": "${MEM0_ANTHROPIC_TOKEN}"
      }
    }
  }
}

Exposed tools (5)

4 read · 0 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.

Tool	Risk	Description
`delete_memory`	destructive	Delete a single memory.
`get_memory`	read	Fetch a single memory by its ID.
`list_entities`	read	List which users/agents/runs currently hold memories.
`mcp_get_entity`	read	Get all relationships for a specific entity (bidirectional).
`mcp_search_graph`	read	Search entities by name/id substring matching in Neo4j knowledge graph.

Trust audit

CAUTIONgrade C · trust 79/100 Install with care. The audit found things worth knowing before you trust its output.

Layer	What it checks	Result
L0	Provenance & inventory	PASS
L1	Static analysis of the code	WARN
L2	Instruction surface (what it tells the agent)	PASS
L3	Class-specific surface	WARN
L4	Behavioural (sandbox)	SKIPPED

What the source does

Filesystem: declared (1 observation(s))
Network: declared (2 observation(s))
Shell: none-observed
Dependencies: pinned
Secrets in source: found

Findings (11)

MEDIUMHard-coded secrets · secret.anthropic · CWE-798, CWE-321

tests/unit/test_llm_anthropic.py:129

OAT_TOKEN = "sk-ant-oat01-test-token-old"

MEDIUMHard-coded secrets · secret.anthropic · CWE-798, CWE-321

tests/unit/test_llm_anthropic.py:130

OAT_TOKEN_NEW = "sk-ant-oat01-test-token-new"

MEDIUMHard-coded secrets · secret.anthropic · CWE-798, CWE-321

tests/unit/test_llm_anthropic.py:487

REFRESH_TOKEN_NEW = "sk-ant-ort01-test-refresh-new"

MEDIUMHard-coded secrets · secret.generic · CWE-798, CWE-321

tests/unit/test_llm_anthropic.py:131

API_KEY = "sk-ant-api03-test-key"

MEDIUMFilesystem / path · mcp.destructive_tools · CWE-22, CWE-59

delete_memory

Why it matters. 1 tool(s) can delete or overwrite

Fix. prefer a read-only mode or scoped tokens; the page states the blast radius

LOWInventory / provenance · inv.hidden_file · CWE-1104

.coderabbit.yaml

.coderabbit.yaml

Why it matters. hidden member outside the usual dotfiles

Fix. review its purpose