Claude
- Open Optimatika Optimisation Service in the Claude directory ↗
- Click Connect
- No sign-in needed: ask away

The Optimatika Optimisation Service solves mathematical optimisation models – linear (LP), quadratic (QP) and mixed-integer (MILP, MIQP) – with deterministic solvers: simplex, interior point, branch and bound.
There is no AI in the solving, so an OPTIMAL result is a proven optimum.
Your AI writes the model as text, in the LP format, and calls solve. The result gives the solution state, the objective value and each variable's value by name. MPS and ojAlgo's EBM format are read too, and translate converts between the three. A model that is not valid LP is an error that names the line, so that it can be corrected. environment reports the limits.
Use it for production planning, scheduling, assignment, blending, knapsack and other allocation problems: anything with a goal to maximise or minimise and constraints that have to hold.
The connector uses Optimatika's public shared instance: free and without an account, for models of up to 1,000 variables or constraints and solves of up to 60 seconds. It is for getting started and tests, not production. Models are held in memory only, and expire within an hour. The same service runs as a container on your own infrastructure, for larger models.
https://service-api.optimatika.se/optimisation/mcphttps://service-api.optimatika.se/optimisation/mcpservice-api.optimatika.seThe AI reads these server instructions before using this connector, every time.
Solves linear, quadratic and mixed-integer optimisation models (LP, QP, MILP, MIQP) with deterministic solvers – simplex, interior point, branch and bound – so an optimal result is a proven one. Write the model in LP format and call solve; the result gives each variable's value by name. Call environment for this server's size and time limits.
environmentsolvetranslateNone in the store listings or on the server
The Optimatika Optimisation Service solves mathematical optimisation models – linear (LP), quadratic (QP) and mixed-integer (MILP, MIQP) – with deterministic solvers: simplex, interior point, branch and bound. There is no AI in the solving, so an OPTIMAL result is a proven optimum. Your AI writes the model as text, in the LP format, and calls solve.
Open its listing in the app's connector directory and connect. No sign-in is needed. Step-by-step setup for each app is on this page.
The Optimatika Optimisation Service MCP server URL is https://service-api.optimatika.se/optimisation/mcp. Paste it as a custom connector in Claude, ChatGPT, Gemini or Grok, or add it to Claude Code, Cursor or any MCP client. Setup steps.
Yes. Optimatika Optimisation Service is published or run by Optimatika, so it is the official MCP server. See other official connectors.
It is listed in 1 store: Claude. Apps where it is not listed can usually still add it as a custom connector.
It has 3 tools: 3 change data. See every tool and its inputs.
It can change data but not delete it. 3 tools can create or update things, for example:
None that we found. None in the store listings or on the server.
No. Its answers come back as text in the chat. Connectors with interactive UI.
This page updates every day. To ask about Optimatika Optimisation Service from Claude, ChatGPT or a coding agent, connect the Agent Ready MCP server: it tracks ranks, tools and new listings across the AI plugin stores.