OpenObserve MCP Server
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., "@OpenObserve MCP Servershow me recent error logs"
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.
OpenObserve MCP Server
An MCP (Model Context Protocol) server that enables AI assistants to query and explore your OpenObserve observability data. This server provides read-only access to logs, metrics, and traces stored in OpenObserve, allowing LLMs to help you analyze and troubleshoot your systems.
(mcp-server-openobserve) mfranz@lenovo-cr14p:~/github/openobserve-oss-mcp$ uv run scripts/o2_mcp_client.py --model google:gemini-3-pro-preview
Info: 'google:' provider is ambiguous. Assuming 'google-gla:' (Google Generative Language API).
Initializing agent with model: google-gla:gemini-3-pro-preview
OpenObserve MCP CLI. Type "/exit" to quit.
user> what streams are there?
user: what streams are there?
tool call: list_streams
tool return: list_streams
assistant: The available streams are:
- **suricata** (Type: logs, Doc count: ~13.5 million)
user> list the hosts sending journald events
user: list the hosts sending journald events
tool call: list_streams
tool return: list_streams
tool call: get_stream_schema
tool return: get_stream_schema
tool call: search_sql
tool return: search_sql
assistant: I found 2 hosts sending journald events (stream: journald):
- franz-OptiPlex-7050 — 1,960 events — last_seen _timestamp = 1771082221716601 (μs since epoch)
- asus-pn50 — 1,268 events — last_seen _timestamp = 1771082221680679 (μs since epoch)
Query used:
SELECT host_name, COUNT(*) AS cnt, MAX(_timestamp) AS last_seen FROM journald GROUP BY host_name ORDER BY cnt DESC LIMIT 200;
Would you like me to:
- convert the last_seen timestamps to human-readable datetimes, or
- list more hosts, or
- show recent journald messages per host?License
This project is licensed under the MIT License - see the LICENSE file for details.
This server cannot be deployed
Maintenance
Related MCP Connectors
- SpanlyOAuthcom.spanly
MCP observability. Query live traffic, errors, duration, and alerts from your AI agent.
Query application logs, traces, and metrics from your AI coding assistant via Foam's MCP server.
Cloud hosted Okahu MCP server that helps you manage genAI trace data
MCP server that lets AI assistants use all OneSchema features exposed via the public API.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceAn MCP server that enables AI assistants to interact with Signoz observability platform, providing tools to query dashboards, metrics, traces, logs, and APM data with time range support.14MIT
- AlicenseBqualityCmaintenanceA read-only MCP server for OpenObserve Community Edition that works over the REST API. Provides tools for searching logs, traces, stream schemas, and dashboards - no Enterprise license required.8190 PyPI16GPL 3.0
- AlicenseAqualityDmaintenanceMCP server that gives AI agents access to your application's OpenTelemetry traces for querying, analysis, and debugging.57 npm2MIT
- AlicenseAqualityDmaintenanceMCP server that enables AI assistants to query Grafana/Loki logs and Thanos/Prometheus metrics directly from MCP-compatible clients like Cursor or Claude Desktop.8MIT