F
licenseNot graded
qualityB
maintenanceEnables agents to autonomously diagnose Linux performance issues by exposing production-debugging primitives such as perf, strace, /proc, flamegraphs, and eBPF as safe, structured, budgeted tools.
-
mcp-agentops
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp-agentopsshow me fleet health and any firing critical alerts"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mcp-agentops
MCP server for Agent Observability & Operations — health checks, metrics collection, alerting, log aggregation, performance profiling, debugging hooks, and operational tooling for agent fleets.
Tools
register_agent
Register a new agent in the observability fleet.
Parameter | Type | Default | Description |
| string enum | required |
|
| string | required | Human-readable name |
| object | - | Agent-specific configuration |
| object | - | Additional metadata (tags, environment, owner) |
Returns the created agent with generated agent_id, status, and timestamps.
get_agent_health
Get real-time health status for a specific agent or fleet-wide.
Parameter | Type | Default | Description |
| string | - | Specific agent ID; omit for fleet-wide health |
Returns health status (healthy/degraded/unhealthy), last seen, and recent metrics count.
record_metrics
Record a metrics snapshot for an agent.
Parameter | Type | Default | Description |
| string | required | Agent identifier |
| object | required | Metric name to value mapping |
| string | now | ISO-8601 timestamp |
Updates agent status based on configured thresholds.
get_metrics_history
Retrieve historical metrics with optional aggregation.
Parameter | Type | Default | Description |
| string | required | Agent identifier |
| array | - | Specific metrics to retrieve |
| integer | 60 | Time window |
| string enum |
|
|
Returns raw entries or aggregated results.
create_alert
Create an alert rule or trigger a manual alert.
Parameter | Type | Default | Description |
| string | - | Agent to alert on; omit for fleet-wide |
| string enum | required | Metric to monitor (from METRIC_TYPES) |
| string enum | required |
|
| number | required | Threshold value |
| string enum |
|
|
| string | - | Human-readable description |
| integer | 15 | Cooldown between firings |
Returns the created alert rule with alert_id.
get_alerts
Retrieve active and historical alerts with filtering.
Parameter | Type | Default | Description |
| string | - | Filter by agent |
| string enum | - | Filter by severity |
| string enum | - |
|
| integer | 50 | Maximum results |
run_profile
Run a performance profile on an agent.
Parameter | Type | Default | Description |
| string | required | Agent to profile |
| string enum |
|
|
| integer | 30 | Profiling duration |
Returns simulated profile results with CPU, memory, latency stats.
get_logs
Retrieve aggregated logs for an agent with filtering.
Parameter | Type | Default | Description |
| string | required | Agent identifier |
| string enum |
|
|
| string | 24h ago | ISO-8601 timestamp |
| integer | 100 | Maximum log entries |
Related MCP server: io.github.morluto/flameox
Installation
pip install -r requirements.txtUsage
python main.pyState persisted in ./state/. Override with MCP_AGENTOPS_STATE_DIR.
Connecting to an MCP client
{
"mcpServers": {
"agentops": {
"command": "python3",
"args": ["/tmp/v3-services/mcp-agentops/main.py"]
}
}
}License
MIT
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues
Related MCP Connectors
Real-time health monitoring and heartbeat tracking for agent services
Operate smplkit from your agent: feature flags, config, logging, audit, and scheduled jobs.
- SuperlogOAuthsh.superlog
Open-source agent that observes and fixes your application. Query logs, traces, metrics, incidents.
Agent-native registry to discover APIs, MCP servers and CLIs, with live health checks.
Related MCP Servers
- FlicenseNot gradedqualityAmaintenanceEnables agents to coordinate profilers, benchmark tools, trace processors, and direct local targets to produce bounded runtime evidence, with optional durable preservation and replayable analysis or capture workflows.-
- FlicenseNot gradedqualityAmaintenanceEnables agents to coordinate profilers, benchmark tools, trace processors, and direct local targets to collect bounded runtime evidence with provenance, coverage, and limitations for application and native code, GPU kernels, and inference stacks.-
- AlicenseNot gradedqualityAmaintenanceEnables coding agents to audit and manage installed skills and MCP servers across harnesses, profile startup token overhead, inspect bundled assets, safely remove unused skills, and check for updates via native tools and a local dashboard.MIT