localmind

A fully local AI stack that provides OpenAI/Anthropic-compatible LLM API, embeddings, mem0 memory, and second-brain RAG via MCP tools, all running independently with no cloud dependencies.

→ shaul1991/localmind · 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

✅

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 4 credentials: EMBEDDINGS_KEY, LITELLM_MASTER_KEY, LOCALMIND_API_KEY, MCP_HTTP_TOKEN

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.

configBASE_URL

configBRAIN_BATCH— / BRAIN_CONCURRENCY / BRAIN_CHUNK_SIZE 32 / 4 / 2000 인덱싱 튜닝

configBRAIN_CHUNK_SIZE— BRAIN_BATCH / BRAIN_CONCURRENCY / 32 / 4 / 2000 인덱싱 튜닝

configBRAIN_CONCURRENCY— BRAIN_BATCH / / BRAIN_CHUNK_SIZE 32 / 4 / 2000 인덱싱 튜닝

configBRAIN_INDEX— NOTES_DIR>/.brain-index.json 임베딩 인덱스 위치. git/싱크 볼트를 안 더럽히려면 밖으로

configCLAUDE_JOB_DIR

🔐 secretEMBEDDINGS_KEY

configEMBEDDINGS_MODEL— text-embedding-3-small (게이트웨이가 bge-m3로 매핑)

configEMBEDDINGS_URL— bge-m3 그대로 + GPU/전용 임베딩 서버(TEI/Infinity) 로 교체 (한국어 품질 유지하며 가속, 권장)

configEMBED_RETRIES

configEMBED_TIMEOUT_MS

🔐 secretLITELLM_MASTER_KEY— OPENAI_API_KEY=sk-local # 값

🔐 secretLOCALMIND_API_KEY— (없음) localmind 인증 시

configLOCALMIND_URL

configMCP_DEFAULT_MODEL— sonnet ask / ask_brain 기본 모델

configMCP_HTTP_ALLOW_NOAUTH

configMCP_HTTP_HOST— MCP_HTTP_PORT / 8788 / 0.0.0.0 원격 MCP 바인딩

configMCP_HTTP_PORT— / MCP_HTTP_HOST 8788 / 0.0.0.0 원격 MCP 바인딩

🔐 secretMCP_HTTP_TOKEN— .env에 설정 후 make up-mcp → 노트북에서 서버별 원격 MCP로 접속 (아래 디바이스/서버별 관리)

configMCP_HTTP_URL

configMCP_INSTANCE— 서버마다 =서버명으로 독립 인스턴스 → 그 서버의 자원/메모리/노트를 로컬에서 관리

configMEMORY_BACKUP_FILE

configMODEL— sonnet npm run smoke # claude 백엔드

configNOTES_DIR— "env": { "": "/내/노트/폴더", "OPENMEMORY_USER": "내이름" }

configOPENMEMORY_URL

configOPENMEMORY_USER— "env": { "NOTES_DIR": "/내/노트/폴더", "": "내이름" }

// 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 6 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/shaul1991-localmind-1e8skr)](https://m8ven.ai/mcp/shaul1991-localmind-1e8skr)

commit: fde778daf824cbc7b10ecf4c21e071a6433e4e80

code hash: 79280848ac99e4e09cea797f11a2c7340e046d53f38c1d449149f8bb21f520a4

verified: 6/28/2026, 9:08:33 AM

view raw JSON →