Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Claude Critical Rules MCP Server verify compliance before deploying to production"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP server providing automatic enforcement of 21 critical rules for Claude AI, based on 96+ documented failure patterns
An MCP (Model Context Protocol) server that makes critical best practices automatically available to Claude AI in every conversation. Based on exhaustive analysis of 96+ real documented failures over 6+ months of intensive production usage.
The system provides 21 numbered rules organized into 5 categories, with automatic verification checklists, rule summaries, and auto-update capabilities.
Related MCP server: focal-mcp
21 Critical Rules - Comprehensive checklist preventing common AI assistant failures
5 Rule Categories - Organized by: Verification, Backups, Execution, Database, Advanced
Pre-flight Verification - Mandatory checklist before technical tasks
Auto-Update System - Check and install rule updates from GitHub automatically
Version Tracking - SHA256 verification and changelog integration
Evidence-based - Every rule derived from real production failures
Add to your claude_desktop_config.json:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json
{
"mcpServers": {
"critical-rules": {
"command": "npx",
"args": ["-y", "@optima-quantum/claude-critical-rules-mcp-new"]
}
}
}npm install -g @optima-quantum/claude-critical-rules-mcp-newThen configure:
{
"mcpServers": {
"critical-rules": {
"command": "claude-critical-rules-mcp"
}
}
}After configuration, restart Claude Desktop to load the MCP server.
Before starting ANY technical task, execute:
critical-rules:verify_compliance
This displays a 21-point checklist organized in 5 categories.
Do NOT proceed until you confirm ALL 21 items.Before creating documents or working with specific technologies:
- Read the appropriate skill file first
- Common location: /mnt/skills/user/sysadmin-professional/SKILL.md
- If skill doesn't exist: search online, verify reliability, propose installationExample Workflow:
User: "Deploy the new API to production"
Claude:
1. Executes: critical-rules:verify_compliance
2. Reviews all 21 rules checklist
3. Reads: /mnt/skills/user/sysadmin-professional/SKILL.md
4. THEN proceeds with deploymentverify_complianceDisplays mandatory 21-rule checklist before technical tasks.
Usage:
critical-rules:verify_compliance
task_description: "Deploy API to production"Returns:
21-point checklist organized by category
Rule numbers and descriptions
Confirmation requirements
Version information
get_rules_summaryQuick reference of all 21 rules with descriptions.
Usage:
critical-rules:get_rules_summaryReturns:
Core principles (5 items)
All 21 rules by category
6-step mandatory workflow
Update instructions
get_version_infoDisplay current version and check for updates.
Usage:
critical-rules:get_version_info
check_remote: true // Optional, default trueReturns:
Current version details
Remote version comparison
Update availability status
SHA256 hash information
check_for_updatesCheck GitHub for new rule versions.
Usage:
critical-rules:check_for_updatesReturns:
Update availability status
Version comparison
Release date
Changelog reference
update_rulesDownload and install latest rules from GitHub.
Usage:
critical-rules:update_rules
force: false // Optional, force reinstallReturns:
Update status
SHA256 verification
Backup location
Next steps
critical-rules://instructionsComplete CRITICAL-RULES.md document with all 21 rules, examples, and detailed explanations.
critical-rules://changelogFull changelog with version history and update details.
Never act without reading instructions completely
Search current best practices (web_search mandatory)
Read skills before creating documents
Read ENTIRE file before modifying
VERIFY, not assume structures/locations
Check correct file/server
Search previous context if mentioned
Backups with timestamp in standardized directories
ASK before deleting/modifying critical items
Ask SCOPE before implementing
STOP if something fails (no cascading)
Validate with EVIDENCE
Complete logs (not just last 20 lines)
Database: backup → test → verify rollback
Production vs Dev differentiation
Security verification (IPs, fail2ban, firewall)
Long commands (>30s) → background execution
NEVER use sed (python/awk/perl instead)
Verify file line count before/after editing
Follow instructions EXACTLY
Check MCPs/skills/context FIRST
Mandatory 21-point confirmation
🔍 VERIFY, DON'T ASSUME - Always check before acting
💾 BACKUP EVERYTHING - Before any modification
🚫 ASK PERMISSION - For deletions and critical changes
📊 EVIDENCE-BASED - Test with proof, not assumptions
🛑 STOP ON ERRORS - Don't continue after failures
Ask scope before starting
Analyze completely
Plan and explain
Create backups
Execute carefully
Validate with evidence
Document changes
Based on comprehensive analysis of:
96+ documented failures in production environments
20+ recurring patterns identified and categorized
6+ months of intensive Claude AI usage
Multiple production systems (servers, databases, APIs, deployments)
SHA256 verification - All downloaded rules verified for integrity
Automatic backups - Previous versions saved before updates
Version tracking - Complete changelog and version history
Manual override - Force parameter for explicit reinstalls
Contributions are welcome! If you've identified additional failure patterns or improvements:
Fork the repository
Create a feature branch
Document the failure pattern with examples
Submit a pull request
MIT License - See LICENSE file for details.
Óptima Quantum Services FZCO
Dubai, UAE
Website: optimaquantum.com
Email: support@optimaquantum.com
GitHub: @optimaquantum
See CHANGELOG.md for version history and updates.
If this MCP server has helped prevent errors in your workflow, please consider starring the repository!
Version: 1.2.0
Last Updated: 2026-01-10
Rules Count: 21 numbered rules
Failure Patterns Analyzed: 96+
Check if a new version of the critical rules is available on GitHub
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description should disclose side effects or network access. It only states the check action, omitting whether it's read-only, safe to call repeatedly, or involves external resources.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence with no wasted words, efficiently conveying the core purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description does not mention the return value (e.g., boolean, version string) or behavior like network fetching, which is critical given the absence of an output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are no parameters, so schema coverage is complete. The description adds no param details, but baseline for 0 params is 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Check') and the specific target ('if a new version of the critical rules is available on GitHub'), making the tool's purpose distinct from siblings like get_version_info or update_rules.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for checking availability before updating, but lacks explicit guidance on when to use this tool vs. alternatives like update_rules or get_version_info.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get a concise summary of the critical rules categories and main requirements
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description does not disclose whether this tool is read-only, requires authentication, or has any side effects. The verb 'Get' implies a read operation, but it's not explicit.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no unnecessary words, efficiently conveying the tool's purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description should explain what is returned; it mentions 'critical rules categories and main requirements' but lacks detail on format, structure, or whether it returns a list or object. Adequate for a simple tool but could be improved.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are no parameters, so schema coverage is 100% by default. The description adds context about the output being a 'concise summary', which is helpful beyond the empty schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves a concise summary of critical rules categories and main requirements, which is distinct from sibling tools like update_rules or verify_compliance.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like check_for_updates or verify_compliance, and no context on prerequisites or typical use cases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get current version information and check if updates are available
| Name | Required | Description | Default |
|---|---|---|---|
| check_remote | No | Whether to check GitHub for latest version (default: true) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description must disclose behavioral traits. It mentions 'check if updates are available', which implies a network call to GitHub, but it does not clarify that this may involve rate limits, latency, or that the tool might fail if offline. No side effects or authentication requirements are noted.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no fluff. Every word is necessary and contributes directly to understanding the tool's purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
There is no output schema, so the description should indicate what the tool returns (e.g., version string, update status). It does not. Also, the sibling check_for_updates exists but is not distinguished. For a simple tool with one optional param, the lack of output description and sibling differentiation makes it incomplete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% because the single parameter check_remote is described in the schema. The description adds no additional meaning beyond the schema; it does not explain the parameter's effect (e.g., setting to false skips remote check). Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get' and the resource 'version information', and adds the action 'check if updates are available'. It distinguishes from siblings like get_rules_summary or update_rules, but does not explicitly differentiate from check_for_updates, which also checks updates.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus the sibling check_for_updates. The description implies a combined operation but does not list alternatives or exclusion criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Download and install the latest version of critical rules from GitHub
| Name | Required | Description | Default |
|---|---|---|---|
| force | No | Force update even if already on latest version (default: false) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must fully convey behavioral traits. It mentions downloading and installing but does not disclose whether the update is destructive, if existing rules are overwritten, or if the operation is safe to repeat. The force parameter hints at idempotency but is not explained in context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with 11 words, very concise with no unnecessary information. It effectively communicates the core action but could be slightly expanded for clarity without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the existence of sibling tools like check_for_updates and verify_compliance, the description does not explain how the update tool fits into the workflow. It also omits any details about return values or side effects, and the tool is simple enough that more context would be helpful.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% for the only parameter (force). The tool description adds no extra meaning beyond what the schema already provides for this parameter. Since the schema already describes it, the baseline is 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states the action (download and install), the resource (latest critical rules), and the source (GitHub). This distinguishes it from sibling tools like check_for_updates or get_rules_summary which check or summarize without updating.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides the core usage scenario but lacks explicit guidance on when to use this tool versus siblings. It does not state prerequisites or conditions for use, such as requiring a network connection or permissions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Verify if all mandatory checks from the critical rules have been completed before starting a technical task
| Name | Required | Description | Default |
|---|---|---|---|
| task_description | Yes | Brief description of the task you are about to start |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It only states the purpose but discloses no behavioral traits (e.g., read-only, side effects, permissions, or return format). Critical details are missing for a complete understanding.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence with 17 words, achieves clarity without redundancy. Information is front-loaded with the verb and core purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has one parameter, no output schema, and no annotations, the description is somewhat complete for a simple verification. However, it lacks details on return value or error conditions, leaving some ambiguity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% for the single parameter 'task_description', which is already well-described in the schema. The tool description adds no additional meaning beyond the schema, so baseline score of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool verifies mandatory checks from critical rules before starting a technical task. It uses a specific verb ('verify') and resource ('compliance of critical rules'). Sibling tools like 'check_for_updates' and 'get_rules_summary' have different purposes, making this distinct.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states when to use: 'before starting a technical task'. Provides clear usage context but does not mention when not to use or list alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tools are mostly distinct: check_for_updates and get_version_info have slight overlap (both check versions) but descriptions clarify differences. The other three tools have unique purposes.
All tool names follow a consistent verb_noun pattern in snake_case (e.g., check_for_updates, get_rules_summary), making them predictable and easy to distinguish.
Five tools is appropriate for a rules management server focused on checking, updating, and verifying compliance. Slightly more could be added (e.g., full rules listing), but the set is well-scoped.
Core operations are covered: checking updates, retrieving summary/version, updating rules, and verifying compliance. Missing a tool to fetch full rule details, but agents can work around with the summary.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Lints + auto-fixes how AI coding agents discover any new product. 24 rules, 6 tools, score 0-100.
Governance copilot for AI-assisted coding. 72 packs, 532 rules, proof bundles.
Deterministic compliance and vertical knowledge bases for autonomous agents. Free 24hr trial.
Pre-execution governance for AI agents. Deterministic PASS/FAIL/REVIEW verdicts, replayable proof.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/optimaquantum/claude-critical-rules-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
