ai-agent-layer
by mhsh77
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | The port the server listens on. | 8787 |
| DB_FILE | No | Path to the SQLite database file. | data/agentlayer.db |
| CRAWL_RENDER | No | When to render pages: auto|never|always. | auto |
| LLM_PROVIDER | No | LLM provider: auto|anthropic|deepseek|heuristic. | auto |
| API_KEY_PEPPER | No | Secret used for hashing API keys; must be set in production. | dev value |
| ANTHROPIC_MODEL | No | Model name to use for Anthropic. | claude-sonnet-5 |
| CRAWL_MAX_PAGES | No | Maximum pages to crawl per site. | 60 |
| DEEPSEEK_API_KEY | No | API key for DeepSeek (alternative provider). | |
| ANTHROPIC_API_KEY | No | API key for Anthropic (enables model extraction pass). | |
| EMBEDDING_API_KEY | No | API key for hosted embedding provider. | |
| EMBEDDING_PROVIDER | No | Embedding provider: local|voyage|openai. | local |
| AGENTLAYER_MCP_TIER | No | MCP tool tier: public or restricted. | restricted |
| MONITOR_INTERVAL_MS | No | Recrawl cadence in milliseconds. | 6h |
| CONTEXT_TOKEN_BUDGET | No | Soft token budget for context.json. | 6000 |
| CRAWL_RESPECT_ROBOTS | No | Whether to respect robots.txt. | 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 | |
This server cannot be deployed
Maintenance
ActivitySlowing
ResponsivenessNo issues