M.I.M.I.R - Multi-agent Intelligent Memory & Insight Repository
by orneryd
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HTTP_PROXY | No | Corporate HTTP proxy URL (if needed) | |
| HTTPS_PROXY | No | Corporate HTTPS proxy URL (if needed) | |
| MIMIR_LLM_API | No | Base URL for the LLM API endpoint | http://copilot-api:4141 |
| SSL_CERT_FILE | No | Custom CA certificate file path (if needed) | |
| MIMIR_PM_MODEL | No | Optional per-agent model override for PM agent (defaults to MIMIR_DEFAULT_MODEL) | |
| MIMIR_QC_MODEL | No | Optional per-agent model override for QC agent (defaults to MIMIR_DEFAULT_MODEL) | |
| NEO4J_PASSWORD | No | Neo4j database password (change in production!) | password |
| MIMIR_LLM_API_KEY | No | Optional API key for LLM provider (required for OpenAI API) | dummy-key |
| MIMIR_LLM_API_PATH | No | Optional path for LLM API chat completions endpoint | /v1/chat/completions |
| MIMIR_WORKER_MODEL | No | Optional per-agent model override for Worker agent (defaults to MIMIR_DEFAULT_MODEL) | |
| HOST_WORKSPACE_ROOT | No | Your main source code directory. This gives Mimir access to your code for file indexing. Tilde (~) automatically expands to your home directory. | ~/src |
| MIMIR_DEFAULT_MODEL | No | Default LLM model to use | gpt-4.1 |
| MIMIR_EMBEDDINGS_API | No | Embeddings API endpoint | http://llama-server:8080 |
| MIMIR_AUTO_INDEX_DOCS | No | Auto-index Mimir documentation on startup. Allows users to immediately query Mimir's docs via semantic search. | true |
| MIMIR_DEFAULT_PROVIDER | No | LLM provider selection. Options: openai, copilot, ollama, llama.cpp | openai |
| MIMIR_EMBEDDINGS_MODEL | No | Embedding model for semantic search. Options: bge-m3, nomic-embed-text, text-embedding-3-small | bge-m3 |
| MIMIR_EMBEDDINGS_ENABLED | No | Enable vector embeddings for AI semantic search | true |
| MIMIR_EMBEDDINGS_API_PATH | No | Optional path for embeddings API endpoint | /v1/embeddings |
| MIMIR_LLM_API_MODELS_PATH | No | Optional path for LLM API models endpoint | /v1/models |
| MIMIR_EMBEDDINGS_CHUNK_SIZE | No | Chunk size for embeddings | 768 |
| MIMIR_EMBEDDINGS_DIMENSIONS | No | Embedding vector dimensions | 1024 |
| MIMIR_FEATURE_VECTOR_EMBEDDINGS | No | Enable vector embeddings feature flag | true |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/orneryd/Mimir'
If you have feedback or need assistance with the MCP directory API, please join our Discord server