Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
MCP server for Inductive Automation Ignition: tags, alarms, history, and Perspective
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
IGNITION_URL, IGNITION_API_TOKEN, IGNITION_BRIDGE_SECRET, IGNITION_ALLOW_WRITESValues marked secret are keys to your account. Never share them or paste them into a chat.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"ignition": {
"command": "uvx",
"args": [
"ignition-mcp"
],
"env": {
"IGNITION_URL": "your-value",
"IGNITION_API_TOKEN": "your-value",
"IGNITION_BRIDGE_SECRET": "your-value",
"IGNITION_ALLOW_WRITES": "your-value"
}
}
}
}Run this in your terminal
claude mcp add ignition --env IGNITION_URL=your-value --env IGNITION_API_TOKEN=your-value --env IGNITION_BRIDGE_SECRET=your-value --env IGNITION_ALLOW_WRITES=your-value -- uvx ignition-mcpFill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"ignition": {
"command": "uvx",
"args": [
"ignition-mcp"
],
"env": {
"IGNITION_URL": "your-value",
"IGNITION_API_TOKEN": "your-value",
"IGNITION_BRIDGE_SECRET": "your-value",
"IGNITION_ALLOW_WRITES": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"ignition": {
"type": "stdio",
"command": "uvx",
"args": [
"ignition-mcp"
],
"env": {
"IGNITION_URL": "your-value",
"IGNITION_API_TOKEN": "your-value",
"IGNITION_BRIDGE_SECRET": "your-value",
"IGNITION_ALLOW_WRITES": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
IGNITION_ALLOW_WRITES envThese settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
The registry name was verified with the GitHub account jsgorana, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
You need to fill in: IGNITION_URL, IGNITION_API_TOKEN, IGNITION_BRIDGE_SECRET
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (0.1.3) reached the registry 4 months ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Python (uv) on your computer.
In the same category: Spec Driven Development, Remote Desktop Commander, Starreel
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Turn a script into a finished, downloadable short-drama episode — via MCP or REST.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
An MCP (Model Context Protocol) server for Inductive Automation Ignition. It gives an AI assistant, Claude Desktop, Claude Code, or any MCP client, structured access to an Ignition gateway: browse and write tags, query history and alarms, manage projects, and deploy full Perspective views.
Tested against Ignition 8.3. 43 tools spanning tags, history, alarms, projects, gateway administration, and Perspective. The server is read-only by default; every write is gated behind an explicit opt-in.
You: "Deploy a Perspective dashboard to a new project called LineOverview with a
gauge bound to [default]Line1/Speed." Claude: (bootstraps the project, writes the view, wires the tag binding, triggers a scan) -> https://gateway:8088/data/perspective/client/LineOverview
Ignition 8.3 ships a native REST API, but it doesn't expose live tag values, tag history, alarm queries, or Perspective view resources. ignition-mcp covers the gap with two transport planes:
/data/api/v1 API, authenticated with an API key, used for projects, gateway configuration, modules, logs, backups, and Perspective session diagnostics.mcp-bridge) you install once on the gateway. It exposes the gateway scripting surface (system.tag.*, system.alarm.*, system.db.*, and project file I/O) over HMAC-signed HTTP requests.Tools that need the bridge degrade with a clear message if it isn't installed. Run ignition_diagnose any time to see what's configured and what's missing.
Gateway web UI -> Config -> Security -> API Keys -> Create. Give it a name, for example claude. Copy the full token; it looks like claude:AbCd....
The key's auto-created security level (Authenticated/ ) needs to be granted gateway read/write access under Config -> Security -> General -> Gateway Read/Write Permissions. Skip this step and calls return HTTP 403; ignition_diagnose will tell you and give the exact fix.
pipx install ignition-mcp
Claude Desktop (claude_desktop_config.json) or Claude Code (.mcp.json):
{
"mcpServers": { "ignition": { "command": "ignition-mcp", "env": { "IGNITION_URL": "http://localhost:8088", "IGNITION_API_TOKEN": "claude:YOUR_SECRET_HERE" } } } }
Restart the client and ask it to run ignition_diagnose. You should get an all-green checklist, aside from a warning about the bridge, which is the next step.
Generate a random secret, enable writes, and let the server install the bridge for you:
"env": {
"IGNITION_URL": "http://localhost:8088", "IGNITION_API_TOKEN": "claude:YOUR_SECRET_HERE", "IGNITION_BRIDGE_SECRET": "a-long-random-string", "IGNITION_ALLOW_WRITES": "true" }
Ask your assistant to install the bridge (this runs the bridge_install tool), then run ignition_diagnose again to confirm the bridge check is green. See docs/bridge.md for the manual install path and troubleshooting.
| Variable | Required | Default | Meaning |
|---|---|---|---|
IGNITION_URL | yes | none | Gateway base URL, e.g. http://localhost:8088 |
IGNITION_API_TOKEN | yes | none | API key, name:secret |
IGNITION_BRIDGE_SECRET | no | unset | HMAC secret for the bridge; bridge tools are disabled without it |
IGNITION_ALLOW_WRITES | no | false | Master switch for every mutating tool |
IGNITION_TLS_VERIFY | no | true | Set to false for self-signed dev gateways |
IGNITION_TIMEOUT_S | no | 30 | Per-request timeout, in seconds |
IGNITION_TAG_WRITE_ALLOWLIST | no | unset | Comma-separated glob patterns; tag writes outside them are refused |
IGNITION_ALLOW_WRITES=true and the call passes confirm=true. Your assistant sets confirm after you approve the action.mcp-bridge logger. Secrets are never logged or echoed back.data/projects/; nothing outside that tree is reachable.| Area | Tools |
|---|---|
| Diagnostics | ignition_diagnose, gateway_info, gateway_trial_status, gateway_trial_reset |
| Tags | tag_browse, tag_read, tag_write, tag_create, tag_config_export, tag_config_import |
| History | history_query, history_providers |
| Alarms | alarm_status, alarm_journal, alarm_acknowledge |
| Projects | project_list, project_get, project_create, project_delete, project_export, project_import, project_scan |
| Perspective | perspective_bootstrap_project, perspective_list_views, perspective_get_view, perspective_upsert_view, perspective_delete_view, perspective_validate_view, perspective_page_config_get/set, perspective_session_props_get, perspective_style_upsert, perspective_list_sessions |
| Gateway admin | gateway_modules, gateway_logs_query, gateway_logger_set_level, gateway_backup, gateway_performance, config_resource_list |
| Database | db_run_named_query, db_query |
| Bridge | bridge_install, bridge_status |
The server also exposes MCP resources the assistant can read to author valid Perspective views: ignition://docs/view-schema and ignition://templates/view/{flex-basic,coordinate-basic,tag-bound-dashboard}.
See docs/perspective-authoring.md for the full writeup. In short: the assistant reads the view-schema resource, starts from a template, validates offline with perspective_validate_view, then deploys with perspective_upsert_view, which validates again, writes the view, and triggers a project scan. A full round-trip example is in examples/deploy-dashboard.md.
git clone https://github.com/jsgorana/ignition-mcp
cd ignition-mcp python -m venv .venv && source .venv/bin/activate pip install -e ".[dev]"
ruff check src tests # lint ruff format --check src tests # format check mypy src # type check pytest tests/unit # unit tests, no gateway needed python bridge/build_zip.py # rebuild the bridge project archive
IGNITION_URL=... IGNITION_API_TOKEN=... IGNITION_BRIDGE_SECRET=... \ IGNITION_ALLOW_WRITES=true python tests/live/live_check.py
Built on the Model Context Protocol and its Python SDK, using httpx for HTTP. The ignition-sdk-examples repository was a useful reference while working out how Ignition's module and scripting APIs fit together.
MIT. See LICENSE.
This project is independent and community-built. It is not affiliated with, endorsed by, or sponsored by Inductive Automation. "Ignition" and "Perspective" are trademarks of Inductive Automation, LLC, used here only to describe compatibility. Test any write-enabled tool against a non-production gateway before pointing it at something that matters.