Scouter MCP Server

Query Scouter APM (objects, counters, XLog transactions) over stdio via a Scouter collector.

Local serverstdioGo

What is the Scouter MCP MCP server?

Query Scouter APM (objects, counters, XLog transactions) over stdio via a Scouter collector. Exposed over MCP by the scouter mcp mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.

What it actually does

A stdio MCP server that connects directly to a Scouter Collector over TCP and queries XLogs, counters, and objects. Its purpose is to let an AI quickly explore Scouter metrics and diagnose root causes. Each result carries txid / gxid / objName / endTimeIso, which you can use as keys to cross-analyze with other observability tools such as OpenSearch or Datadog.

Adding it to your client

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.

Its toolset

Everything the assistant can do here goes through one of these:

  • list_objects — List objects/agents
  • search_xlog — Search XLogs (latency/errors)
  • get_service_summary — Per-service aggregate (count/avg/max/p95/errorRate), top 50
  • get_summary — Collector's daily pre-aggregated stats (top-50 SQL/service/error/... — no scanning)
  • get_xlog_detail — XLog detail (SQL/bind params)
  • get_xlog_by_gxid — Distributed-transaction group
  • get_counter — Counter time series (same-day, full resolution)
  • get_counter_stat — Long-range counter stats (5-min resolution, up to 31 days)
  • list_counters — Available counters for an objType
  • list_alerts — Past collector alerts
  • get_active_services — Services running right now
  • list_threads — JVM thread list (state histogram + top 50 by cpu)

Configuration

You will need 5 environment variables: SCOUTER_COLLECTOR_HOST, SCOUTER_COLLECTOR_PORT, SCOUTER_USER, SCOUTER_PASSWORD, SCOUTER_TZ. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Caveats

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Scouter MCP.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the scouter mcp mcp server does with a few real requests.

When to reach for it

This sits in the database access group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Scouter MCP's toolset — list_objects, search_xlog, get_service_summary and 11 more — is a fair guide to whether it matches your workflow. It is maintained by 335; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Available tools

ToolWhat it does
list_objectsList objects/agents
search_xlogSearch XLogs (latency/errors)
get_service_summaryPer-service aggregate (count/avg/max/p95/errorRate), top 50
get_summaryCollector's daily pre-aggregated stats (top-50 SQL/service/error/... — no scanning)
get_xlog_detailXLog detail (SQL/bind params)
get_xlog_by_gxidDistributed-transaction group
get_counterCounter time series (same-day, full resolution)
get_counter_statLong-range counter stats (5-min resolution, up to 31 days)
list_countersAvailable counters for an objType
list_alertsPast collector alerts
get_active_servicesServices running right now
list_threadsJVM thread list (state histogram + top 50 by cpu)
get_thread_detailLive thread of an ACTIVE transaction (stack/lock owner/current SQL)
get_object_envAgent JVM system properties (secrets masked)

How to install the Scouter MCP MCP server

{
  "mcpServers": {
    "scouter-prod": {
      "command": "java",
      "args": ["-jar", "/ABSOLUTE/PATH/scouter-mcp-<version>-all.jar"],
      "env": {
        "SCOUTER_COLLECTOR_HOST": "prod-collector", "SCOUTER_COLLECTOR_PORT": "6100",
        "SCOUTER_USER": "prod-user", "SCOUTER_PASSWORD": "***", "SCOUTER_TZ": "Asia/Seoul"
      }
    },
    "scouter-stg": {
      "command": "java",
      "args": ["-jar", "/ABSOLUTE/PATH/scouter-mcp-<version>-all.jar"],
      "env": {
        "SCOUTER_COLLECTOR_HOST": "stg-collector", "SCOUTER_COLLECTOR_PORT": "6100",
        "SCOUTER_USER": "stg-user", "SCOUTER_PASSWORD": "***", "SCOUTER_TZ": "Asia/Seoul"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
SCOUTER_COLLECTOR_HOSTEndpoint or connection string the server talks to.Optional
SCOUTER_COLLECTOR_PORTConfiguration value read at startup.Optional
SCOUTER_USERConfiguration value read at startup.Optional
SCOUTER_PASSWORDConfiguration value read at startup.Optional
SCOUTER_TZConfiguration value read at startup.Optional

Example prompts to try

  • Use Scouter MCP to list objects.
  • Use Scouter MCP to search xlog.
  • Use Scouter MCP to get service summary.

Frequently asked questions

It connects Scouter MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (list_objects, search_xlog, get_service_summary, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Scouter MCP directly.