Loggles MCP Server

A local-first log sink that turns your coding agent into a runtime companion.

Remote serverstreamable-httpPython

What is the Loggles MCP server?

A local-first log sink that turns your coding agent into a runtime companion. The loggles mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 14 defined tools rather than through you.

Its toolset

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

  • search_logs — Search with filters: time range, level, service, message text, structured properties. Supports pagination
  • get_log_by_id — Retrieve a single log event by ID
  • get_services — List all source/service names that have emitted logs
  • get_log_levels — List distinct log levels present
  • get_properties — List distinct structured property keys
  • get_property_values — List distinct values for a property key within a time window
  • get_log_stats — Log counts grouped by level and service
  • get_logs_by_trace_id — Retrieve all logs sharing a trace/correlation ID
  • get_related_logs — Context window of logs around a specific event
  • get_recent_errors — Last N error/critical log events, optionally filtered by service
  • tail_logs — Most recent N log events
  • get_log_rate — Bucketed log counts over time — observe traffic volume and rhythm

Adding it to your client

Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.

When to reach for it

Plenty of monitoring and observability servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Loggles's toolset — search_logs, get_log_by_id, get_services and 11 more — is a fair guide to whether it matches your workflow. It is maintained by bytesquashcom; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Caveats

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Loggles.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the loggles mcp server does with a few real requests.

Available tools

ToolWhat it does
search_logsSearch with filters: time range, level, service, message text, structured properties. Supports pagination.
get_log_by_idRetrieve a single log event by ID
get_servicesList all source/service names that have emitted logs
get_log_levelsList distinct log levels present
get_propertiesList distinct structured property keys
get_property_valuesList distinct values for a property key within a time window
get_log_statsLog counts grouped by level and service
get_logs_by_trace_idRetrieve all logs sharing a trace/correlation ID
get_related_logsContext window of logs around a specific event
get_recent_errorsLast N error/critical log events, optionally filtered by service
tail_logsMost recent N log events
get_log_rateBucketed log counts over time — observe traffic volume and rhythm
get_message_templatesList distinct message templates, optionally filtered by service
find_log_patternsCluster messages by recurring pattern

How to install the Loggles MCP server

{
  "mcpServers": {
    "loggles": {
      "command": "npx",
      "args": ["-y", "@opentelemetry/sdk-node"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Loggles to search logs.
  • Use Loggles to get log by id.
  • Use Loggles to get services.

Frequently asked questions

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