mcp-local-memory
by Beledarian
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OLLAMA_URL | No | Full API Endpoint for the LLM strategy (e.g., http://localhost:11434/api/generate). | http://localhost:11434 |
| USE_WORKER | No | Run Archivist in a background thread to prevent blocking. Options: true, false. | true |
| MEMORY_DB_PATH | No | Location of the SQLite database file. | ./memory.db |
| EXTENSIONS_PATH | No | Optional path to load custom tool extensions from external directory. Allows adding private/experimental tools without modifying the codebase. | |
| TAG_MATCH_BOOST | No | Score boost for exact tag matches in recall results. Higher = stronger tag priority. | 0.15 |
| ARCHIVIST_LANGUAGE | No | Optional language setting for the Archivist. Default is 'en'. | en |
| ARCHIVIST_STRATEGY | No | Control automatic entity extraction behavior. Options: passive, nlp, llm. Can be comma-separated (e.g., nlp,llm). | nlp |
| CONTEXT_TODO_LIMIT | No | Max pending todos shown in memory://current-context. | 3 |
| CONTEXT_MAX_ENTITIES | No | Max high-importance entities in context. | 5 |
| CONTEXT_MAX_MEMORIES | No | Max recent memories in context. | 5 |
| CONTEXT_WINDOW_LIMIT | No | Max characters returned by memory://current-context. | 500 |
| EMBEDDING_CONCURRENCY | No | Max concurrent embedding operations for remember_facts. Higher values = faster batch processing but more CPU/memory usage. | 5 |
| MEMORY_HALF_LIFE_WEEKS | No | Weeks until memory importance decays to 50%. Longer = slower decay. | 4.0 |
| MEMORY_SEMANTIC_WEIGHT | No | Balance between semantic similarity (0.7) and decayed importance (0.3) in recall ranking. | 0.7 |
| ENABLE_CONSOLIDATE_TOOL | No | Enable the consolidate_context tool for retrospective memory extraction. Options: true, false. | false |
| EXTRACT_COMPLEX_CONCEPTS | No | Enable extraction of modifier+noun phrases (e.g., 'optimized WGSL'). Options: true, false. | true |
| MEMORY_CONSOLIDATION_FACTOR | No | Strength of access-based consolidation. Higher = frequently-used memories resist decay more. | 1.0 |
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/Beledarian/mcp-local-memory'
If you have feedback or need assistance with the MCP directory API, please join our Discord server