agent-tools-cloud
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| UPSTREAM_API_KEY | Yes | API key for upstream model API | |
| UPSTREAM_BASE_URL | Yes | Base URL for upstream model API, used by /v1/models | |
| AGENT_TOOLS_DB_PATH | Yes | SQLite path for the directory database | |
| METRICS_BEARER_TOKEN | No | Optional remote access token for /metrics endpoint; without it metrics are local-only | |
| AGENT_TOOLS_ASK_MODEL | Yes | Model name for the ask LLM backend | |
| AGENT_TOOLS_ASK_API_KEY | Yes | API key for the ask LLM backend | |
| AGENT_TOOLS_ASK_BASE_URL | Yes | Base URL for LLM backend used by /api/v1/ask | |
| AGENT_TOOLS_SAFETY_MODEL | No | Optional model name for the safety LLM (falls back to AGENT_TOOLS_ASK_* if not set) | |
| AGENT_TOOLS_SAFETY_API_KEY | No | Optional API key for the safety LLM (falls back to AGENT_TOOLS_ASK_* if not set) | |
| AGENT_TOOLS_SAFETY_BASE_URL | No | Optional override base URL for the scan_mcp_safety advisory LLM (falls back to AGENT_TOOLS_ASK_* if not set) | |
| AGENT_TOOLS_ASK_RATE_LIMIT_PER_DAY | Yes | Rate limit for public ask endpoint per day (e.g., '1000') | |
| AGENT_TOOLS_ASK_RATE_LIMIT_PER_MINUTE | Yes | Rate limit for public ask endpoint per minute (e.g., '10') |
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
ResponsivenessUnresponsive