Seq MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SEQ_API_KEY | No | Seq API Key for authentication (CLI flag: -k, --api-key) | |
| SEQ_WORKSPACE | No | Default workspace identifier (CLI flag: -w, --workspace) | default |
| SEQ_SERVER_URL | No | Base URL of the Seq server (CLI flag: -u, --url) | http://localhost:5341 |
| SEQ_TIMEOUT_MS | No | Request timeout in milliseconds | 30000 |
| SEQ_SECRETS_PATH | No | Path to secrets.json for multi-tenant workspace keys (CLI flag: -s, --secrets) | secrets.json |
| SEQ_MCP_LOG_LEVEL | No | Log level (debug, info, warn, error, silent) (CLI flag: -l, --log-level) | info |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
| resources | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| seq_searchC | Search historical structured log events in Seq with filters, date ranges (ISO 8601), signal IDs, and pagination. For all events, leave filter empty or use '*'. |
| seq_queryC | Execute an analytical SQL-like query against Seq log data (e.g., "select count(*) from stream group by time(5m)", "select @Timestamp, @Message, @Level from stream where @Level = 'Error' limit 50"). |
| seq_list_signalsB | List available signals (saved searches and predefined filters) in Seq. Returns signal IDs, titles, descriptions, and filter expressions. |
| seq_get_signalC | Get detailed configuration and filter rules of a specific signal by ID. |
| seq_convert_filterC | Convert a fuzzy or relaxed user search string into strict Seq filter syntax (e.g. converts 'error' or 'user==alice' into strict expressions). |
| seq_tail_eventsB | Wait for and capture recent or live stream events from Seq within a specified timeout window. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Seq Saved Signals | List of all shared signals (saved searches and filters) configured in Seq. |
| Seq Server Information | Metadata about the connected Seq instance including version and available endpoints. |
TDQS
Scored across 6 tools
Most tools are clearly distinct: signals listing/retrieval, filter conversion, and live tailing each have unique purposes. However, seq_search for historical events and seq_query for analytical SQL-like queries could be confused by an agent deciding how to retrieve or analyze log data. Descriptions provide enough guidance to resolve most ambiguity.
All tools use a consistent seq_ prefix followed by a verb_noun pattern in snake_case (seq_search, seq_list_signals, seq_get_signal, etc.). No mixed conventions or vague naming.
Six tools is well-scoped for a Seq log querying server, covering search, analytical query, signal inspection, filter conversion, and live tailing without bloat. Each tool earns its place for the core workflows.
The server covers key read and query operations: historical search, SQL-like analytics, signal discovery, filter conversion, and live tailing. Minor gaps exist around managing signals (e.g., create/update/delete) and exporting results, but core agent workflows are supported.