SkillAgentSearch skills...

seq-mcp

Seq Open Telemetry MCP Server

Install / Use

claude mcp add MCLifeLeader -- npx -y github:MCLifeLeader/seq-mcp

If the server publishes to npm under a different name, use that package instead — check the repo README.

About this skill
🔌

MCP Server

Model Context Protocol server

Quality Score

71/100

Category

Operations

Supported Platforms

Claude Code
Claude Desktop

Our assessment of seq-mcp

seq-mcp scores 71/100 on our quality scale, 695th of 760 Operations skills we index.

Its MCP Server is 17 KB long, well organised into 18 sections with 20 code examples: a thorough specification that gives an agent plenty to work with.

It has 3 GitHub stars, so there is little community track record yet; judge it on its content.

Substance
30/30
Structure
20/20
Description
4/15
Adoption
3/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated 12 days ago, so seq-mcp is actively maintained.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 87/100, with 2 cautions from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

seq-mcp compared with similar skills

All 4 of these similar skills score higher than seq-mcp; compare them before choosing.

SkillScoreStarsUpdatedFormat
seq-mcp (this skill)by MCLifeLeader71312d agoMCP Server
Agent-Reachby Panniantong100101.9ktodayCLAUDE.md
headroomby headroomlabs-ai10077.7ktodayCLAUDE.md
CowAgentby zhayujie10047.6ktodayCLAUDE.md
Scraplingby D4Vinci10089.6k2d agoMCP Server

Frequently asked questions

How do I install seq-mcp?
Run claude mcp add MCLifeLeader -- npx -y github:MCLifeLeader/seq-mcp. The install tabs above show the steps for each supported agent.
Which AI agents does seq-mcp work with?
It is written for Claude Code and Claude Desktop, as a MCP Server file. Other agents that read the same format can often use it too.
Is seq-mcp safe to use?
It is MIT-licensed and scores 87/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is seq-mcp still maintained?
The repository was last updated 12 days ago, so seq-mcp is actively maintained.

mcp-seq-otlp

Standalone MCP server that gives AI agents controlled API access to a user-owned Datalust Seq instance.

Official Seq API Docs

What This Service Assumes

  • You already run/manage your own Seq instance.
  • This service only needs connection settings.

Required configuration:

  • SEQ_URL
  • SEQ_API_KEY

URL Support

SEQ_URL accepts either:

  • Host URL (recommended; service will append /api):
    • http://localhost:10150
    • https://seq.example.com
  • Full API base URL (also supported):
    • http://localhost:10150/api
    • https://seq.example.com/api

Available MCP Tools

  • seq_agent_guide: returns agent-focused tool selection rules, recommended workflows, examples, and safety limits.
  • seq_connection_test: validates Seq connectivity and API reachability, and reports the resolved root /health URL used for the check.
  • seq_starter_help: lists the compact starter alias tools.
  • seq_starter_overview: quick health, user, diagnostics, signals, and workspace summary.
  • seq_starter_events_search: common event search by filter/signal/time range.
  • seq_starter_event_by_id: fetch one event by id.
  • seq_starter_data_query: run a q query using GET or POST.
  • seq_starter_signals_list / seq_starter_signal_by_id: signal discovery helpers.
  • seq_starter_dashboards_list: list dashboards.
  • seq_starter_alerts_list: list alerts.
  • seq_starter_events_stream: bounded live-tail style stream call.
  • seq_api_catalog: returns the full official Seq route/verb/permission catalog.
  • seq_api_live_links: discovers live name -> route links from your Seq instance.
  • seq_api_request: generic verb/path invoker for official cataloged Seq API routes.
  • seq_server_ttl: report remaining idle lifetime without resetting the timer.
  • seq_server_keep_alive: reset the idle timer without contacting Seq.
  • seq_<verb>_<route>: auto-generated tool per official route+verb (from docs).

Scope note:

  • seq_starter_* tools are focused on common read workflows.
  • seq_api_request and seq_<verb>_<route> expose the broader HTTP API surface from the Seq endpoint catalog, including non-GET routes.
  • Generic requests are constrained to official route templates, with bounded query/path maps and request/response size limits to reduce accidental high-cost calls.

Agent Usage Process

AI agents should follow this sequence for reliable use:

  1. Start with seq_agent_guide to get the current workflow guidance and example calls.
  2. Use seq_connection_test if the target Seq instance, API key, or URL shape may be wrong.
  3. Use seq_starter_overview to understand the current user, diagnostics status, and visible signals/workspaces.
  4. Prefer seq_starter_events_search, seq_starter_data_query, and other seq_starter_* tools for common read workflows.
  5. For advanced API access, call seq_api_catalog first, then call seq_api_request with the exact official route template.

Short examples:

{
    "tool": "seq_starter_events_search",
    "arguments": {
        "filter": "@Level = 'Error'",
        "count": 50,
        "render": true
    }
}
{
    "tool": "seq_api_request",
    "arguments": {
        "method": "GET",
        "path": "api/events/{id}",
        "pathParams": {
            "id": "event-123"
        },
        "query": {
            "render": "true"
        }
    }
}

Detailed agent workflow guide:

Seq API Key Permissions

Use least privilege based on the exact tools/workflows your MCP client will call.

Authoritative Datalust references:

Recommended permission profiles:

  • Read-focused starter usage (seq_starter_*, seq_connection_test, read-only queries): enable Read; disable Ingest, Write, Project, Organization, System.
  • Full route-surface usage (seq_api_request and seq_<verb>_<route>): required permissions depend on the specific route+verb; check seq_api_catalog or the official endpoint table before granting.

Permission guidance for this project:

| Permission | Needed now | Why | | -------------- | ---------- | ---------------------------------------------------------------------------------------------------------------------- | | Read | Yes | Required by starter query/retrieval workflows. | | Ingest | Usually No | Needed only when calling ingestion routes such as ingest/* or api/events/raw when API-key-for-writing is required. | | Write | Maybe | Needed for write routes (for example signals, dashboards, alerts, permalinks, SQL queries). | | Project | Maybe | Needed for project-scoped administration and some settings/index routes. | | Organization | Maybe | Needed for organization/user-management routes. | | System | Maybe | Needed for system administration routes (for example apps, feeds, backups, updates). |

Starter endpoint mapping in current implementation:

  • GET /health: public endpoint.
  • GET /api/events/resources: public endpoint.
  • GET /api/events: Read permission demand.
  • GET /api/events/{id}: Read permission demand.
  • GET /api/data: Read permission demand.

API Key Header

The server authenticates to Seq using the X-Seq-ApiKey header.

Resilience and Permission Handling

Tool failures are returned as structured MCP error responses (isError: true) instead of crashing the server process.

Current graceful handling includes:

  • 401 Unauthorized: returns guidance to verify SEQ_API_KEY and SEQ_URL.
  • 403 Forbidden: returns a permission-denied response with route-derived permission hints when available.
  • Network/timeout failures: returns connectivity diagnostics for AI clients.
  • Oversized requests/responses: returns actionable limit errors instead of exhausting the server process.
  • Binary responses: returns structured metadata with base64 payloads for non-text endpoints such as icon routes.

Health check behavior:

  • seq_connection_test always probes the Seq host root at /health.
  • If SEQ_URL is configured as either http://host:port or http://host:port/api, the health check resolves to http://host:port/health.

Local Run (Node)

Use Node.js v24.21.0 LTS and npm 12.2.0 (see .nvmrc and package.json). Install the pinned npm version after selecting Node.js:

npm install --global npm@12.2.0
npm ci
npm run build
npm test
npm audit

The Docker build and CI use the same npm version. Both Docker stages pin the Node.js 24.21.0 / Alpine 3.24 image by digest for reproducible builds.

Windows PowerShell:

$env:SEQ_URL = "http://localhost:10150"
$env:SEQ_API_KEY = "your-key"
node dist/index.js

Docker Standalone Run

Docker Hub documentation assets in this repo:

Build image and refresh local MCP catalog artifacts:

./build-docker-image.sh

Run via Docker Compose (recommended for MCP stdio):

PowerShell:

./scripts/run-mcp-compose.ps1 -SeqUrl "http://localhost:10150" -SeqApiKey "<YOUR_SEQ_API_KEY>" -Build

Bash:

./scripts/run-mcp-compose.sh --seq-url "http://localhost:10150" --seq-api-key "<YOUR_SEQ_API_KEY>" --build

Compose run behavior:

  • Value precedence is: explicit script args -> existing environment variables -> .env.
  • If the target .env is missing, scripts create a generic template .env automatically.
  • When that generated generic template is in use, ensure SEQ_URL and SEQ_API_KEY are resolved via script args, existing environment variables, or a populated .env file.
  • MCP_IMAGE_TAG is optional; when empty, Compose uses an untagged image reference (mcp/seq-otlp).
  • Scripts check image availability through compose service metadata and auto-build if the selected tag is not available.
  • By default, no container name is specified, so Docker auto-generates a random name.
  • You can override container name with -ContainerName (PowerShell) or --container-name (Bash).
  • For security, prefer setting SEQ_API_KEY via environment variables or .env instead of CLI args.

Or use helper scripts:

PowerShell:

./build-docker-image.ps1

Bash:

./build-docker-image.sh

Script intent:

  • ./build-docker-image.sh: generates Docker MCP Toolkit manifests, builds and validates the Docker image, and refreshes the local Docker MCP catalog when Docker MCP is available.
  • ./build-docker-image.ps1: generates Docker MCP Toolkit manifests, builds and validates the Docker image, and refreshes the local Docker MCP catalog when Docker MCP is available.
  • ./scripts/run-mcp-compose.sh: runs the MCP server through Docker Compose for stdio use; it can build if needed, but its primary job is to run the container.

Default build behavior:

  • When you run the build script without --tag or -Tag, it builds the named image mcp/seq-otlp, which Docker treats as mcp/seq-otlp:latest.
  • If you want a different reusable image such as mcp/seq-otlp:v0.4.1, pass an explicit tag.
  • --latest-tag or -LatestTag remains optional and adds an additional tag alongside the primary image tag.
  • To skip local Docker MCP catalog refresh, pass -SkipDockerMcpCatalogInstall in PowerShell or --skip-docker-mcp-catalog-install in Bash.

Build and push to registry (pullable by other Docker hosts):

PowerShell:

./build-docker-image.ps1 -Registry ghcr.io/mclifeleader -Tag v0.4.1 -Push

Bash:

./build-docker-image.sh --registry ghcr.io/mclifeleader --tag v0.4.1 --push

By default, the build scripts do not apply an additional tag. If you want one, pass it explicitly with PowerShell -LatestTag <tag> or Bash --latest-tag <tag>.

Build and export tar (loadable with docker load):

PowerShell:

./build-docker-image.ps1 -SaveTar ./mcp-seq-otlp.tar

Bash:

./build-docker-image.sh --save-tar ./mcp-seq-otlp.tar

Run against local Seq:

docker run --rm -i \
  -e SEQ_URL=http://host.docker.internal:10150 \
  -e SEQ_API_KEY=your-key \
    mcp/seq-otlp

Run against FQDN Seq:

docker run --rm -i \
  -e SEQ_URL=https://seq.example.com \
  -e SEQ_API_KEY=your-key \
    mcp/seq-otlp

Run with Podman:

podman build -t mcp/seq-otlp .
podman run --rm -i \
  -e SEQ_URL=https://seq.example.com \
  -e SEQ_API_KEY=your-key \
    mcp/seq-otlp

The container startup contract requires both variables to be present:

  • SEQ_URL
  • SEQ_API_KEY

Optional stability controls:

  • MCP_IDLE_TIMEOUT_MS: idle lifetime in milliseconds, default 900000 (15 minutes), bounded to 1-2147483647.
  • SEQ_TIMEOUT_MS: request timeout in milliseconds, default 30000, bounded to 1000-120000.
  • SEQ_MAX_REQUEST_BYTES: max outbound request body size, default 262144.
  • SEQ_MAX_RESPONSE_BYTES: max inbound response size, default 1048576.

If either is missing, the container exits immediately with a clear startup error.

Container lifecycle

The server automatically stops after 15 minutes without an MCP request. Set MCP_IDLE_TIMEOUT_MS to con

Truncated for display — read the full file on GitHub.

Related Skills

View on GitHub
GitHub Stars3
CategoryOperations
Updated12d ago
Forks0

Languages

TypeScript

Trust signals

87/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

2 low