SigNoz MCP Server

A Model Context Protocol (MCP) server that provides seamless access to SigNoz observability data through AI assistants and LLMs. Query metrics, traces, logs, alerts, dashboards, and services using natural language.

[📖 Full Documentation](https://signoz.io/docs/ai/signoz-mcp-server/)

Table of Contents

• Connect to SigNoz Cloud
• Self-Hosted Installation
• Connect to Self-Hosted SigNoz
• What Can You Do With It?
• Available Tools
• Environment Variables
• Claude Desktop Extension
• Architecture
• Contributing

Connect to SigNoz Cloud

Connect your AI tool to SigNoz Cloud's hosted MCP server. No installation is required; just add the hosted MCP URL and authenticate.

https://mcp.<region>.signoz.cloud/mcp

Make sure you select the correct region that matches your SigNoz Cloud account. Using the wrong region will result in authentication failures.

>

Find your region under Settings → Ingestion in SigNoz, or see the SigNoz Cloud region reference.

One-Click Install Links

GitHub does not reliably make custom-protocol links like cursor:// and vscode: clickable in README rendering.

Use the documentation page for one-click install buttons:

• Open one-click install links for Cursor
• Open one-click install links for VS Code

If you prefer, use the manual configuration examples below in this README.

Cursor

#### Manual Configuration

Add this configuration to .cursor/mcp.json:

{
  "mcpServers": {
    "signoz": {
      "url": "https://mcp.<region>.signoz.cloud/mcp"
    }
  }
}

Need help? See the Cursor MCP docs.

VS Code / GitHub Copilot

#### Manual Configuration

Add this configuration to .vscode/mcp.json:

{
  "servers": {
    "signoz": {
      "type": "http",
      "url": "https://mcp.<region>.signoz.cloud/mcp"
    }
  }
}

Need help? See the VS Code MCP docs.

Claude Desktop

Add SigNoz Cloud as a custom connector in Claude Desktop:

1. Open Claude Desktop.
2. Go to Settings → Developer (or Features, depending on your version).
3. Click Add Custom Connector or Add Remote MCP Server.
4. Enter your SigNoz MCP URL: https://mcp.<region>.signoz.cloud/mcp

When prompted, complete the authentication flow.

Claude Code

Run this command to add the hosted SigNoz MCP server:

claude mcp add --scope user --transport http signoz https://mcp.<region>.signoz.cloud/mcp

After configuring the MCP server, authenticate in a terminal:

claude /mcp

Select the signoz server and complete the authentication flow.

OpenAI Codex

Run this command to add the hosted SigNoz MCP server:

codex mcp add signoz --url https://mcp.<region>.signoz.cloud/mcp

Or add this configuration to config.toml:

[mcp_servers.signoz]
url = "https://mcp.<region>.signoz.cloud/mcp"

After adding the server, authenticate:

codex mcp login signoz

Then run /mcp inside Codex to verify the connection.

SigNoz Cloud Authentication

When you add the hosted MCP URL to your client, the client initiates an authentication flow. You will be prompted to enter:

1. Your SigNoz instance URL (for example, your-instance.signoz.cloud). Protocol-less URLs are accepted; paths, query parameters, and fragments are ignored.
2. Your API key

Create an API key in Settings → API Keys in SigNoz. Only Admin users can create API keys.

Self-Hosted Installation

Download Binary (Recommended)

Download the latest binary from GitHub Releases:

# macOS (Apple Silicon)
curl -L https://github.com/SigNoz/signoz-mcp-server/releases/latest/download/signoz-mcp-server_darwin_arm64.tar.gz | tar xz

# macOS (Intel)
curl -L https://github.com/SigNoz/signoz-mcp-server/releases/latest/download/signoz-mcp-server_darwin_amd64.tar.gz | tar xz

# Linux (amd64)
curl -L https://github.com/SigNoz/signoz-mcp-server/releases/latest/download/signoz-mcp-server_linux_amd64.tar.gz | tar xz

This extracts a signoz-mcp-server binary in the current directory. Move it somewhere on your PATH or note the absolute path for the config below.

Go Install

go install github.com/SigNoz/signoz-mcp-server/cmd/server@latest

The binary is installed as server to $GOPATH/bin/ (default: $HOME/go/bin/server). You may want to rename it:

mv "$(go env GOPATH)/bin/server" "$(go env GOPATH)/bin/signoz-mcp-server"

Docker

Docker images are available on Docker Hub:

docker pull signoz/signoz-mcp-server:latest

Run in HTTP mode:

docker run -p 8000:8000 \
  -e TRANSPORT_MODE=http \
  -e MCP_SERVER_PORT=8000 \
  -e SIGNOZ_URL=https://your-signoz-instance.com \
  -e SIGNOZ_API_KEY=your-api-key \
  signoz/signoz-mcp-server:latest

Use a specific version tag (e.g. v0.1.0) instead of latest for pinned deployments.

Build from Source

git clone https://github.com/SigNoz/signoz-mcp-server.git
cd signoz-mcp-server
make build

The binary is at ./bin/signoz-mcp-server.

Connect to Self-Hosted SigNoz

Prerequisites

• A running SigNoz instance
• SigNoz v0.120.0 or newer for alert rule tools that use the /api/v2/rules APIs
• A SigNoz API key (Settings → API Keys in the SigNoz UI)
• The signoz-mcp-server binary (see Self-Hosted Installation)

Stdio Mode (Claude Desktop / Cursor / Any MCP Client)

Add this to your MCP client config (claude_desktop_config.json, .cursor/mcp.json, etc.). Replace the command path with the absolute path to your signoz-mcp-server binary:

{
    "mcpServers": {
        "signoz": {
            "command": "/absolute/path/to/signoz-mcp-server",
            "args": [],
            "env": {
                "SIGNOZ_URL": "https://your-signoz-instance.com",
                "SIGNOZ_API_KEY": "your-api-key-here",
                "LOG_LEVEL": "info"
            }
        }
    }
}

HTTP Mode

#### With OAuth (Multi-Tenant / Cloud)

Start the server:

TRANSPORT_MODE=http \
MCP_SERVER_PORT=8000 \
OAUTH_ENABLED=true \
OAUTH_TOKEN_SECRET=$(openssl rand -base64 32) \
OAUTH_ISSUER_URL=https://your-public-mcp-url.com \
./signoz-mcp-server

Client config — just the URL, no keys needed:

{
    "mcpServers": {
        "signoz": {
            "url": "https://your-public-mcp-url.com/mcp"
        }
    }
}

The client discovers OAuth endpoints automatically, opens a browser for credentials, and handles token exchange.

#### Without OAuth (Simple Setup)

The API key and SigNoz URL only need to be provided in one place — either on the server or on the client.

Option A — Credentials on the server (simpler client config):

SIGNOZ_URL=https://your-signoz-instance.com \
SIGNOZ_API_KEY=your-api-key \
TRANSPORT_MODE=http \
MCP_SERVER_PORT=8000 \
./signoz-mcp-server

{
    "mcpServers": {
        "signoz": {
            "url": "http://localhost:8000/mcp"
        }
    }
}

Option B — API key on the client (server holds the URL, client sends the key):

SIGNOZ_URL=https://your-signoz-instance.com \
TRANSPORT_MODE=http \
MCP_SERVER_PORT=8000 \
./signoz-mcp-server

{
    "mcpServers": {
        "signoz": {
            "url": "http://localhost:8000/mcp",
            "headers": {
                "SIGNOZ-API-KEY": "your-api-key-here"
            }
        }
    }
}

HTTP Probe Endpoints

HTTP mode exposes unauthenticated probe endpoints. New Kubernetes deployments should use /livez for livenessProbe and /readyz for readinessProbe.

What Can You Do With It?

"Show me all available metrics"
"What's the p99 latency for http_request_duration_seconds?"
"List all active alerts"
"Show me error logs for the paymentservice from the last hour"
"How many errors per service in the last hour?"
"Search traces for the checkout service from the last hour"
"Get details for trace ID abc123"
"Create a dashboard with CPU and memory widgets"
"How do I send Docker logs to SigNoz?"

Available Tools

SigNoz compatibility: alert-rule tools target /api/v2/rules/*, which is available in SigNoz v0.120.0 and newer. Self-hosted deployments on older SigNoz versions will see HTTP 404 from the affected alert-rule tools. Notification-channel tools target the render-envelope /api/v1/channels/* routes introduced by SigNoz/signoz#10941, #10957, #10995, and #10997.

Tool metadata: every tool accepts searchContext, the user's original question/search text. It is used for MCP observability and is not forwarded to SigNoz APIs.

For detailed usage and examples, see the full documentation.

Resource deep links: the resource read tools (signoz_list_dashboards, signoz_get_dashboard, signoz_list_alerts, signoz_list_alert_rules, signoz_get_alert, signoz_list_services, signoz_search_traces, signoz_get_trace_details) include a webUrl field — an absolute deep link to the resource in the SigNoz web UI (per result row for signoz_search_traces) — when the request carries a SigNoz instance URL.

Agent Routing Guidance

Use signoz_search_docs for any SigNoz product question: how-to, feature usage, setup, configuration, API behavior, deployment, instrumentation, OpenTelemetry integration with SigNoz, and troubleshooting. Use live data tools for actual telemetry, alert state, dashboard contents, saved views, and tenant-specific resources. When a docs search result needs exact commands or a specific section, call signoz_fetch_doc.

Docs tools use the same authentication path as other MCP tools.

<details> <summary><strong>Parameter Reference</strong></summary>

#### signoz_list_metrics

Search and list available metrics from SigNoz. Supports filtering by name substring, time range, and source.

• Parameters:
• searchText (optional) - Filter metrics by name substring (e.g., 'cpu', 'memory')
• limit (optional) - Maximum number of metrics to return (default: 50)
• timeRange (optional) - Relative range: 30m, 1h, 6h, 24h, 7d (default: 1h; ignored when both start and end are provided)
• start/end (optional) - Unix ms timestamps. When both are provided, they override timeRange.
• source (optional) - Data-source filter. Use "meter" to list Cost Meter metrics — the usage/billing metrics SigNoz meters on (currently telemetry ingestion volume); omit for the default metrics store
• Completeness note: the response appends a note reporting hasMore (inferred from returnedRows == limit) so a limit-truncated list is never mistaken for the full set; narrow with searchText for more specificity

#### signoz_query_metrics

Query metrics with smart aggregation defaults and validation. Automatically applies the right timeAggregation and spaceAggregation based on metric type (gauge, counter, histogram). Auto-fetches metric metadata if not provided.

• Parameters:
• metricName (required) - Metric name to query
• metricType (optional) - gauge, sum, histogram, exponential_histogram (auto-fetched if absent)
• isMonotonic (optional) - Boolean (or the strings "true"/"false"); auto-fetched if absent. An invalid value is rejected rather than silently treated as false
• temporality (optional) - cumulative, delta, unspecified (auto-fetched if absent)
• timeAggregation (optional) - Aggregation over time (auto-defaulted by type)
• spaceAggregation (optional) - Aggregation across dimensions (auto-defaulted by type)
• groupBy (optional) - Comma-separated field names
• filter (optional) - Filter expression
• timeRange (optional) - Relative time range <number><unit> where unit is m/h/d (e.g. '30m', '1h', '6h', '7d'; default: '1h'; ignored when both start and end are provided)
• start/end (optional) - Unix ms timestamps. When both are provided, they override timeRange.
• stepInterval (optional) - Step in seconds (auto-calculated if omitted)
• requestType (optional) - Response format. Enum: time_series (default), scalar. Unknown values are rejected.
• reduceTo (optional) - For scalar: sum, count, avg, min, max, last, median
• formula (optional) - Expression over named queries (e.g., "A / B * 100")
• formulaQueries (optional) - JSON array of additional named metric queries for formula
• source (optional) - Data-source filter. Use "meter" to query Cost Meter data; omit for the default metrics store

#### signoz_get_top_metrics

Return top 100 metrics ranked by ingested sample volume with pre-computed percentages. Use this to identify which metrics are driving the most ingestion volume and cost. Wraps POST /api/v2/metrics/treemap. Response fields: metricName, percentage (share of total sample volume), totalValue (absolute sample count).

• Parameters:
• timeRange (optional) - Relative time range <number><unit> where unit is m/h/d (e.g. '1h', '24h', '3d', '7d', '30d'; default: '7d'; ignored when both start and end are provided). Start with 7d; if the query times out, retry with 3d, then 24h
• start/end (optional) - Unix ms timestamps. When both are provided, they override timeRange
• Completeness note: returns a fixed top 100 by ingested sample volume; the response appends a note flagging whether the list was truncated at that cap (hasMore)

#### signoz_list_alerts

Lists currently firing/silenced/inhibited alert instances from Alertmanager — not rule definitions. Use signoz_list_alert_rules for configured rules, signoz_get_alert with an id for one full rule definition, or signoz_get_alert_history for the state timeline.

• Parameters:
• limit (optional) - Maximum number of alerts per page (default: 50)
• offset (optional) - Number of results to skip for pagination (default: 0)
• active / silenced / inhibited (optional) - Tri-state filters. Boolean (or the strings "true"/"false"). Omit to defer to the backend default (all states included). An invalid value is rejected rather than silently dropped
• filter (optional) - Comma-separated Prometheus matcher expressions (e.g., alertname="HighCPU",severity="critical")
• receiver (optional) - Regex to filter alerts by receiver name

#### signoz_list_alert_rules

Lists configured alert rules from GET /api/v2/rules, including inactive/OK and disabled rules. Returns compact summaries with ruleId, alert, alertType, ruleType, state, disabled, severity, labels, createdAt, and updatedAt.

• Parameters:
• limit (optional) - Maximum number of rules to return per page (default: 50, max: 1000; higher values are clamped)
• offset (optional) - Number of rules to skip for pagination (default: 0)

#### signoz_get_alert

Gets the rule definition for an alert (GET /api/v2/rules/{id}).

• Parameters: id (required) - Alert rule ID (UUIDv7 on v2-capable servers).
• Note: Response shape depends on the SigNoz server version. Post-#10997 servers return the canonical Rule type with createdAt/updatedAt/createdBy/updatedBy; older servers return GettableRule with createAt/updateAt/createBy/updateBy (no 'd').

#### signoz_list_dashboards

Lists all dashboards with summaries (name, UUID, description, tags).

#### signoz_get_dashboard

Gets complete dashboard configuration.

• Parameters: id (required) - Dashboard UUID

#### signoz_create_dashboard

Creates a dashboard.

• Parameters:
• title (required) – Dashboard name
• description (optional) – Short summary of what the dashboard shows
• tags (optional) – List of tags
• layout (required) – Widget positioning grid
• variables (optional) – Map of variables available for use in queries
• widgets (required) – List of widgets added to the dashboard

#### signoz_import_dashboard

Creates a dashboard from a curated template hosted in the SigNoz/dashboards repo (main branch). The server fetches the template JSON, validates it, and creates the dashboard in one call.

To discover available paths, call signoz_list_dashboard_templates first and let the model pick the best match.

• Parameters:
• path (required) – Template path within the SigNoz/dashboards repo, e.g. hostmetrics/hostmetrics.json

#### signoz_list_dashboard_templates

Returns the full bundled catalog of curated SigNoz dashboard templates (id, title, path, description, category, keywords) as a JSON array. Pair with signoz_import_dashboard: have the model read the catalog, choose the entry that best matches the user's intent, then import it by its path.

• Parameters: none

#### signoz_update_dashboard

Updates an existing dashboard.

• Parameters:
• id (required) – Unique identifier of the dashboard to update
• dashboard (required) – Complete dashboard object representing the post-update state
• title (required) – Dashboard name
• description (optional) – Short summary of what the dashboard shows
• tags (optional) – List of tags applied to the dashboard
• layout (required) – Full widget positioning grid
• variables (optional) – Map of variables available for use in queries
• widgets (required) – Complete set of widgets defining the updated dashboard

#### signoz_list_services

Lists all services within a time range.

• Parameters:
• timeRange (optional) - Relative time range <number><unit> where unit is m/h/d (e.g. '30m', '1h', '6h', '7d'; defaults to last 6 hours; ignored when both start and end are provided)
• start (optional) - Start time in unix milliseconds (defaults to 6 hours ago).
• end (optional) - End time in unix milliseconds (defaults to now)
• limit (optional) - Maximum services per page (default: 50, max: 1000; higher values are clamped)
• offset (optional) - Number of results to skip for pagination (default: 0)

#### signoz_get_service_top_operations

Gets top operations for a specific service.

• Parameters:
• service (required) - Service name
• timeRange (optional) - Relative time range <number><unit> where unit is m/h/d (e.g. '30m', '1h', '6h', '7d'; defaults to last 6 hours; ignored when both start and end are provided)
• start (optional) - Start time in unix milliseconds (defaults to 6 hours ago).
• end (optional) - End time in unix milliseconds (defaults to now)
• tags (optional) - Raw JSON array of tag filters, passed through to the SigNoz API as-is (advanced; the backend expects structured tag-filter objects)

#### signoz_get_alert_history

Gets alert history timeline for a specific rule.

• Parameters:
• id (required) - Alert rule ID
• timeRange (optional) - Relative time range <number><unit> where unit is m/h/d (e.g. '30m', '1h', '6h', '7d'; defaults to last 6 hours; ignored when both start and end are provided)
• start (optional) - Start timestamp in unix milliseconds (defaults to 6 hours ago).
• end (optional) - End timestamp in unix milliseconds (defaults to now)
• state (optional) - Filter by alert state. Enum: firing, inactive (omit for all transitions)
• offset (optional) - Offset for pagination (default: 0)
• limit (optional) - Limit number of results (default: 20, max: 10000; higher values are clamped — paginate with offset)
• order (optional) - Sort order. Enum: asc, desc (default: 'asc')
• Completeness note: the response appends a note reporting hasMore (inferred from returnedRows == limit) and the nextOffset to fetch

#### signoz_list_views

List SigNoz saved Explorer views for a given sourcePage. Supports pagination; response includes a pagination block with total, hasMore, and nextOffset.

• Parameters:
• sourcePage (required) - One of: traces, logs, metrics, meter. Cost Meter views are filed under meter (a distinct Explorer page), not metrics
• name (optional) - Partial-match filter on view name (server-side)
• category (optional) - Partial-match filter on view category (server-side)
• limit (optional) - Page size (default: 50, max: 1000; higher values are clamped)
• offset (optional) - Number of results to skip (default: 0)

#### signoz_get_view

Get a single saved view by UUID.

• Parameters: id (required) - Saved view UUID

#### signoz_search_docs

Search official SigNoz documentation with BM25 over indexed markdown content.

• Parameters:
• searchText (required) - Natural-language or keyword query to search official SigNoz docs
• limit (optional) - Maximum results to return as a string (default: 10, max: 25; a numeric value is also accepted). The 25 ceiling is deliberate — each result hydrates document text out of the in-process docs index, so a larger limit inflates this server's resident memory.
• section_slug (optional) - Exact top-level docs section filter, such as setup, logs-management, apm-distributed-tracing, metrics, alerts, dashboards, signoz-apis, querying, or collection-agents
• searchContext - User's original question

#### signoz_fetch_doc

Fetch full markdown for one official SigNoz docs page from the local index. Accepts only https://signoz.io/docs/... URLs or /docs/... paths.

• Parameters:
• url (required) - Docs page URL or path
• heading (optional) - Heading anchor ID or heading text
• searchContext - User's original question

#### signoz://docs/sitemap

Read-only MCP resource containing the indexed docs sitemap used by the docs search and fetch tools.

#### signoz://logs/query-builder-guide

Read-only MCP resource with logs Query Builder v5 filter syntax, field contexts, body text search, body JSON-path search, timestamp format, and complete raw/aggregation/time-series examples.

#### signoz://traces/query-builder-guide

Read-only MCP resource with traces Query Builder v5 filter syntax, field contexts, built-in span columns, timestamp format, and complete raw/aggregation/time-series examples.

#### signoz_create_view

Create a new saved Explorer view.

• Parameters: JSON payload matching the SavedView schema.
• Tip: Read MCP resources signoz://view/instructions and signoz://view/examples before composing payloads.

#### signoz_update_view

Replace an existing saved view (full-body PUT).

• Parameters:
• id (required) - UUID of the view to replace
• view (required) - Full SavedView object (name, sourcePage, compositeQuery, plus any of category, tags, extraData)
• Tip: Read MCP resources signoz://view/instructions and signoz://view/examples before composing payloads. Call signoz_get_view first, pass its data object under view with whichever fields changed. Partial bodies wipe unspecified fields.

#### signoz_delete_view

Delete a saved view by UUID.

• Parameters: id (required) - Saved view UUID

#### signoz_aggregate_logs

Aggregate logs with count, average, sum, min, max, or percentiles, optionally grouped by fields.

• Parameters:
• aggregation (required) - Aggregation function: count, count_distinct, avg, sum, min, max, p50, p75, p90, p95, p99, rate
• aggregateOn (optional) - Field to aggregate on (required for all except count and rate)
• groupBy (optional) - Comma-separated fields to group by (e.g., 'service.name, severity_text')
• filter (optional) - Filter expression using SigNoz search syntax. Combine conditions with AND, OR, and parentheses. Unknown keys hard-error; ambiguous keys default to resource context. See signoz://logs/query-builder-guide
• service (optional) - Shortcut filter for service name
• severity (optional) - Shortcut filter for severity (DEBUG, INFO, WARN, ERROR, FATAL)
• orderBy (optional) - Order expression and direction (e.g., 'count() desc')
• limit (optional) - Maximum number of groups to return (default: 10, max: 10000; higher values are clamped to bound server memory)
• timeRange (optional) - Relative time range <number><unit> where unit is m/h/d (e.g. '30m', '1h', '6h', '24h', '7d'; default: '1h'; ignored when both start and end are provided)
• start / end (optional) - Start/end time in unix milliseconds. When both are provided, they override timeRange.
• requestType (optional) - scalar (default — one aggregate value over the whole range) or time_series (one value per time bucket). Unknown values are rejected.
• stepInterval (optional) - Time bucket size in seconds for time_series mode. Accepts a number or numeric string (backend auto-selects when omitted)

#### signoz_search_logs

Search logs with flexible filtering across all services.

• Parameters:
• filter (optional) - Filter expression using SigNoz search syntax. Combine conditions with AND, OR, and parentheses (e.g., "(severity_text = 'ERROR' OR body CONTAINS 'panic') AND service.name = 'payment-svc'"). Legacy query is still accepted for backward compatibility, but filter is canonical. See signoz://logs/query-builder-guide
• service (optional) - Service name to filter by
• severity (optional) - Severity filter (DEBUG, INFO, WARN, ERROR, FATAL)
• searchText (optional) - Text to search for in log body (uses CONTAINS matching)
• timeRange (optional) - Relative time range <number><unit> where unit is m/h/d (e.g. '30m', '1h', '6h', '24h', '7d'; default: '1h'; ignored when both start and end are provided)
• start / end (optional) - Start/end time in unix milliseconds. When both are provided, they override timeRange.
• limit (optional) - Maximum number of logs to return (default: 100, max: 10000; higher values are clamped — paginate with offset)
• offset (optional) - Offset for pagination (default: 0)
• Completeness note: the response appends a note reporting hasMore (inferred from returnedRows == limit) and the nextOffset to fetch, so a truncated page is never mistaken for the full result set

#### signoz_get_field_keys

Get available field keys for a given signal (metrics, traces, or logs).

• Parameters:
• signal (required) - Signal type. Enum: metrics, traces, logs
• searchText (optional) - Filter field keys by name substring
• metricName (optional) - Filter by metric name (relevant for metrics signal)
• fieldContext (optional) - Restrict to a field context: resource, attribute (alias tag), scope, log/span/metric (intrinsic/built-in columns), or body (JSON log body). Distinguishes intrinsic columns from user attributes.
• fieldDataType (optional) - Restrict to a data type: string, bool, int64, float64, number, or array forms like []string
• source (optional) - Filter by source

#### signoz_get_field_values

Get possible values for a specific field key for a given signal.

• Parameters:
• signal (required) - Signal type. Enum: metrics, traces, logs
• name (required) - Field key name to get values for (e.g., service.name, http.method)
• searchText (optional) - Filter values by substring
• metricName (optional) - Filter by metric name (relevant for metrics signal)
• fieldContext (optional) - Restrict the lookup to a field context (resource, attribute/tag, scope, log/span/metric, body) when the same key name exists in more than one
• source (optional) - Filter by source

#### signoz_search_traces

Search traces/spans with flexible filtering.

• Parameters:
• filter (optional) - Filter expression using SigNoz search syntax. Combine conditions with AND, OR, and parentheses (e.g., "service.name = 'payment-svc' AND (hasError = true OR responseStatusCode >= 500)"). Legacy query is still accepted for backward compatibility, but filter is canonical. See signoz://traces/query-builder-guide
• service (optional) - Service name to filter by
• operation (optional) - Operation/span name to filter by
• error (optional) - Filter by error status. Boolean (or the strings "true"/"false"). An invalid value is rejected rather than silently dropped
• minDuration / maxDuration (optional) - Min/max span duration in nanoseconds (e.g., '500000000' for 500ms)
• timeRange (optional) - Relative time range <number><unit> where unit is m/h/d (e.g. '30m', '1h', '6h', '24h', '7d'; default: '1h'; ignored when both start and end are provided)
• start / end (optional) - Start/end time in unix milliseconds. When both are provided, they override timeRange.
• limit (optional) - Maximum number of traces to return (default: 100, max: 10000; higher values are clamped — paginate with offset)
• offset (optional) - Offset for pagination (default: 0)
• Completeness note: the response appends a note reporting hasMore (inferred from returnedRows == limit) and the nextOffset to fetch, so a truncated page is never mistaken for the full result set

#### signoz_aggregate_traces

Aggregate trace statistics like count, average, sum, min, max, or percentiles over spans, optionally grouped by fields.

• Parameters:
• aggregation (required) - Aggregation function: count, count_distinct, avg, sum, min, max, p50, p75, p90, p95, p99, rate
• aggregateOn (optional) - Field to aggregate on (e.g., 'durationNano'). Required for all except count and rate
• groupBy (optional) - Comma-separated fields to group by (e.g., 'service.name, name')
• filter (optional) - Filter expression using SigNoz search syntax. Combine conditions with AND, OR, and parentheses. Unknown keys hard-error; ambiguous keys default to resource context. See signoz://traces/query-builder-guide
• service (optional) - Shortcut filter for service name
• operation (optional) - Shortcut filter for span/operation name
• error (optional) - Shortcut filter for error spans. Boolean (or the strings "true"/"false"). An invalid value is rejected rather than silently dropped
• orderBy (optional) - Order expression and direction (e.g., 'avg(durationNano) desc')
• limit (optional) - Maximum number of groups to return (default: 10, max: 10000; higher values are clamped to bound server memory)
• timeRange (optional) - Relative time range <number><unit> where unit is m/h/d (e.g. '30m', '1h', '6h', '24h', '7d'; default: '1h'; ignored when both start and end are provided)
• start / end (optional) - Start/end time in unix milliseconds. When both are provided, they override timeRange.
• requestType (optional) - scalar (default — one aggregate value over the whole range) or time_series (one value per time bucket). Unknown values are rejected.
• stepInterval (optional) - Time bucket size in seconds for time_series mode. Accepts a number or numeric string (backend auto-selects when omitted)

#### signoz_get_trace_details

Gets trace information including all spans and metadata.

• Parameters:
• traceId (required) - Trace ID to get details for
• timeRange (optional) - Relative time range <number><unit> where unit is m/h/d (e.g. '30m', '1h', '6h', '7d'; defaults to last 6 hours; ignored when both start and end are provided)
• start (optional) - Start time in unix milliseconds (defaults to 6 hours ago).
• end (optional) - End time in unix milliseconds (defaults to now)
• includeSpans (optional) - Include detailed span information. Boolean (or the strings "true"/"false"), default: true

#### signoz_create_alert

Create a new alert rule in SigNoz via POST /api/v2/rules.

• Parameters: JSON payload matching the SigNoz alert rule schema.
• Schema varies by `ruleType`:
• threshold_rule / promql_rule → v2alpha1 (structured condition.thresholds, evaluation, notificationSettings).
• anomaly_rule → v1 schema: top-level evalWindow and frequency; condition.op/matchType/target/algorithm/seasonality; anomaly function inside compositeQuery.queries[].spec.functions. Omit thresholds, evaluation, schemaVersion.
• Tip: Read MCP resources signoz://alert/instructions and signoz://alert/examples (the ten canonical SigNoz PR #11023 payloads plus a Cost Meter cumulative-budget example) before composing payloads. For promql_rule, also read signoz://promql/instructions — OTel dotted metric names require the Prometheus 3.x UTF-8 quoted-selector form.

#### signoz_update_alert

Update an existing alert rule via PUT /api/v2/rules/{id}. Replaces the full rule configuration — fetch the current rule with signoz_get_alert first and merge changes on top of it.

• Parameters:
• id (required) - UUIDv7 of the rule to update (obtain from signoz_list_alert_rules / signoz_get_alert).
• Plus all fields of the alert rule schema (same shape as signoz_create_alert).

#### signoz_delete_alert

Delete an alert rule via DELETE /api/v2/rules/{id}. Irreversible — confirm with the user first.

• Parameters:
• id (required) - UUIDv7 of the rule to delete. The server rejects non-UUIDv7 values with invalid_input.

#### signoz_delete_dashboard

Delete a dashboard by ID.

• Parameters: id (required) - Dashboard UUID to delete

#### signoz_list_notification_channels

List notification channels configured in SigNoz.

• Parameters:
• limit (optional) - Maximum number of channels to return per page (default: 50, max: 1000; higher values are clamped)
• offset (optional) - Offset for pagination (default: 0)

#### signoz_create_notification_channel

Create a notification channel and send a test notification.

• Parameters:
• type (required) - Channel type: slack, webhook, pagerduty, email, opsgenie, msteams
• name (required) - Channel name
• send_resolved (optional) - Send notifications when alerts resolve. Boolean (or the strings "true"/"false"), default: true
• Type-specific fields (required by channel type), such as slack_api_url, webhook_url, pagerduty_routing_key, email_to, opsgenie_api_key, or msteams_webhook_url
• Test-send behavior: the channel is created first, then a test notification is sent. If the test fails, the tool still returns success (the channel WAS created) but appends a prominent warning note so the failure is not buried — verify the configuration and re-test.

#### signoz_update_notification_channel

Update an existing notification channel and send a test notification.

• Parameters:
• id (required) - Notification channel UUID
• type (required) - Channel type
• name (required) - Channel name
• send_resolved (optional) - Send notifications when alerts resolve. Boolean (or the strings "true"/"false"), default: true
• Full channel configuration fields for the selected channel type
• Test-send behavior: same as create — a failed verification test-send surfaces a prominent warning note instead of flipping the result to an error.

#### signoz_get_notification_channel

Get a single notification channel by ID (GET /api/v1/channels/{id}).

• Parameters:
• id (required) - Notification channel UUID

#### signoz_delete_notification_channel

Delete a notification channel by ID (DELETE /api/v1/channels/{id}). Irreversible — warn if alert rules still reference this channel.

• Parameters:
• id (required) - Notification channel UUID

#### signoz_execute_builder_query

Executes a SigNoz Query Builder v5 query.

• Parameters: query (required) - Complete SigNoz Query Builder v5 JSON object
• Query types: the per-envelope compositeQuery.queries[i].type selects the spec shape:
• builder_query — signal-specific spec (logs/traces/metrics) with filter, aggregations, groupBy, etc.
• builder_formula — formula expression referencing other query names (e.g. A / B * 100).
• promql — {name, query, disabled, step?, legend?}. PromQL for OTel metrics requires the Prometheus 3.x UTF-8 quoted-selector form {"metric.name.with.dots"}; read the signoz://promql/instructions resource for details.
• clickhouse_sql — {name, query, disabled, legend?}.
• Backend warnings: non-fatal warnings the backend returns (e.g. ambiguous-key resolution) are surfaced as a note alongside the raw response and WARN-logged, matching the search/aggregate/query_metrics tools (previously the body was returned verbatim and warnings were dropped).
• Documentation: See SigNoz Query Builder v5 docs

</details>

Environment Variables

The MCP server does not run an OTLP log exporter; logs are emitted as JSON to stderr. OTEL_LOGS_EXPORTER is therefore not used.

Claude Desktop Extension

Building the Bundle

Requires Node.js. See Anthropic MCPB for details.

make bundle

Installing

1. Open Claude Desktop → Settings → Developer → Edit Config → Add bundle.mcpb
2. Select ./bundle/bundle.mcpb
3. Enter your SIGNOZ_URL, SIGNOZ_API_KEY, and optionally LOG_LEVEL
4. Restart Claude Desktop

Architecture

For a detailed overview of request flow, component interactions, and design decisions, see docs/architecture.md.

Contributing

See CONTRIBUTING.md for development workflow, required docs/manifest sync for MCP changes, and PR checklist.

Made with ❤️ for the observability community