MCP Server Builder
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
Workflow skill for KiCAD schematic design via MCP tools. An agent skill from mixelpixx/Konnect.
$ npx skills add mixelpixx/Konnect --skill kicad-schematic -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mixelpixx/Konnect kicad-schematic --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/mixelpixx/Konnect.git skills-src && mkdir -p .claude/skills && cp -r skills-src/crates/konnect/assets/skills/kicad-schematic .claude/skills/kicad-schematic && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "kicad-schematic" agent skill from https://github.com/mixelpixx/Konnect/tree/main/crates/konnect/assets/skills/kicad-schematic into .claude/skills/kicad-schematic/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kicad-schematic", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/mixelpixx/Konnect/tree/main/crates/konnect/assets/skills/kicad-schematicType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add mixelpixx/Konnect --skill kicad-schematic -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mixelpixx/Konnect kicad-schematic --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mixelpixx/Konnect.git skills-src && mkdir -p .agents/skills && cp -r skills-src/crates/konnect/assets/skills/kicad-schematic .agents/skills/kicad-schematic && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "kicad-schematic" agent skill from https://github.com/mixelpixx/Konnect/tree/main/crates/konnect/assets/skills/kicad-schematic into .agents/skills/kicad-schematic/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kicad-schematic", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mixelpixx/Konnect --skill kicad-schematic -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mixelpixx/Konnect kicad-schematic --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mixelpixx/Konnect.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/crates/konnect/assets/skills/kicad-schematic .cursor/skills/kicad-schematic && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "kicad-schematic" agent skill from https://github.com/mixelpixx/Konnect/tree/main/crates/konnect/assets/skills/kicad-schematic into .cursor/skills/kicad-schematic/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kicad-schematic", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/mixelpixx/Konnect.git --path crates/konnect/assets/skills/kicad-schematic--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add mixelpixx/Konnect --skill kicad-schematic -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mixelpixx/Konnect kicad-schematic --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mixelpixx/Konnect.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/crates/konnect/assets/skills/kicad-schematic .gemini/skills/kicad-schematic && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "kicad-schematic" agent skill from https://github.com/mixelpixx/Konnect/tree/main/crates/konnect/assets/skills/kicad-schematic into .gemini/skills/kicad-schematic/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kicad-schematic", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install mixelpixx/Konnect kicad-schematicInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add mixelpixx/Konnect --skill kicad-schematic -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/mixelpixx/Konnect.git skills-src && mkdir -p .github/skills && cp -r skills-src/crates/konnect/assets/skills/kicad-schematic .github/skills/kicad-schematic && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "kicad-schematic" agent skill from https://github.com/mixelpixx/Konnect/tree/main/crates/konnect/assets/skills/kicad-schematic into .github/skills/kicad-schematic/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kicad-schematic", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mixelpixx/Konnect --skill kicad-schematic -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install mixelpixx/Konnect kicad-schematic --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mixelpixx/Konnect.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/crates/konnect/assets/skills/kicad-schematic .opencode/skills/kicad-schematic && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "kicad-schematic" agent skill from https://github.com/mixelpixx/Konnect/tree/main/crates/konnect/assets/skills/kicad-schematic into .opencode/skills/kicad-schematic/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kicad-schematic", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
kicad-schematicWorkflow skill for KiCAD schematic design via MCP tools. An agent skill from mixelpixx/Konnect.
Kicad Schematic is an agent skill from mixelpixx/Konnect. Workflow skill for KiCAD schematic design via MCP tools. Triggers on: "design a circuit", "add a component", "wire up", "connect pins", "build schematic", "place resistor", "place cap", "place IC", "schematic", "add symbol", "net label", "power rail".
Its SKILL.md is about 4.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/common-lib-ids.md` and `references/wiring-patterns.md`).
It sits in Agent Workflows, covering MCP servers. The repository describes itself as: AI-assisted PCB design for KiCAD 10. Native KiCAD plugin — a single Rust binary exposing 217 schematic, layout, routing, placement, design-review, and manufacturing tools to…. The licence is AGPL-3.0.
4 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 9488e5f. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Kicad Schematic loads about 4.1k tokens when it runs, and up to ~6.2k if it reads all its reference files. Until then it costs about 67 tokens; SKILL.md has 1,965 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from mixelpixx/Konnect at commit 9488e5f, republished under its AGPL-3.0 licence (© mixelpixx). 1,965 words, ~4,056 tokens.
.claude/skills/kicad-schematic/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.This skill guides Claude to design schematics using Konnect MCP tools. ALL modifications go through MCP tools — never edit .kicad_sch files directly.
Before any schematic work, load the required toolsets:
load_toolset('sch_components') # place, move, rotate, delete symbols
load_toolset('sch_wiring') # wires, net labels, power symbols, connections
load_toolset('sch_analysis') # connection validation, short and orphan checks
load_toolset('sch_export') # direct ERC and rendered schematic evidence
load_toolset('project') # save_project before formal checksLoad additional toolsets as needed:
load_toolset('library') # search_symbols, get_symbol_info, list_symbol_libraries
load_toolset('sch_batch') # batch operations for 3+ itemsAlways call get_active_toolsets() first to see what is already loaded.
Read references/common-lib-ids.md when choosing
a common generic KiCad symbol. It is a quick-start index, not an allowlist;
search the active libraries when the required part is absent or package-specific.
search_symbols to find the correct lib_idget_symbol_info to see pin names, numbers, and positionslist_schematic_componentsBefore placing or wiring a custom symbol, a manufacturer-specific discrete,
or any package whose view can be mirrored, require the kicad-library skill's
accepted physical pin map for the exact MPN and package suffix. The map must
join each datasheet lead to the symbol pin and footprint pad, identify the
drawing view/direction, reconcile duplicate and mechanical pads, and include
query-back plus disposable rendered inspection. get_symbol_info proves the
library data that exists; it does not prove that data matches the package.
If the accepted physical pin map is missing, incomplete, based on a different suffix, or ambiguous about top/bottom/mating view, stop before real schematic placement. Do not infer physical numbering from a generic symbol name or from the order pins appear on screen.
| Component | lib_id |
|---|---|
| Resistor | Device:R |
| Capacitor | Device:C |
| Capacitor Polar | Device:C_Polarized |
| Inductor | Device:L |
| LED | Device:LED |
| Diode | Device:D |
| Zener | Device:D_Zener |
| NPN Transistor | Transistor_BJT:Q_NPN_BEC |
| PNP Transistor | Transistor_BJT:Q_PNP_BEC |
| N-MOSFET | Transistor_FET:Q_NMOS_GDS |
| P-MOSFET | Transistor_FET:Q_PMOS_GDS |
| 2-pin Connector | Connector_Generic:Conn_01x02 |
| 4-pin Connector | Connector_Generic:Conn_01x04 |
| Ground | power:GND |
| +3.3V | power:+3V3 |
| +5V | power:+5V |
| VCC | power:VCC |
| VDD | power:VDD |
Power symbols: GND uses 0 (arrow points down), VCC/VDD/+3V3/+5V use 0 (arrow points up).
Read references/wiring-patterns.md when
choosing between direct wires and labels or when building one of its common
subcircuits. Verify every named pin against the placed symbol before applying a
pattern.
| Scenario | Method | Why |
|---|---|---|
| Two pins physically close (<30mm) | connect_pins | Direct wire, auto-routed |
| Named signal (SDA, MOSI, EN, etc.) | connect_to_net | Stub wire + net label, cleaner |
| Power rail (VCC, GND, +3V3) | add_power_symbol | Proper power symbol, global net |
| Bus signals (D0-D7) | connect_to_net | Net labels with bus naming |
| Cross-sheet signal | Global label | Connects across schematic sheets |
| Multiple pins to same net (3+) | batch_connect_to_net | Efficient bulk operation |
Use for direct pin-to-pin connections. The tool auto-routes with L-bends.
connect_pins(schematic, ref1, pin1, ref2, pin2)Use for named nets. Creates a short stub wire and attaches a net label.
connect_to_net(schematic, reference, pin_number, net)pin_x/pin_y: the stub then points away
from the symbol body on its own, instead of the label text running back
across the pin names. Override with direction only to fix a layout clash.batch_connect_to_net does the same for many pins in one read/write. By
default it places its labels directly on the pin endpoints without stubs;
pass stub_length, direction and label_type for connect_to_net's
layout on every pin in the call.add_schematic_net_label instead? Take its
rotation from orientation_degrees in get_schematic_pin_locations, or the
text reads back across the symbol's pin names.add_power_symbol or add_schematic_net_label with
label_type: global_label; both are one net across all sheets and instances.Use for all power connections, in preference to labelling a pin with the rail name. The one exception is a rail that must stay separate per instance of a repeated sheet — see below.
add_power_symbol(schematic, power_net, x, y, rotation?)get_schematic_pin_locations) — a power symbol carries its
pin at its own origin, so the two coinciding is the connection.power_net is loaded as power:<power_net>, so it must name a symbol in
KiCad's power library: +3V3 and +12V, never 3V3 or 12V. A miss is an
error and nothing is placed.rotation defaults to 0 — see Rotation Conventions above.+5V symbol on every sheet, and in every
instance of a sheet, joins one +5V net. A rail that must stay separate per
instance of a repeated sheet (each node's own 5V, say) takes a local net
label via connect_to_net instead — power:+5V there shorts all the
instances' rails together.Load sch_batch toolset when placing 3 or more components or making bulk connections.
Place multiple components in one call. Provide schematic and a components array of {lib_id, x, y, rotation?, reference?, value?, unit?} objects. Pass reference explicitly for each component -- it is not auto-assigned.
The batch commits all symbols once, then reconciles every new pin endpoint in that same atomic write. Check the "junctions_added_count" and "junctions_pruned_count" response fields; a pin placed mid-segment on an existing wire is not electrically connected in KiCad unless the required junction was added.
Connect multiple pins to the same net in one call. Ideal for:
Bulk-modify component properties (values, footprints, fields) across multiple components.
The default remains update-only. Set create_missing: true to create a missing
custom field on every placed unit of each named component. Reference, Value,
Footprint and Datasheet are never created through this option; use the
dedicated arguments or workflows for built-in fields. Inspect each result's
“updated_units” and “created_units” counts, because a partially populated
multi-unit component can report both.
Place 100nF cap (Device:C) within 5mm of IC power pin. Connect one pin to VCC via power symbol, other pin to GND via power symbol. One cap per VCC/VDD pin.
Place resistor (Device:R) vertically. Connect one pin to the signal net via connect_to_net, other pin to VCC via add_power_symbol. Typical values: 4.7k for I2C, 10k for general.
Two resistors in series, vertically aligned. Top to input net, middle junction to output net, bottom to GND. Use connect_to_net for input/output, add_power_symbol for GND.
Resistor in series with LED. Connect resistor to signal/power, resistor to LED anode, LED cathode to GND. R = (Vsupply - Vf) / If. Typical: 330R for 3.3V, 470R for 5V.
For analog circuits: 100nF ceramic + 10uF electrolytic in parallel, close to power pins. Place ceramic closest to IC.
Crystal (Device:Crystal) between XI and XO pins. Two load capacitors from each crystal pin to GND. Typical load caps: 12-22pF. Optional 1M feedback resistor across crystal.
After placing components and wiring, always run these checks:
Numbers ? designators the way eeschema's Tools → Annotate does (ascending X, first free number in the project, numbers reserved across every sheet instance in the file) and writes both places a designator lives. The units of one multi-unit part get one shared designator. Duplicated designators are reported, not fixed: read unresolved and the outcome — partial means the schematic still has a conflict — and pass resolve_duplicates: true to renumber all but the first of each group of separate parts; a shared designator that could be the units of one package is never renumbered, so fix those by hand. It annotates one project's instance records (the schematic's owner, or project) and never edits another project's; numbers used on the project's other sheets are reserved through its sheet tree (the response lists the sheets it consulted), but duplicates already spread across sheets are not detected, so annotate each sheet and then run run_erc. Run after all placement is complete; dry_run: true shows the plan first.
Checks that all wires connect properly to pins. Reports:
Verifies that components have the expected connections. Reports:
Finds floating wires, labels, and symbols that are not connected to anything.
annotate_schematic, then save with save_project.validate_wire_connections and validate_component_connections.find_shorted_nets; reconcile each finding against the intended nets.find_orphan_items as a heuristic and corroborate its findings.run_erc and classify every violation.render_schematic_png with inline output and inspect the actual image.The agent can see its own schematic. After meaningful edits:
render_schematic_png — rasterize the sheet (pass inline true to get
the image back as base64 and actually look at it).set_visual_baseline — capture the known-good render before a batch of
edits (stored under the project's own state directory with the source
hash and renderer identity).compare_visual_baseline — after edits: PASS/DRIFT against a 2% content
threshold with the changed region's bounding box. "No baseline stored" is
a normal state, and a baseline from an older renderer is flagged rather
than silently trusted.Use the loop to catch what connectivity checks cannot. Completion requires coherent functional grouping, label-inclusive overlap inspection, clear signal flow, and page-boundary acceptance for every symbol, label, and note. Inspect the image itself; a successful render command is not visual acceptance.
Apply this order when evidence disagrees:
A weaker heuristic may raise a question but does not override stronger direct
evidence. If any required check did not run, failed structurally, returned
impossible coverage, or contradicts stronger evidence without resolution, the
result is INCOMPLETE. Report the blocked evidence and stop short of a clean or
production-ready claim.
get_schematic_pin_locations or get_symbol_info to look up pin numbers before connectingsearch_symbols to confirm lib_id existsadd_power_symbol for rails, not net labels; the exception is a rail that must stay separate per instance of a repeated sheet, which takes a local label because power symbols are globalsave_project after major operationsget_active_toolsets() and load what you need before starting© mixelpixx, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 2 other files (references) in crates/konnect/assets/skills/kicad-schematic of mixelpixx/Konnect.
Open the folder on GitHubat commit 9488e5f
Kicad Schematic next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Kicad Schematic this skillmixelpixx/Konnect | 905 | — | ~4.1k | Automated safety check: Pass | AGPL-3.0 | |
| MCP Server Builderanthropics/skills | 180k | 64 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| MCP Server BuildershareAI-lab/learn-claude-code | 78k | 5 repos | ~1.2k | Automated safety check: Pass | MIT | |
| MCP Integration for Pluginsanthropics/claude-plugins-official | 38k | 11 repos | ~3.1k | Automated safety check: Pass | Apache-2.0 | |
| Microsoft Skill CreatorMicrosoftDocs/mcp | 1.9k | 3 repos | ~2.1k | Automated safety check: Pass | CC-BY-4.0 | |
| Fastmcp Client CLIPrefectHQ/fastmcp | 28k | 1 repos | ~823 | Automated safety check: Pass | Apache-2.0 |
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
shareAI-lab/learn-claude-code
Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.
anthropics/claude-plugins-official
Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.
MicrosoftDocs/mcp
Create agent skills for Microsoft technologies using official documentation.
PrefectHQ/fastmcp
Query and invoke tools on MCP servers using fastmcp list and fastmcp call.
charmbracelet/crush
Explains how to configure the Crush coding agent with crushrc or crush.json, covering providers, models, LSPs, MCP servers, hooks, permissions and config precedence.
mixelpixx/Konnect
Manufacturing and fabrication workflow for KiCAD projects via MCP tools.
mixelpixx/Konnect
Design review and validation workflow for KiCAD projects via MCP tools.
mixelpixx/Konnect
Workflow skill for KiCAD PCB layout and routing via MCP tools.
mixelpixx/Konnect
Mandatory operating rules for ANY task involving KiCAD projects.
mixelpixx/Konnect
Library management workflow for KiCAD — creating symbols, footprints, and managing libraries via MCP tools.
Categories
Workflow skill for KiCAD schematic design via MCP tools. An agent skill from mixelpixx/Konnect. Kicad Schematic is an agent skill from mixelpixx/Konnect. Workflow skill for KiCAD schematic design via MCP tools.
Kicad Schematic fits situations like: : design a circuit; add a component; build schematic.
Run `npx skills add mixelpixx/Konnect --skill kicad-schematic -a claude-code`. Or copy the skill folder (crates/konnect/assets/skills/kicad-schematic in mixelpixx/Konnect) into .claude/skills/kicad-schematic in your project. Claude Code loads it when a task matches its description.
Run `npx skills add mixelpixx/Konnect --skill kicad-schematic -a codex`. Or copy the skill folder (crates/konnect/assets/skills/kicad-schematic in mixelpixx/Konnect) into .agents/skills/kicad-schematic in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mixelpixx/Konnect --skill kicad-schematic -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/kicad-schematic, .gemini/skills/kicad-schematic, .github/skills/kicad-schematic and .opencode/skills/kicad-schematic in your project.
SKILL.md names no scripts, command-line tools or credentials: Kicad Schematic is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Kicad Schematic is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 4.1k tokens (SKILL.md is roughly 16k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.1k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Kicad Schematic: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MCP Integration for Plugins (anthropics/claude-plugins-official, 38k stars) and Microsoft Skill Creator (MicrosoftDocs/mcp, 1.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
mixelpixx (a GitHub user) maintains it in mixelpixx/Konnect, which has 905 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on October 6, 2026.
Source: mixelpixx/Konnect on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.