agentops-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| cost_summaryA | Token cost across Claude Code projects: output/input tokens, cache hit rate, estimated list-price dollars, and the top projects and tools by spend. |
| audit_summaryC | What the agent actually did: command count, file writes, errors, sensitive-path accesses, and the most common command verbs. |
| safety_reportA | Dangerous actions the agent ATTEMPTED (force-push, rm -rf on risky paths, curl|sh, chmod 777, etc.), whether or not a guardrail stopped them. |
| efficiency_reportB | Where tokens are wasted: re-read files, oversized tool output, cache hit rate, plus concrete recommendations to cut waste. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool targets a clearly distinct aspect of agent operations: actions, costs, efficiency, and safety. No overlap or ambiguity exists between the tool purposes.
All tool names follow a consistent adjective_noun pattern using underscores, making them predictable and easy to understand (e.g., audit_summary, cost_summary).
With only 4 tools, the server is tightly scoped around monitoring agent behavior. Each tool earns its place, and the count is appropriate for a focused observability server.
The tool surface covers the essential dimensions of agent operations: actions, costs, efficiency, and safety. There are no obvious gaps for the intended purpose of auditing and optimizing agent performance.