/ 100

1 month ago

glama

mem0-agent-memory

Item: mem0-agent-memory
Rating: 56
Author: M8ven

An MCP server that provides persistent memory capabilities for AI agents using Mem0, enabling storage, search, and management of contextual information across conversations with support for multiple backends and LLM providers.

→ arunkumars-mf/mem0-agent-memory · listed on glama

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find.

Install from

Glama

M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.

// key findings

⚠️

Tool descriptions don’t match what handlers do

1 tool describes read intent but its handler mutates — setup_steering (line 2304: with open(filepath, "w", encoding="utf-8") as f:)

✅

No credential exfiltration, no sensitive file access, no obfuscation

Static analysis found nothing flowing your secrets to unexpected places.

✅

Open source with a license and README

Anyone can audit the code, the license is declared, and the publisher documents what it does.

🔐

You'll be asked for 1 credential: MEM0_API_KEY

These are read from process.env at runtime. Make sure you trust where they’ll be sent.

// required environment variables

This server reads these from process.env. You'll be asked to provide them before it can run.

configMEM0_TELEMETRY

configAWS_REGION— "": "us-west-2"

configOLLAMA_HOST— export ="http://localhost:11434"

configOLLAMA_EMBED_MODEL— export ="nomic-embed-text" # Default

configOLLAMA_LLM_MODEL— export ="llama3.2" # Default

configLMSTUDIO_HOST— export ="http://localhost:1234"

configLMSTUDIO_EMBED_MODEL— export ="text-embedding-nomic-embed-text-v1.5"

configLMSTUDIO_LLM_MODEL— export ="llama-3.2-3b-instruct"

configBEDROCK_EMBED_MODEL— export ="amazon.titan-embed-text-v2:0"

configBEDROCK_LLM_MODEL— export ="us.anthropic.claude-3-5-haiku-20241022-v1:0"

configBEDROCK_MAX_TOKENS— export ="1500" # Default: 1500

🔐 secretMEM0_API_KEY— export ="your-api-key"

configQDRANT_HOST— export ="localhost"

configQDRANT_PATH— export =".mem0/qdrant"

configOPENSEARCH_HOST— export ="your-opensearch-endpoint"

configQDRANT_PORT— export ="6333" # Optional

configFAISS_PATH— export ="/path/to/.mem0/memory" # Optional, defaults to .mem0/memory

configNOMIC_USE_PREFIXES— Note: For Nomic embeddings, set =true for better search accuracy.

configKUZU_DB_PATH

configMEM0_USER_ID— export ="custom-user-id" # Defaults to system username

configMEM0_AGENT_ID— export ="custom-agent-id" # Defaults to workspace name

configMEM0_RUN_ID— export ="session-123" # Optional: session partitioning

configMEM0_INFER_DEFAULT— export ="true" # LLM inference for fact extraction

configMEM0_VERBOSE— export ="false" # Compact responses (default) vs verbose

configMEM0_MAX_RELATIONS— export ="20" # Max graph relations in compact mode

configMEM0_MAX_RELEVANCE_SCORE

// full audit trail

The full breakdown of what we checked, the deductions that landed, the network hosts, the dependency advisories, and concrete fix guidance is available to verified publishers.

// improvement guidance — verified publishers only

We have 5 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.

// embed badge in your README

[![M8ven Score](https://m8ven.ai/badge/mcp/arunkumars-mf-mem0-agent-memory-sqksz8)](https://m8ven.ai/mcp/arunkumars-mf-mem0-agent-memory-sqksz8)

commit: f617adc9f83b9ca3cc4819a5bfcf5d91b996bc4b

code hash: e767c11a89c016468068782c6d87f90ab2fcf6d2cc1cd8b723726f996871f753

verified: 6/21/2026, 10:18:04 AM

view raw JSON →