Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Ceramic glaze chemistry: unity formulas, limit checks, substitutes, recipes, shelf and firing logs.
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.
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": {
"glazemath": {
"command": "npx",
"args": [
"-y",
"@reneturcios/glazemath",
"mcp"
]
}
}
}Run this in your terminal
claude mcp add glazemath -- npx -y @reneturcios/glazemath mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"glazemath": {
"command": "npx",
"args": [
"-y",
"@reneturcios/glazemath",
"mcp"
]
}
}
}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": {
"glazemath": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@reneturcios/glazemath",
"mcp"
]
}
}
}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.
These 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 6, 2026
The registry name was verified with the GitHub account CloudCorpRecords, 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.
The registry does not list a required key, though some servers ask you to sign in on first use.
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 (0.1.0) reached the registry yesterday.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js, Docker on your computer.
In the same category: Spec Driven Development, Remote Desktop Commander, HotCodePush
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.
Manage over-the-air (OTA) updates for React Native, Expo, Capacitor and Cordova apps.
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.
glazemath is a small local bridge to the hosted Glazecalc MCP server, which does ceramic glaze chemistry. It can look materials up in a shared library, work out a recipe's unity (Seger) formula, check a recipe against published limits for its firing, convert between cones and temperatures, find substitutes for discontinued materials, remake a recipe from the materials on hand, solve for a target formula, and lay out line, triaxial and progression blends for test tiles. It also reaches the caller's own Glazecalc account: saved recipes, private materials, the on-hand shelf, firing logs, notebook entries, settings and trash.
The bridge keeps no glaze data of its own. It serves the upstream server's tool list locally, exactly as captured from the live endpoint, and forwards each tool call upstream, returning the result untouched. Every record it can change belongs to the caller's own account; there is no sending, payment or third-party surface in the captured tools.
Reference and calculation:
search_materials — find library materials by name, alias or maker. Required: query.get_material — one library material: oxides, loss on ignition, replacements, hazards. Required: name.analyze_recipe — unity formula, oxide groups, silica to alumina ratio, expansion and Stull placement for a recipe. Required: lines.check_limits — check a recipe against recommended limits for its firing. Required: lines.convert_cone_temperature — convert between Orton or SK cones and temperatures. No required fields.suggest_substitutes — modern replacements for discontinued or scarce materials in a recipe. Required: lines.match_from_materials — remake a recipe from only the listed materials. Required: lines, have.solve_target — make a recipe whose formula comes near a target unity formula or analysis. Required: target.blend_recipes — line or triaxial blend tiles between two or three recipes. Required: a, b.vary_material — progression tiles showing what one material does across a range. Required: recipe, material, to.compare_recipes — two recipes side by side, oxide by oxide. Required: a, b.search_guides — search the plain-language guides for potters. Required: query.Your own account records:
list_recipes — list saved recipes, newest first, with search and firing filters. No required fields.get_recipe — one saved recipe with its formula worked out afresh. Required: id.list_my_materials — list materials saved in your own account. No required fields.get_shelf — the materials marked as on hand. No required fields.match_with_what_i_have — remake a recipe from only the shelf materials. No required fields.list_firings — list saved firing logs. No required fields.get_firing — one firing log. Required: id.list_notes — list notebook entries. No required fields.get_my_settings — your saved settings. No required fields.create_recipe — save a new recipe. Required: title, lines.update_recipe — change a saved recipe. Required: id.add_notebook_entry — add a notebook entry. Required: content.add_my_material — save a private material with its analysis. Required: name, analysis.update_my_material — change a private material. Required: id.add_to_shelf — mark materials as on hand. Required: materials.remove_from_shelf — remove materials from the shelf. Required: materials.undo_shelf_change — undo the last shelf change. No required fields.move_to_trash — move one of your records to the trash. Required: kind, id.create_firing_log — save a new firing log. Required: title, columns, rows.add_firing_rows — add readings to a firing log. Required: id, rows.link_firing — save a test result linking a recipe to a firing. Required: recipeId, firingId.Calculated results are guides from published figures, not test results and not a guarantee of food safety — the fired tiles decide.
GLAZECALC_MCP_URL (optional) — override the upstream endpoint. Defaults to https://glazecalcapp.com/mcp. (The override hook is this rebuild's own labelled reconstruction.)GLAZECALC_API_KEY (optional) — when set, every upstream request carries an Authorization: Bearer header, for the caller's own Glazecalc token, which the original's registry record scopes to the caller's own saved records. When it is not set, no key header is sent. (The header name is pinned by the original's registry record; the Bearer scheme and this env forwarding are labelled reconstructions — the original surface was captured keyless.)On the first tool call the client opens a streamable HTTP session with the upstream: a JSON-RPC initialize request (protocolVersion 2025-03-26, clientInfo name glazemath), then a notifications/initialized notification, then the tools/call request carrying the caller's arguments unchanged. When the upstream answers initialize with an Mcp-Session-Id header, that value rides on every later request of the session, which is reused for the life of the process. Replies may arrive as plain JSON or as server-sent events; both are read.
Successful upstream results pass through verbatim, including any isError flag the upstream sets. Failures — a JSON-RPC error, a non-2xx status, an unreadable response, or a request that cannot be completed — come back as an isError result whose text starts with glazemath error: (this rendering is this rebuild's own labelled reconstruction).
Each tool is also a subcommand taking one JSON argument string:
npx @reneturcios/glazemath search_materials '{"query":"custer"}'
npx @reneturcios/glazemath analyze_recipe '{"lines":[{"material":"Custer Spar","amount":30}]}' npx @reneturcios/glazemath get_shelf npx @reneturcios/glazemath --version
Exit codes: 0 on success, 1 on an isError result, 2 on a usage error.
npx -y @reneturcios/glazemath mcp
MCP client config:
{
"mcpServers": { "glazemath": { "command": "npx", "args": ["-y", "@reneturcios/glazemath", "mcp"] } } }
docker run -i ghcr.io/cloudcorprecords/glazemath
docker run --rm ghcr.io/cloudcorprecords/glazemath --version
The container's default command is mcp, so the first form is a stdio MCP server; any other arguments reach the CLI normally.
npm install
npm run build npm test npm run dev
The test suite runs entirely against a stubbed JSON-RPC upstream — no live network calls.
MIT — see LICENSE.