Signoz Mcp Server
@DrDroidLab
About Signoz Mcp Server
The Signoz MCP Server lets you connect developer tools like Cursor or Claude Desktop to your Signoz instance. It's an open-source project maintained by DrDroid (not affiliated with Signoz), and allows you to query logs, dashboards, metrics, and more — making observability data di
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"signoz": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"-e",
"SIGNOZ_HOST",
"-e",
"SIGNOZ_API_KEY",
"-e",
"SIGNOZ_SSL_VERIFY",
"signoz-mcp-server",
"-t",
"stdio"
],
"env": {
"SIGNOZ_HOST": "https://your-signoz-instance.com",
"SIGNOZ_API_KEY": "your-signoz-api-key-here",
"SIGNOZ_SSL_VERIFY": "true"
}
}
}
}Tools
9Verify connectivity to your Signoz instance and configuration.
List all available dashboards from Signoz.
Retrieve detailed information about a specific dashboard by its ID. This information contains the metadata of the dashboard, not the live panel data.
Fetch all panel data for a given dashboard by name and time range.
Retrieve standard APM metrics (request rate, error rate, latency, apdex, etc.) for a given service and time range.
Fetch all instrumented services from Signoz with optional time range filtering.
Execute custom Clickhouse SQL queries via the Signoz API with time range support.
Execute Signoz builder queries for custom metrics and aggregations with time range support.
Fetch traces or logs from SigNoz using ClickHouse SQL. Specify `data_type` ('traces' or 'logs'), time range, service name, and limit. Returns tabular results for traces or logs.
Overview
What is Signoz MCP Server?
Signoz MCP Server is an MCP (Model Context Protocol) server that connects AI assistants like Claude Desktop or Cursor to a SigNoz observability instance. It provides a set of tools to query dashboards, APM metrics, services, traces, logs, and execute ClickHouse queries directly from the AI tool.
How to use Signoz MCP Server?
Install dependencies with uv sync, then run with uv run -m src.signoz_mcp_server.mcp_server. Alternatively, deploy using Docker Compose or Docker with environment variables. Configure via config.yaml or environment variables (SIGNOZ_HOST, SIGNOZ_API_KEY, etc.). Integrate with AI assistants using stdio mode or HTTP/SSE endpoint.
Key features of Signoz MCP Server
- Test connectivity to your SigNoz instance.
- List and retrieve details of all dashboards.
- Fetch live panel data for a dashboard by name and time range.
- Retrieve APM metrics (request rate, error rate, latency, apdex) per service.
- List all instrumented services with optional time range filtering.
- Execute custom ClickHouse SQL queries and builder queries via SigNoz API.
- Fetch traces or logs using ClickHouse SQL with service filtering.
Use cases of Signoz MCP Server
- Query dashboards and panel data directly from an AI coding assistant.
- Monitor service health (APM metrics) without switching to the SigNoz UI.
- Run ad‑hoc ClickHouse queries on observability data from a chat interface.
- Investigate traces or logs for a specific service during debugging.
- Automate observability data retrieval in MCP‑compatible workflows.
FAQ from Signoz MCP Server
What authentication is required?
An API key is optional; if your SigNoz instance requires one, obtain it from the SigNoz UI and set it via the SIGNOZ_API_KEY environment variable or config.yaml.
How is configuration loaded?
Configuration is loaded in order: environment variables take precedence over the YAML file (config.yaml). Supported env vars include SIGNOZ_HOST, SIGNOZ_API_KEY, SIGNOZ_SSL_VERIFY, MCP_SERVER_PORT, and MCP_SERVER_DEBUG.
What transport modes are supported?
The server supports stdio mode (for local integration with MCP clients like Claude Desktop) and HTTP/SSE mode (for remote or containerized deployments, default port 8000).
How can I verify the server is running?
Access the health check endpoint at http://localhost:8000/health (or your configured host). Returns a success response when running.
Where does observability data live?
All data remains in your SigNoz instance; the server only passes queries and results between the AI assistant and SigNoz. No data is stored by the MCP server.
Frequently asked questions
What authentication is required?
An API key is optional; if your SigNoz instance requires one, obtain it from the SigNoz UI and set it via the `SIGNOZ_API_KEY` environment variable or `config.yaml`.
How is configuration loaded?
Configuration is loaded in order: environment variables take precedence over the YAML file (`config.yaml`). Supported env vars include `SIGNOZ_HOST`, `SIGNOZ_API_KEY`, `SIGNOZ_SSL_VERIFY`, `MCP_SERVER_PORT`, and `MCP_SERVER_DEBUG`.
What transport modes are supported?
The server supports stdio mode (for local integration with MCP clients like Claude Desktop) and HTTP/SSE mode (for remote or containerized deployments, default port 8000).
How can I verify the server is running?
Access the health check endpoint at `http://localhost:8000/health` (or your configured host). Returns a success response when running.
Where does observability data live?
All data remains in your SigNoz instance; the server only passes queries and results between the AI assistant and SigNoz. No data is stored by the MCP server.
Basic information
More Developer Tools MCP servers
endoflife.ai
endoflife.aiFree MCP server for software end-of-life intelligence: EOL dates, support status, and the 0-100 EOL Risk Score across 485 tracked products. Agents can check a single version, pull a product's full lifecycle schedule, or
DevDocs by CyberAGI 🚀
cyberagiincCompletely free, private, UI based Tech Documentation MCP server. Designed for coders and software developers in mind. Easily integrate into Cursor, Windsurf, Cline, Roo Code, Claude Desktop App

BetterBugs
BetterBugsThe BetterBugs MCP (Model Context Protocol) enables you to load BetterBugs bug reports (via report links) directly to your preferred AI Agents and developer environments with MCP Client capabilities (such as Cursor, VS C

Reelier
Maxime HouleAgents make claims. Reelier writes receipts — record an agent's tool-call workflow once, replay it deterministically at 0 tokens, and diff runs to catch drift.
Grafana MCP server
grafanaMCP server for Grafana
Comments