Schema | MCP Ops Agent

MCP Ops Agent

Describes the environment variables required to run the server.

Name	Required	Description	Default
`LLM_MODEL`	No	LLM model name.
`LOG_LEVEL`	No	Log level (DEBUG, INFO, WARNING, ERROR).	INFO
`LOG_FORMAT`	No	Log format (text or json).	text
`LLM_API_KEY`	Yes	API key for LLM provider (OpenAI-compatible). Required for OpenAI; optional if using local Ollama.
`LLM_BASE_URL`	No	Base URL for OpenAI-compatible API (default: https://api.openai.com).
`LLM_PROVIDER`	No	LLM provider name.	openai
`AGENT_MAX_STEPS`	No	Maximum steps for the agent loop.
`OPS_CORE_API_KEY`	Yes	API key for ops-core-api.
`OPS_CORE_TIMEOUT`	No	Timeout for ops-core-api requests (seconds).
`SECURITY_API_KEY`	No	Optional API key for POST /api/v1/invoke (min 16 chars). Must be set if exposing publicly.
`OPS_CORE_BASE_URL`	Yes	Base URL for ops-core-api.	http://localhost:8000
`AGENT_MCP_SELF_URL`	No	Self-loopback URL for MCP.	http://localhost:8000/mcp
`CORS_ALLOWED_ORIGINS`	No	Comma-separated list of allowed CORS origins (empty = none).
`OPS_CORE_TOTAL_ATTEMPTS`	No	Total retry attempts for ops-core-api.

Server capabilities have not been inspected yet.

Functions exposed to the LLM to take actions

Name	Description
No tools

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/upkero/mcp-ops-agent'

If you have feedback or need assistance with the MCP directory API, please join our Discord server