Optimization Solver MCP server
Commit Nov 13, 2026Solves production, blending, transportation, and scheduling problems using linear programming and mixed-integer programming.
Also known as Saify-Technologies/saifs-ai-mcps-docs, optimization-solver
- Stars
- 4
- Tools
- 6
- Downloads, 30 days
- —
- Latest version
- 1.0.1
- Last commit
- Nov 13, 2026
- License
- MIT
What is Optimization Solver MCP?
Optimization Solver solves production, blending, transportation, and scheduling problems using linear programming and mixed-integer programming. It exposes 6 tools, such as explain_solution, optimize_blend, optimize_production_mix.
Summary generated from the project's README
About Optimization Solver MCP server
Solving complex production, blending, transportation, and scheduling problems through linear and mixed-integer programming is what this remote server enables. It allows users to define objectives and constraints to receive optimal plans along with shadow prices. The service operates via Streamable HTTP, meaning no local installation is required, though users must complete an OAuth 2.1 PKCE sign-in process through a web page on their first use.
Developers can utilize specialized tools like optimize_blend for least-cost mixing or optimize_schedule for minimizing shift coverage costs. For more complex requirements, solve_custom_lp provides a general solver for power users. The system also includes an explain_solution tool to identify binding constraints and sensitivity. If a problem is mathematically impossible to solve, the server identifies the specific conflicting constraints to help with troubleshooting.
What you can do with it
- 1Optimize manufacturing outputDetermine the most profitable quantities of products to manufacture based on available resources and constraints.
- 2Minimize ingredient costsCreate a least-cost mixture that still meets all required specifications.
- 3Manage workforce shiftsDevelop a low-cost staffing plan that adheres to all organizational rules.
- 4Plan logistics and shippingGenerate a shipping plan that minimizes costs while balancing supply and demand across locations.
- 5Analyze constraint sensitivityUnderstand the cost implications of specific constraints and which ones are currently limiting the solution.
Written from the project's README. Every use case is checked against a quote from it.
How to install Optimization Solver MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Optimization Solver MCP in Claude Code
$ claude mcp add --transport http optimization-solver https://optimization-solver-mcp.saifs.ai/mcpInstall Optimization Solver MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"optimization-solver": {
"url": "https://optimization-solver-mcp.saifs.ai/mcp"
}
}
}Install Optimization Solver MCP in VS Code
.vscode/mcp.json
{
"servers": {
"optimization-solver": {
"type": "http",
"url": "https://optimization-solver-mcp.saifs.ai/mcp"
}
}
}Install Optimization Solver MCP in VS Code CLI
$ code --add-mcp '{"name":"optimization-solver","type":"http","url":"https://optimization-solver-mcp.saifs.ai/mcp"}'Install Optimization Solver MCP in Codex
$ codex mcp add optimization-solver --url https://optimization-solver-mcp.saifs.ai/mcpInstall Optimization Solver MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.optimization-solver] url = "https://optimization-solver-mcp.saifs.ai/mcp"
Install Optimization Solver MCP in Gemini CLI
$ gemini mcp add -s user --transport http optimization-solver https://optimization-solver-mcp.saifs.ai/mcpInstall Optimization Solver MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"optimization-solver": {
"url": "https://optimization-solver-mcp.saifs.ai/mcp",
"type": "http"
}
}
}Optimization Solver MCP tools 6
Detected from the READMEexplain_solutionoptimize_blendoptimize_production_mixoptimize_scheduleoptimize_transportationsolve_custom_lp
| explain_solution | — | |
| optimize_blend | — | |
| optimize_production_mix | — | |
| optimize_schedule | — | |
| optimize_transportation | — | |
| solve_custom_lp | — |
Automated checks
Ran Nov 13, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablesaify-technologies/saifs-ai-mcps-docs is public and reachablegithub.com/saify-technologies/saifs-ai-mcps-docs ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-13github.com/saify-technologies/saifs-ai-mcps-docs ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model6 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeHTTPS endpoint answered 401 (sign-in required)Pass
README
View on GitHubOptimization Solver (LP / MIP Scheduling)
A general constraint-optimization server: describe the objective and constraints, get the optimal plan plus shadow prices. Pre-built templates cover production mix, blending, transportation and shift coverage so callers do not have to write an LP. Infeasible problems return the conflicting constraints.
| Registry name | ai.saifs/optimization-solver |
| Endpoint | https://optimization-solver-mcp-microsoft.saifs.ai/mcp |
| Transport | Streamable HTTP (remote, nothing to install) |
| Auth | OAuth 2.1 — PKCE (S256) and dynamic client registration; your client opens a sign-in page on first use |
| Publisher | SAIFS AI |
Install
VS Code / GitHub Copilot
Add to .vscode/mcp.json (workspace) or your user mcp.json:
{
"servers": {
"saifs-optimization-solver": {
"type": "http",
"url": "https://optimization-solver-mcp-microsoft.saifs.ai/mcp"
}
}
}
Then start the server from the MCP view and sign in when prompted.
Claude (claude.ai, Desktop)
Settings → Connectors → Add custom connector, and paste:
https://optimization-solver-mcp-microsoft.saifs.ai/mcp
Claude Code
claude mcp add --transport http saifs-optimization-solver https://optimization-solver-mcp-microsoft.saifs.ai/mcp
Any other MCP client
Point it at https://optimization-solver-mcp-microsoft.saifs.ai/mcp using the Streamable HTTP transport. The server returns 401 with a
WWW-Authenticate: Bearer … resource_metadata=… challenge, so OAuth-aware clients sign in automatically.
Tools
| Tool | What it does |
|---|---|
explain_solution |
Which constraints bind, shadow prices (what each constraint costs) and sensitivity. |
optimize_blend |
Least-cost mix meeting specs (diet / blending). |
optimize_production_mix |
Optimal quantities and profit given products, resources and constraints. |
optimize_schedule |
Min-cost shift coverage meeting staffing rules. |
optimize_transportation |
Min-cost shipping plan from sources, destinations, supply and demand. |
solve_custom_lp |
General LP solver for power users from an objective and constraints. |
Example prompts
- “Find the best production mix within capacity”
- “Allocate budget across projects”
- “Schedule jobs on machines”
Support
- Website: https://saifs.ai
- Issues: https://github.com/Saify-Technologies/saifs-ai-mcps-docs/issues
- Privacy: https://saifs.ai/privacy_policy
Optimization Solver MCP questions
How do I add Optimization Solver MCP to Claude Code?
Run claude mcp add --transport http optimization-solver https://optimization-solver-mcp.saifs.ai/mcp in your terminal. Add --scope user to make it available in every project.
How do I add Optimization Solver 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 Optimization Solver MCP provide?
It exposes 6 tools, including explain_solution, optimize_blend, optimize_production_mix, optimize_schedule, optimize_transportation.
What kind of problems can this solver handle?
It handles production mix, blending, transportation, shift coverage, and general custom linear programming problems.
What happens if a problem is infeasible?
If a problem cannot be solved due to conflicting constraints, the server returns the specific constraints that are causing the conflict.
Can I get more information about a specific solution?
Yes, you can use the explain_solution tool to see which constraints are binding, view shadow prices, and analyze sensitivity.