First Principles Prover Connector for AI agents.
1 live capability
Derive original engineering and business solutions from raw logical axioms.
Waiting for input…
Why people use First Principles Prover
First Principles Prover for High-Stakes Engineering Logic
This Connector changes the conversation by forcing your AI client to stop looking at what others did. It locks the agent into a 6-pivot validation process that strips away the noise. Instead of a generic recommendation, you get a derivation based on the physics and math of your specific problem, giving you a solution that actually works for your unique setup.
What Vinkius changes
You get a derivation based on facts rather than a copy of someone else's homework.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Scaling a global database
An engineer realizes 'use a microservice' doesn't solve the latency.
- Real-world use case 02
New product strategy
A consultant wants to avoid 'best practices.
- Real-world use case 03
Complex hardware design
A designer uses the capability to verify that a component's physical limits aren't being violated by a standard manufacturing assumption.
Complete set · 1capability
The complete First Principles Prover capability set.
These are the exact actions your AI can choose when you ask it to work with First Principles Prover.
01
1 capability in this set.
Part of 1 available through First Principles Prover.
- 01 Capability
Validate first principles
Forces the agent to discard analogies, isolate truths, and build a solution from axioms while purging jargon.
Set up in minutes
One URL. Then ask First Principles Prover to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use First Principles Prover from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_pp4uUsix9xan1UJeLTzZUUEkcW2z3K8yJ3NYaBFy/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it First Principles Prover, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable First Principles Prover for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_pp4uUsix9xan1UJeLTzZUUEkcW2z3K8yJ3NYaBFy/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the First Principles Prover URL.
- Step 03
Save and start
Save the connection and enable First Principles Prover in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"first-principles-prover": {
"url": "https://edge.vinkius.com/vk_preview_pp4uUsix9xan1UJeLTzZUUEkcW2z3K8yJ3NYaBFy/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using First Principles Prover
Open Agent mode in chat and ask: "Using First Principles Prover, help me...". 1 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"first-principles-prover": {
"url": "https://edge.vinkius.com/vk_preview_pp4uUsix9xan1UJeLTzZUUEkcW2z3K8yJ3NYaBFy/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using First Principles Prover
Ask Copilot: "Using First Principles Prover, help me...". 1 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"first-principles-prover": {
"url": "https://edge.vinkius.com/vk_preview_pp4uUsix9xan1UJeLTzZUUEkcW2z3K8yJ3NYaBFy/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using First Principles Prover
Open Cascade and ask: "Using First Principles Prover, help me...". 1 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"first-principles-prover": {
"url": "https://edge.vinkius.com/vk_preview_pp4uUsix9xan1UJeLTzZUUEkcW2z3K8yJ3NYaBFy/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using First Principles Prover
Ask Cline: "Using First Principles Prover, help me...". 1 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add first-principles-prover --transport http "https://edge.vinkius.com/vk_preview_pp4uUsix9xan1UJeLTzZUUEkcW2z3K8yJ3NYaBFy/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using First Principles Prover
Ask Claude: "Using First Principles Prover, show me...". 1 tools are ready
Where the request belongs
Work First Principles Prover can move forward.
This is for high-level technical leads and strategists who need to move beyond 'standard' solutions to solve unique, high-stakes problems.
Systems Architect
Uses this to verify that a new architecture actually meets scale requirements rather than just following a generic template.
Strategic Consultant
Uses this to identify non-obvious competitive advantages by stripping away market conventions.
Research Scientist
Uses this to ensure logical proofs hold up under extreme scrutiny and are grounded in raw axioms.
Software Engineer
Uses this to debug complex system bottlenecks where standard 'best practice' solutions have already failed.
When one Connector is not enough
Carry the request into a workflow.
Combine First Principles Prover with the systems that finish the task.
View all recipesBuild the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse Connectors
Systems Thinking Prover
AI thinks in straight lines. This engine is a 6-pivot cognitive trap that forces the LLM to map feedback loops, second-order effects, and bottlenecks before proposing any architectural change.
Critical Thinking Prover
AI agents accept premises without questioning, analyze from one perspective, cherry-pick evidence, ignore consequences, and present uncertainty as certainty. This capability forces rigor: surface assumptions, apply competing frameworks, weigh counterevidence, trace ripple effects, bound confidence.
Deep Analyst Prover
AI gives surface analysis. restates the question, misses hidden assumptions, uses single-lens thinking. This capability forces multi-model depth: First Principles decomposition, Second-Order cascades (3 levels), Steelmanning (Ideological Turing Test), Inversion, and Premortem risk mapping.
Inversion Thinking Prover
AI agents are sycophantic. They agree with your bad ideas. This engine forces a 6-pivot cognitive trap: agents must destroy their own hypotheses, define measurable kill criteria, and simulate post-mortem failures before executing code.
DeepSeek
Access powerful open-weight language models for reasoning, code generation, and complex problem solving at competitive cost.
Einstellung-Challenger Prover
AI models default to complex, familiar heuristics even when simpler solutions exist. This capability breaks suboptimal cognitive sets: identify default heuristics, search for counterexamples, map alternative paths, benchmark complexity metrics, and choose the most elegant solution.
Bring your own AI
Change the model, client or framework. Keep First Principles Prover connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about First Principles Prover.
The practical details behind the request, access and result.
What is the First Principles Prover MCP for?
It is a reasoning capability that forces your AI agent to solve problems using basic facts and logic rather than just copying common industry trends.
Can First Principles Prover help with engineering problems?
Yes, it's excellent for engineering. It forces the AI to consider the physical and mathematical limits of a system to find a unique solution.
Does First Principles Prover remove AI buzzwords?
Yes, it specifically purges jargon like 'leverage' and 'synergy' to ensure the AI provides clear, information-dense answers.
How does First Principles Prover differ from standard AI reasoning?
Standard AI often reasons by analogy (copying what others do). This Connector forces the agent to reason from axioms (starting from the ground up).
What industry is First Principles Prover best for?
It's best for high-stakes fields like systems architecture, strategic consulting, research science, and complex product design.
Will First Principles Prover give me 'best practices'?
No, it actually tries to discard 'best practices' if they don't fit your specific constraints, providing a custom derivation instead.
Can First Principles Prover help me find flaws in my assumptions?
Yes, it includes a step to deconstruct assumptions, helping you identify which parts of your plan are facts and which are just conventions.
Why does the logic engine scan for buzzwords?
Because words like 'leverage', 'synergy', or 'best practices' are proof of analogical thinking. The semantic trap prevents the AI from faking deep thought.
What qualifies as a fundamental truth?
Physics (like the speed of light or CPU thermal limits), mathematical laws (like Big O complexity), or hard engineering constraints (like network bandwidth limits). Opinions and conventions do not count.
Why must the solution be built from scratch?
To ensure you aren't just importing a library or framework that carries hidden architectural assumptions. Deriving solutions from axioms guarantees a clean, unbloated design optimized for the exact problem.
One connection away
Give your agent a direct line to First Principles Prover.
Connect First Principles Prover once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available