SAGE — Solver-Augmented Grounding Engine

io.github.pragnakarPublished by GitHub account pragnakarv0.1.1Updated Oct 24, 2026

LLM-native optimization solver: LP, MIP, portfolio & scheduling via HiGHS/OR-Tools.

VerifiedSTDIODesktop onlyDeveloper ToolsData & Analytics

Overview

AI-generated overview

A local MCP server that lets an assistant formulate and solve optimization problems such as linear programs, mixed-integer programs, portfolios, and schedules.

What you can do
SAGE (Solver-Augmented Generation Engine) exposes optimization tools to MCP-compatible clients such as Claude Desktop. According to the description, it covers linear programming, mixed-integer programming, portfolio and scheduling problems, solved with the open-source HiGHS and OR-Tools solvers. It runs as a local process and reads or writes files only at paths the user explicitly provides.
When to use it
Worth adding when an assistant needs to solve quantitative optimization problems rather than just describe them, for example resource allocation, scheduling, or portfolio construction. It suits users who want the solving to happen on their own machine.
Requirements
A local runtime: it is a PyPI package (sage-solver-mcp) run over stdio, for example with uvx, and it is desktop-only. No authentication, environment variables, or headers are declared, and no network access is described.
Before you install
The README states that all computation runs locally, that no data, file contents, or models are transmitted or stored externally, and that no analytics, telemetry, or network requests are made. Files are read or written only at paths you explicitly provide, so review those paths before use.

Installation

In SourceWeft

  1. Open SAGE — Solver-Augmented Grounding Engine in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

sage-solver-mcp

mcp-name: io.github.pragnakar/sage-solver-mcp

Local MCP server for SAGE (Solver-Augmented Generation Engine).

Exposes optimization tools to Claude Desktop and other MCP-compatible LLM clients.

See the monorepo root for full documentation and installation instructions.

Privacy Policy

SAGE operates entirely on your local machine. It does not collect, transmit, or store any user data, file contents, or optimization models externally. All computation runs locally using open-source solvers (HiGHS, OR-Tools). No analytics, telemetry, or network requests are made. Files are only read from or written to paths you explicitly provide.

Source: sage-solver-mcp/README.md at commit 5941251

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.1LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts