Gives AI coding agents searchable CleanSlice architecture docs and conventions for NestJS and Nuxt full-stack apps.
Also known as CleanSlice/mcp, mcp
- Stars
- 18
- Tools
- 4
- Downloads, 30 days
- —
- Latest version
- 1.0.0
- Last commit
- Oct 26, 2026
- License
- MIT
What is CleanSlice MCP?
CleanSlice gives AI coding agents searchable CleanSlice architecture docs and conventions for NestJS and Nuxt full-stack apps. It exposes 4 tools, such as get-started, list-categories, search.
Summary generated from the project's README
About CleanSlice MCP server
Providing AI coding agents with precise architectural guidance for NestJS and Nuxt full-stack applications is what CleanSlice accomplishes. It serves as a specialized knowledge bridge, allowing developers to connect their AI tools to a structured repository of CleanSlice conventions and implementation standards. This ensures that agents do not guess architectural patterns but instead follow established rules for full-stack development.
Developers can integrate this server with various MCP-compatible clients including Claude, Cursor, Windsurf, and VS Code Copilot. The setup can be managed via remote HTTP connections or by running the server locally using Bun or Docker. The system provides specific tools like get-started to load core rules, list-categories to browse documentation areas, search to find specific snippets, and read-doc to retrieve full document content when more detail is required.
What you can do with it
- 1Enforce architectural standardsInstruct an AI agent to follow specific CleanSlice rules before it begins writing any new application code.
- 2Discover framework conventionsAsk the AI to find specific implementation details or edge cases for NestJS or Nuxt features using the search tool.
- 3Retrieve full documentationHave the AI agent read an entire architectural guide after finding a relevant snippet through a search query.
Written from the project's README. Every use case is checked against a quote from it.
How to install CleanSlice MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall CleanSlice MCP in Claude Code
$ claude mcp add --transport http mcp https://mcp.cleanslice.org/mcpInstall CleanSlice MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"mcp": {
"url": "https://mcp.cleanslice.org/mcp"
}
}
}Install CleanSlice MCP in VS Code
.vscode/mcp.json
{
"servers": {
"mcp": {
"type": "http",
"url": "https://mcp.cleanslice.org/mcp"
}
}
}Install CleanSlice MCP in VS Code CLI
$ code --add-mcp '{"name":"mcp","type":"http","url":"https://mcp.cleanslice.org/mcp"}'Install CleanSlice MCP in Codex
$ codex mcp add mcp --url https://mcp.cleanslice.org/mcpInstall CleanSlice MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.mcp] url = "https://mcp.cleanslice.org/mcp"
Install CleanSlice MCP in Gemini CLI
$ gemini mcp add -s user --transport http mcp https://mcp.cleanslice.org/mcpInstall CleanSlice MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"mcp": {
"url": "https://mcp.cleanslice.org/mcp",
"type": "http"
}
}
}CleanSlice MCP tools 4
Detected from the READMEget-startedlist-categoriessearchread-doc
Automated checks
Ran Nov 12, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablePass
- Open source license (OSI)Pass
- Commit or release in the last yearPass
- Package name not close to a popular packageNot checked
- Remote endpoint uses HTTPSPass
- Destructive tools are labelledPass
- No hidden instructions to the modelPass
- No critical advisory in the package or its dependenciesNot checked
README
View on GitHubCleanSlice MCP Server
MCP (Model Context Protocol) server that gives AI coding agents access to the CleanSlice architecture documentation. Connect it to Claude, Cursor, Windsurf, or any MCP-compatible client so the AI knows how to build apps using CleanSlice conventions.
Installation
Run this command. See Claude Code MCP docs for more info.
claude mcp add --scope user --transport http cleanslice https://mcp.cleanslice.org/mcp
Remove
--scope userto install for the current project only.
Tip: enforce MCP usage with CLAUDE.md
To make sure Claude Code always consults the CleanSlice MCP before writing any code, add the following to your project's CLAUDE.md:
## CleanSlice MCP — Required
Before writing or modifying any code you MUST consult the CleanSlice MCP:
1. Call `get-started` to load the core architecture rules.
2. Call `list-categories` to see available documentation areas.
3. Call `search` with at least 2 task-relevant queries covering:
(a) core implementation details for the feature you are building,
(b) edge cases, constraints, or standards that apply.
4. Call `read-doc` to read the full document when search snippets aren't enough.
Do NOT guess conventions — always verify against MCP results first.
This ensures the agent reads CleanSlice docs at the start of every task, not after the fact.
Optional: add a Stop hook as a safety net
To catch cases where the agent skips the MCP despite the CLAUDE.md instruction, add this to .claude/settings.json:
{
"hooks": {
"Stop": [
{
"hooks": [
{
"type": "agent",
"timeout": 180,
"prompt": "You are a verification subagent. Your job: ensure the main Claude Code agent used the `cleanslice` MCP knowledge sufficiently and did not guess.\n\nContext JSON:\n$ARGUMENTS\n\nVerification requirements:\n1) Identify what the user asked for (deliverables + constraints) from the conversation/transcript in $ARGUMENTS.\n2) Verify the agent consulted the `cleanslice` MCP server for relevant knowledge BEFORE finalizing:\n - Must call `cleanslice` \"get-started\" at least once (or equivalent) to confirm the server's purpose and usage.\n - Must call \"list-categories\" to understand the available knowledge areas.\n - Must call \"search\" with task-relevant queries (at least 2 searches) covering: (a) core implementation details, (b) edge cases / constraints.\n - May call \"read-doc\" to get full document content when search snippets are insufficient.\n3) Validate coverage:\n - If any required category is relevant but not checked, fail.\n - If answers include specifics that are not supported by MCP results, fail.\n4) Output STRICT JSON only:\n - If everything is verified: {\"ok\": true}\n - If anything is missing/unsupported: {\"ok\": false, \"reason\": \"What is missing + exact MCP calls the main agent must run next (e.g., run list-categories, then search for X/Y, then update the solution).\"}\n\nImportant:\n- `cleanslice` tools will appear as MCP tools. Use whatever exact tool names are available in this environment (they follow the mcp__<server>__<tool> naming pattern).\n- Do not allow stopping until MCP-backed evidence is sufficient."
}
]
}
]
}
}
Go to: Settings -> Cursor Settings -> MCP -> Add new global MCP server
Paste the following into your Cursor ~/.cursor/mcp.json file. You may also install in a specific project by creating .cursor/mcp.json in your project folder. See Cursor MCP docs for more info.
{
"mcpServers": {
"cleanslice": {
"type": "http",
"url": "https://mcp.cleanslice.org/mcp"
}
}
}
Tip: enforce MCP usage with a Cursor rule
Create .cursor/rules/cleanslice.mdc in your project to make Cursor always consult the MCP before writing code:
---
description: CleanSlice architecture rules
globs: **/*.{ts,vue,prisma}
alwaysApply: true
---
## CleanSlice MCP — Required
Before writing or modifying any code you MUST consult the CleanSlice MCP:
1. Call `get-started` to load the core architecture rules.
2. Call `list-categories` to see available documentation areas.
3. Call `search` with at least 2 task-relevant queries covering:
(a) core implementation details for the feature you are building,
(b) edge cases, constraints, or standards that apply.
4. Call `read-doc` to read the full document when search snippets aren't enough.
Do NOT guess conventions — always verify against MCP results first.
Add to your Windsurf MCP config file. See Windsurf MCP docs for more info.
{
"mcpServers": {
"cleanslice": {
"type": "http",
"serverUrl": "https://mcp.cleanslice.org/mcp"
}
}
}
Tip: enforce MCP usage with a Windsurf rule
Create .windsurf/rules/cleanslice.md in your project to make Windsurf always consult the MCP before writing code:
## CleanSlice MCP — Required
Before writing or modifying any code you MUST consult the CleanSlice MCP:
1. Call `get-started` to load the core architecture rules.
2. Call `list-categories` to see available documentation areas.
3. Call `search` with at least 2 task-relevant queries covering:
(a) core implementation details for the feature you are building,
(b) edge cases, constraints, or standards that apply.
4. Call `read-doc` to read the full document when search snippets aren't enough.
Do NOT guess conventions — always verify against MCP results first.
Add to .vscode/mcp.json in your project. See VS Code MCP docs for more info.
{
"servers": {
"cleanslice": {
"type": "http",
"url": "https://mcp.cleanslice.org/mcp"
}
}
}
Tip: enforce MCP usage with Copilot instructions
Create .github/copilot-instructions.md in your project root to make Copilot always consult the MCP before writing code:
## CleanSlice MCP — Required
Before writing or modifying any code you MUST consult the CleanSlice MCP:
1. Call `get-started` to load the core architecture rules.
2. Call `list-categories` to see available documentation areas.
3. Call `search` with at least 2 task-relevant queries covering:
(a) core implementation details for the feature you are building,
(b) edge cases, constraints, or standards that apply.
4. Call `read-doc` to read the full document when search snippets aren't enough.
Do NOT guess conventions — always verify against MCP results first.
Add to your claude_desktop_config.json. See Claude Desktop MCP docs for more info.
{
"mcpServers": {
"cleanslice": {
"type": "http",
"url": "https://mcp.cleanslice.org/mcp"
}
}
}
Add this to your Opencode configuration file. See Opencode MCP docs for more info.
{
"mcp": {
"cleanslice": {
"type": "remote",
"url": "https://mcp.cleanslice.org/mcp",
"enabled": true
}
}
}
Tip: enforce MCP usage with AGENTS.md
Create AGENTS.md in your project root to make Opencode always consult the MCP before writing code:
## CleanSlice MCP — Required
Before writing or modifying any code you MUST consult the CleanSlice MCP:
1. Call `get-started` to load the core architecture rules.
2. Call `list-categories` to see available documentation areas.
3. Call `search` with at least 2 task-relevant queries covering:
(a) core implementation details for the feature you are building,
(b) edge cases, constraints, or standards that apply.
4. Call `read-doc` to read the full document when search snippets aren't enough.
Do NOT guess conventions — always verify against MCP results first.
git clone https://github.com/CleanSlice/mcp.git
cd mcp
bun install
bun run dev
Then point your MCP client to http://localhost:8080/mcp.
Available Tools
| Tool | Description |
|---|---|
get-started |
Returns the essential CleanSlice rules and conventions. Call this first. |
list-categories |
Lists all documentation categories available for search filtering |
search |
Search docs by query, category, framework, phase, or tags. Returns snippets (keyword-in-context excerpts) and document paths |
read-doc |
Read the full content of a specific document by path. Use after search to get complete docs |
Recommended workflow
get-started → learn the core rules
list-categories → discover what's available
search(query: "...") → find relevant docs (returns snippets)
read-doc(path: "...") → read full document when snippets aren't enough
The search tool returns 1-3 keyword-in-context snippets per result instead of full document content. This keeps responses compact (~3-5K instead of ~95K) while showing the most relevant sections. Use read-doc with the path from search results to fetch the complete document when needed.
Environment Variables
| Variable | Default | Description |
|---|---|---|
PORT |
8080 |
Server port |
NODE_ENV |
- | Set to dev for debug/verbose logging |
DOCS_PATH |
Auto-discover | Path to bundled docs directory |
GITHUB_REPO |
CleanSlice/docs |
Fallback GitHub repo for docs |
GITHUB_BRANCH |
main |
GitHub branch to fetch from |
GITHUB_TOKEN |
- | GitHub token (optional, for higher rate limits) |
GITHUB_CACHE_TTL |
3600 |
GitHub content cache TTL in seconds |
CORS_ORIGIN |
* |
Allowed CORS origin(s) |
Docker
docker build -t cleanslice-mcp .
docker run -p 8080:8080 cleanslice-mcp
Endpoints
| Endpoint | Description |
|---|---|
GET /sse |
SSE transport (for Claude Desktop, Cursor) |
POST /messages |
SSE message handler |
POST /mcp |
Streamable HTTP transport |
GET /health |
Health check |
GET /api |
Swagger docs |
Architecture documentation synchronization
The four reliability guides in docs/architecture/ are generated from the website repository's docs/architecture/ files (sibling checkout ../docs/docs/architecture). Run node scripts/sync-architecture-docs.mjs after editing the canonical docs and node scripts/sync-architecture-docs.mjs --check before release. For another checkout layout pass --source=/absolute/path/to/architecture. The check fails on missing or divergent copies. Commit the generated bundle with the MCP change so standalone deployments can search/read the same versioned content.
get-started loads 00-quickstart/get-started.md directly, with local-first/remote fallback. If unavailable it fails explicitly rather than returning empty rules. The bundled-knowledge integration tests exercise real loading, searching and rendered startup content. Updating files locally does not update the hosted MCP: build/test, publish the docs and deploy the MCP through the normal authorized release process.
CleanSlice MCP questions
How do I add CleanSlice MCP to Claude Code?
Run claude mcp add --transport http mcp https://mcp.cleanslice.org/mcp in your terminal. Add --scope user to make it available in every project.
How do I add CleanSlice MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does CleanSlice MCP provide?
It exposes 4 tools, including get-started, list-categories, search, read-doc.
What tools does the CleanSlice MCP server provide?
It provides four tools: get-started, list-categories, search, and read-doc, which together let an agent load rules, browse categories, search docs, and read full documents.
What does the search tool return?
It returns 1-3 keyword-in-context snippets per result plus document paths, keeping responses compact; use read-doc for full content.