Local MCP server and supporting skill(s)

[nblumhardt]

This ticket tracks TODOs for the seqcli skills install, seqcli mcp install, and seqcli mcp run commands, which will ship v1s in the 2026.1 release.

Here's how to get started today, compatible with many agents, substitute claude for whatever you're using:

dotnet tool install --global seqcli --prerelease
seqcli config -k connection.serverUrl -v https://seq.example.com
seqcli config -k connection.apiKey -v 1234567890abc
seqcli mcp install -a claude --global
seqcli skill install -a claude --global

Remaining issues and feature gaps (in loose priority order; these may not all make it in time for the 2026.1 release):

• Signal support; currently expecting to add a seq_list_signals tool, a signal (expression) parameter on search and query tools, and a supporting entry in the search-and-query-seq skill
• Review the seq-search-and-query skill to ensure it covers CLI usage equally well
• Investigate and measure alternative schema discovery approaches to increase reliability, e.g. including a "new schema" block in search result responses
• Metrics support
• Improve the examples in SKILL.md to cover non-OTel log/span property naming conventions, e.g. perhaps coalescing @Resource.service.name with Application, re-test
• Investigate supporting a Streamable HTTP transport via seqcli mcp listen (or similar), so that datalust/seqcli can run server-side in a container alongside Seq (or on a Windows server); would likely need API key forwarding and some careful state management
• Script some evaluations
• Add --native as an output format option on seqcli search|query|tail, and nudge agents towards this for full property display
• ...

[gertjvr-ghd]

love the attention on this one, as I am using seq, but using the playwright cli to extract logs for me etc,

Also been using lots of mcps in the past but a recent trend I have noticed is that everything is moving away from mcps to cli + skill, they are way more context friendly over mcp and secure by nature over mcps

just a few examples

• https://playwright.dev/agent-cli/installation
• https://github.com/upstash/context7
• https://developer.atlassian.com/cloud/acli/guides/introduction/

[nblumhardt]

Thanks for dropping by, @gertjvr-ghd!

Aiming for implementation/UX parity between direct seqcli CLI use and the MCP server is a worthwhile goal, thanks for the feedback.

Right now, this might look like:

• Being careful to keep the search-and-query-seq skill agnostic of whether the agent is using the CLI, MCP, or some form of direct UI manipulation/computer use
• Feeding what we've learned about data representation back through the search and query commands, and
• Back-filling feature gaps like schema discovery, where we feel the CLI command set is lacking.

The big difference right now between seqcli search/seqcli query and the MCP server is how results are represented; the MCP server keeps all representation strictly in agent-friendly Seq syntax terms. Both commands already internally support output format switching (e.g. we'd add --native), and we could introduce a global output.nativeTypes config option that the CLI or skills could somehow suggest agents use.

Right now, the MCP server is the CLI via STDIO, so there isn't an additional security boundary involved; if anything, the MCP server makes it easier to keep Seq credentials hidden from agents, so there might be pros/cons on the security front. Hosting the MCP server as an HTTP endpoint opens up the other can of worms 👍

We also tracked the CLI → MCP move earlier this year, but recently we've seen an uptick in requests for an MCP server, so right now it's hard for us to pick which will be the more popular. Which works best probably also comes down to your environment and preferences, and also the relative implementation quality of each option for whatever you're targeting. Happily, it looks like most of what we're doing here will cover both.

Cheers!

[KodrAus]

Improve the examples in SKILL.md

I suspect we'll need to experiment a fair bit with the structure of the skill in general. Right now it's very reference-like, and we may see better results if most of that was moved to a reference file and the skill itself was more role or task centric.

As an example, I played with it using my local Qwen 3.6 27B setup. Using the skill as-is, it didn't actually read or follow most of it and failed to interact with Seq properly. I played with moving most of the contents of SKILL.md into a references/seq-docs.md, and made the SKILL.md instruct the agent to read and understand it, leaving the examples and gotchas in the skill, and appear to have more success with that approach.