agent-engrams-mcp
by johndlong73
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | HTTP server port (HTTP mode only) | 3000 |
| USE_STDIO | No | Force stdio transport | |
| MCP_CONFIG | No | Path to a JSON config file (overrides XDG default) | ~/.config/agent-engrams-mcp/mcp.json |
| ENGRAMS_DIR | No | Store root directory (docs/ holds markdown; index/ reserved) | ~/.config/agent-engrams-mcp |
| EMBEDDER_TYPE | No | Provider type: openai, bedrock, ollama | openai |
| EMBEDDER_MODEL | No | Embedding model name | Qwen3-Embedding-0.6B-4bit-DWQ |
| XDG_CONFIG_HOME | No | Base config directory | ~/.config |
| EMBEDDER_API_KEY | Yes | API key for the embedding provider | |
| EMBEDDER_BASE_URL | Yes | Base URL for the embedding API | |
| EMBEDDER_DIMENSIONS | No | Embedding vector dimensions | 512 |
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 | |
This server cannot be deployed
Maintenance
ActivityInactive
ResponsivenessNo issues