Skip to content
MCP server

ProvenDecisions optimization solver

MCP server and API that solve LP, MILP and convex models with solver-checked answers

Answers · sign-in required (OAuth)

The server answered 3 hours ago with a sign-in request for OAuth (HTTP 401), so we could not list its tools.

Install
Pricing
Freemium
Platforms
Web, API
Runs
Remotely
Access
Needs sign-in (OAuth)
Version
1.0.1
Listing updated
today

Similar MCP servers

About ProvenDecisions optimization solver

ProvenDecisions optimization solver is a freemium MCP server for analytics and data. It runs as a hosted remote server, so there is nothing to install locally.

The README-free source here is the product's developer page and MCP registry entry, which describe a solver service rather than a chat assistant. You send an optimization model written as typed math or LaTeX and get back the solver status, objective, solution, a check of every constraint, and a dual or KKT certificate with a proof label. A depth setting controls how detailed the step-by-step walkthrough is.

The same tools are exposed over streamable HTTP so Claude and other MCP clients can call the solver and quote its checked numbers instead of estimating them. Access is through a personal API key or a browser sign-in for claude.ai connectors. The site also offers read-only access to its tutorials, glossary and reports.

The service suits developers wiring optimization into their own programs and analysts who want verified answers from an assistant. API and MCP access is included in the Standard and Pro plans, with per-minute, daily and monthly request limits shared with the website.

Install

Run in a terminal

claude mcp add --transport http solver https://proven-decisions.ai/mcp

Add to Settings → Connectors → Add custom connector

https://proven-decisions.ai/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "solver": {
      "url": "https://proven-decisions.ai/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "solver": {
      "type": "http",
      "url": "https://proven-decisions.ai/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "solver": {
      "serverUrl": "https://proven-decisions.ai/mcp"
    }
  }
}

Add to Grok Bot desktop app → Connect apps → Add a custom connector

https://proven-decisions.ai/mcp

Enter a Name (for example "ProvenDecisions optimization solver"), choose Type: Remote HTTPS, paste this as the Server URL and choose Add plugin. When we checked, this server asked for OAuth sign-in. If its docs give you an OAuth client ID and secret, enter them in the form's OAuth Client ID and Client Secret fields.

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "solver": {
      "type": "http",
      "url": "https://proven-decisions.ai/mcp"
    }
  }
}

Using several servers? Build one config file with the MCP config generator.

Tools this server provides (7)

Taken from the project documentation; the running server may differ.

solve
Solve an optimization model and return checked results.
dual
Return the dual of a linear or convex quadratic program.
kkt
Return the KKT certificate at the solution of a smooth model.
explain
Return the solution walkthrough as text at a chosen depth.
search_content
Search the site's tutorials and reference content.
get_content
Fetch one item of the site's content by slug.
list_content
List items of the site's content.

What it does

Checked solver answers
Each result includes a feasibility check, maximum constraint violation and a proof label.
Dual and KKT certificates
Endpoints return dual problems and Lagrange multiplier certificates for smooth models.
Adjustable walkthrough depth
The explanation of a solution can be requested at depths from 1 to 10.
MCP tools for assistants
Solve, dual, kkt and explain tools plus content search are offered over streamable HTTP.
Typed math input
Models are entered as typed math or LaTeX, with integer and binary declarations supported.

Good for

  • Solve a product mix or resource allocation problem from a Python script
  • Have an AI assistant check a linear or integer program before quoting results
  • Obtain dual values and KKT multipliers for a convex quadratic model
  • Verify that a proposed solution satisfies every constraint of a model

Pricing

Freemium, from $50 a month

Free plan for typed math; Standard $50/mo and Pro $100/mo include API and MCP access; 3-day trial on new paid subscriptions.

Prices change. Check proven-decisions.ai before you buy.

ProvenDecisions optimization solver FAQ

Which plans include API and MCP access?

The Standard and Pro plans include API and MCP access; the Free and Student plans do not list it.

How do I connect it to Claude?

You can add the MCP server with the Claude Code command using a browser sign-in or a Bearer key, or add it as a custom connector in claude.ai using Sign in now.

What input formats are accepted through the API?

The API takes typed math and LaTeX; word, photo and voice problems are only solved in the web app.

What are the request limits?

API and MCP requests share plan limits: at most 5 a minute, 100 a day and 1,000 a month, one problem at a time, and 10 minutes of solving a day.

Is ProvenDecisions optimization solver free?

ProvenDecisions optimization solver has a free plan, with paid plans for more usage or features. Paid plans start at $50 a month.

How do I add ProvenDecisions optimization solver to Claude Code?

Run this command in your terminal: claude mcp add --transport http solver https://proven-decisions.ai/mcp

What are the best alternatives to ProvenDecisions optimization solver?

The closest alternatives to ProvenDecisions optimization solver are TradingCalc MCP: Options, Forex, Risk Stats, Prediction Markets, On-Chain & Crypto Futures, Laplace Analytics, optlens and Genius Decision.

Where this comes from

  • Description: written from the project's website and its MCP Registry entry.
  • Status: checked automatically by AIPoweredBot on 19 November 2026.
  • Install steps: from the official MCP Registry entry.

How AIPoweredBot checks servers