Testing Agent MCP Server
by ESTELLA219
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LLM_PROVIDER | Yes | The LLM provider to use. Supported values: openai, openai_http, deepseek. | |
| OPENAI_MODEL | Yes | Model name to use with OpenAI. | |
| AGENT_MCP_HOST | No | Host address for HTTP MCP server. | |
| AGENT_MCP_PATH | No | Path for MCP endpoint. | |
| AGENT_MCP_PORT | No | Port for HTTP MCP server. | |
| OPENAI_API_KEY | Yes | API key for the OpenAI provider (or compatible endpoint). | |
| AGENT_RUNTIME_ROOT | Yes | Root directory for runtime data (logs, artifacts, etc.). | |
| AGENT_MCP_TRANSPORT | Yes | MCP transport mode: 'stdio' or 'http'. | |
| AGENT_MCP_PUBLIC_URL | No | Public URL for the MCP server, used for callbacks. | |
| AGENT_PLATFORM_TARGETS_JSON | No | JSON mapping of platform target IDs to base URLs and authentication config. | |
| AGENT_MCP_CLIENT_TOKENS_JSON | No | JSON mapping of client IDs to bearer tokens for MCP authentication. | |
| AGENT_MCP_REMOTE_PLATFORM_ONLY | No | When 'true', the server only accepts requests from remote platforms (not local UI). |
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