AgentOps EvalBench MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DATABASE_URL | Yes | PostgreSQL connection string (e.g., postgresql://user:pass@host:5432/db). Falls back to local SQLite if not set. | |
| DEFAULT_MODEL | No | Chat model to use (default: gpt-4o-mini). | gpt-4o-mini |
| OPENAI_API_KEY | Yes | API key for OpenAI embeddings and chat completions. Required for live runs. | |
| LANGSMITH_API_KEY | No | API key for LangSmith tracing (optional). | |
| LANGSMITH_TRACING | No | Enable LangSmith tracing (optional, set to 'true' to enable). | |
| CHROMA_PERSIST_DIR | No | Directory for Chroma vector store persistence (default: ./data/chroma). | ./data/chroma |
| EVAL_MIN_GROUNDEDNESS | No | Minimum groundedness score to pass (default: 0.80). | 0.80 |
| DEFAULT_EMBEDDING_MODEL | No | Embedding model to use (default: text-embedding-3-small). | text-embedding-3-small |
| EVAL_MAX_LATENCY_SECONDS | No | Maximum latency in seconds to pass (default: 5). | 5 |
| EVAL_MIN_RETRIEVAL_SCORE | No | Minimum retrieval quality score to pass (default: 0.75). | 0.75 |
| EVAL_MAX_HALLUCINATION_RISK | No | Maximum hallucination risk score to pass (default: 0.20). | 0.20 |
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
ActivityMaintained
ResponsivenessUnresponsive