45
/ 100
22 days ago
glama

M.I.M.I.R - Multi-agent Intelligent Memory & Insight Repository

Provides AI assistants with persistent graph database memory using Neo4j, enabling task management, relationship understanding, semantic search with embeddings, file indexing, and multi-agent coordination through the Model Context Protocol.

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

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

// key findings
🚨
Secret credentials may flow to a network call
4 flows detected: MIMIR_OAUTH_USERINFO_URL, MIMIR_EMBEDDINGS_API_KEY. We can’t prove the destination matches the brand the credential belongs to.
🚨
Known vulnerabilities in dependencies: 1 critical, 5 high
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
🔐
You'll be asked for 8 credentials: CONFIRMATION_SECRET, MIMIR_DEV_PASSWORD, MIMIR_EMBEDDINGS_API_KEY, MIMIR_EMBEDDINGS_VL_API_KEY, MIMIR_LLM_API_KEY, MIMIR_OAUTH_CLIENT_SECRET, NEO4J_PASSWORD, OPENAI_API_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// known CVEs in dependencies1 critical5 high3 low

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

criticalvitest@3.2.4GHSA-5xrq-8626-4rwp

When Vitest UI server is listening, arbitrary file can be read and executed

high@langchain/core@1.0.1GHSA-r399-636x-v7f6

LangChain serialization injection vulnerability enables secret extraction

high@modelcontextprotocol/sdk@1.20.1GHSA-345p-7cg4-v4c7

@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse

high@modelcontextprotocol/sdk@1.20.1GHSA-8r9q-7v3j-jr4g

Anthropic's MCP TypeScript SDK has a ReDoS vulnerability

high@modelcontextprotocol/sdk@1.20.1GHSA-w48q-cv73-mx4w

Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default

Depend on this server? Get alerted when its CVEs change.Watch this server free →
// required environment variables
This server reads these from process.env. You'll be asked to provide them before it can run.
configALLOW_CLEAR_ALL_IN_TEST
configAPI_BASE
🔐 secretCONFIRMATION_SECRET
configHOST_WORKSPACE_ROOTThe ONLY required configuration is in .env:
configMCP_ALLOWED_ORIGIN
configMCP_HOST
configMCP_PORT
configMCP_SERVER_URL
configMIMIR_AGENTS_DIR
configMIMIR_AGENT_RECURSION_LIMIT
configMIMIR_AUDIT_LOG_DESTINATION
configMIMIR_AUDIT_LOG_FILE
configMIMIR_AUDIT_LOG_FORMAT
configMIMIR_AUDIT_LOG_LEVEL
configMIMIR_AUDIT_WEBHOOK_AUTH_HEADER
configMIMIR_AUDIT_WEBHOOK_BATCH_INTERVAL_MS
configMIMIR_AUDIT_WEBHOOK_BATCH_SIZE
configMIMIR_AUDIT_WEBHOOK_URL
configMIMIR_AUTH_PROVIDER
configMIMIR_AUTO_INDEX_DOCS
configMIMIR_DATABASE_PROVIDER
configMIMIR_DEFAULT_CONTEXT_WINDOW
configMIMIR_DEFAULT_MODELgpt-4.1 # Default: gpt-4.1
configMIMIR_DEFAULT_PROVIDERopenai # Options: openai, copilot, ollama, llama.cpp
🔐 secretMIMIR_DEV_PASSWORD
configMIMIR_DEV_USERNAME
configMIMIR_EMBEDDINGS_APISet to match your embeddings provider
🔐 secretMIMIR_EMBEDDINGS_API_KEY
configMIMIR_EMBEDDINGS_API_PATH/v1/embeddings # Optional (default: /v1/embeddings)
configMIMIR_EMBEDDINGS_CHUNK_OVERLAP
configMIMIR_EMBEDDINGS_CHUNK_SIZE768 # Default: 768
configMIMIR_EMBEDDINGS_DELAY_MS
configMIMIR_EMBEDDINGS_DIMENSIONS1024 # Default: 1024
configMIMIR_EMBEDDINGS_ENABLED
configMIMIR_EMBEDDINGS_IMAGES
configMIMIR_EMBEDDINGS_IMAGES_DESCRIBE_MODE
configMIMIR_EMBEDDINGS_MAX_DELAY
configMIMIR_EMBEDDINGS_MAX_RETRIES
configMIMIR_EMBEDDINGS_MODELbge-m3 # Default: bge-m3
configMIMIR_EMBEDDINGS_MODEL_LOADING_DELAY
configMIMIR_EMBEDDINGS_PROVIDERUse Copilot embeddings (experimental - set =copilot)
configMIMIR_EMBEDDINGS_VL_API
🔐 secretMIMIR_EMBEDDINGS_VL_API_KEY
configMIMIR_EMBEDDINGS_VL_API_PATH
configMIMIR_EMBEDDINGS_VL_CONTEXT_SIZE
configMIMIR_EMBEDDINGS_VL_DIMENSIONS
configMIMIR_EMBEDDINGS_VL_MAX_TOKENS
configMIMIR_EMBEDDINGS_VL_MODEL
configMIMIR_EMBEDDINGS_VL_PROVIDER
configMIMIR_EMBEDDINGS_VL_TEMPERATURE
configMIMIR_EMBEDDINGS_VL_TIMEOUT
configMIMIR_ENABLE_AUDIT_LOGGING
configMIMIR_ENABLE_ECKO
configMIMIR_ENABLE_RBAC
configMIMIR_ENABLE_SECURITY
configMIMIR_ENV
configMIMIR_FEATURE_PM_MODEL_SUGGESTIONS
configMIMIR_FEATURE_VECTOR_EMBEDDINGS
configMIMIR_IMAGE_MAX_PIXELS
configMIMIR_IMAGE_RESIZE_QUALITY
configMIMIR_IMAGE_TARGET_SIZE
configMIMIR_INDEXING_THREADS
configMIMIR_INSTALL_DIR
configMIMIR_LLM_APISwitching Providers: Change MIMIR_DEFAULT_PROVIDER and in .env, then restart:
🔐 secretMIMIR_LLM_API_KEYdummy-key # Optional (use for OpenAI API)
configMIMIR_LLM_API_MODELS_PATH/v1/models # Optional (default: /v1/models)
configMIMIR_LLM_API_PATH/v1/chat/completions # Optional (default: /v1/chat/completions)
configMIMIR_MAX_TOKEN_AGE_SECONDS
configMIMIR_OAUTH_AUTHORIZATION_URL
configMIMIR_OAUTH_CALLBACK_URL
configMIMIR_OAUTH_CLIENT_ID
🔐 secretMIMIR_OAUTH_CLIENT_SECRET
configMIMIR_OAUTH_PROVIDER_NAME
configMIMIR_OAUTH_TIMEOUT_MS
configMIMIR_OAUTH_TOKEN_URL
configMIMIR_OAUTH_USERINFO_URL
configMIMIR_PARALLEL_EXECUTION
configMIMIR_PM_MODELgpt-4.1 # PM agent model
configMIMIR_PORT
configMIMIR_QC_MODELgpt-4.1 # QC agent model
configMIMIR_RBAC_AUTH_HEADER
configMIMIR_RBAC_CONFIG
configMIMIR_SENSITIVE_FILES
configMIMIR_SERVER_URL
configMIMIR_WORKER_MODELgpt-4o-mini # Worker agent model
🔐 secretNEO4J_PASSWORDpassword # Change in production!
configNEO4J_URI
configNEO4J_USER
configOLLAMA_BASE_URLUse external Ollama server (recommended - set in .env)
🔐 secretOPENAI_API_KEY
configPCTX_ENABLED
configPCTX_URL
configPORT
configVITEST
configWORKSPACE_ROOT${HOST_WORKSPACE_ROOT:-~/src}:${:-/workspace}:ro # Add :ro flag
// 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/orneryd-mimir-1c74y7)](https://m8ven.ai/mcp/orneryd-mimir-1c74y7)
commit: 01c0203d447ab4f6e04aa15d0c830d92bd4f2749
code hash: ed0bcc7614ec9e35aecb63949a6245a699de6b27ce2e7a5f0b9eb18660a75230
verified: 7/9/2026, 10:19:23 AM
view raw JSON →