Cognio
by 0xReLogic
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| API_KEY | No | Optional API key for authentication | |
| DB_PATH | No | Path to the SQLite database file | ./data/memory.db |
| API_HOST | No | API server host | 0.0.0.0 |
| API_PORT | No | API server port | 8080 |
| LOG_LEVEL | No | Logging level | info |
| BATCH_SIZE | No | Batch size for processing | 32 |
| GROQ_MODEL | No | Groq model | openai/gpt-oss-120b |
| EMBED_MODEL | No | Sentence transformer model for embeddings | all-MiniLM-L6-v2 |
| HYBRID_MODE | No | Hybrid search mode: candidate or rerank | rerank |
| EMBED_DEVICE | No | Device for embedding model (cpu or cuda) | cpu |
| GROQ_API_KEY | No | Groq API key (required if LLM_PROVIDER=groq) | |
| HYBRID_ALPHA | No | Hybrid search alpha parameter | 0.6 |
| LLM_PROVIDER | No | LLM provider for auto-tagging | groq |
| OPENAI_MODEL | No | OpenAI model | gpt-4o-mini |
| LEANN_BACKEND | No | LEANN backend | hnsw |
| LEANN_ENABLED | No | Enable LEANN vector search | false |
| HYBRID_ENABLED | No | Enable hybrid search | true |
| OPENAI_API_KEY | No | OpenAI API key | |
| AUTOTAG_ENABLED | No | Enable auto-tagging | true |
| MAX_TEXT_LENGTH | No | Maximum text length for processing | 10000 |
| LEANN_INDEX_PATH | No | Path to LEANN index | ./data/leann/memories.leann |
| LEANN_LAZY_BUILD | No | Lazy build LEANN index | true |
| HYBRID_RERANK_TOPK | No | Rerank candidate pool size | 100 |
| SUMMARIZE_THRESHOLD | No | Summarization threshold | 50 |
| DEFAULT_SEARCH_LIMIT | No | Default number of search results | 5 |
| EMBEDDING_CACHE_PATH | No | Path to embedding cache | ./data/embedding_cache.pkl |
| SIMILARITY_THRESHOLD | No | Similarity threshold for search | 0.4 |
| SUMMARIZATION_METHOD | No | Summarization method: extractive or abstractive | abstractive |
| LEANN_WARMUP_ON_START | No | Warmup LEANN on start | false |
| SUMMARIZATION_ENABLED | No | Enable summarization | true |
| LEANN_RECOMPUTE_ON_SEARCH | No | Recompute LEANN index on search | true |
| SUMMARIZATION_EMBED_MODEL | No | Summarization embedding model | all-MiniLM-L6-v2 |
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/0xReLogic/Cognio'
If you have feedback or need assistance with the MCP directory API, please join our Discord server