Security, Science & HardwareDone with custom-built or unnamed agent Sep 7, 2026
Give agents a multi-engine math kernel via MCP
MathKernel is an evidence-aware multi-engine mathematics kernel exposed as an MCP server for agents to use.
- What They Did
- MathKernel runs as an MCP server (mathkernel-mcp, stdio, 162 math_ tools). The model parses and plans, and the kernel does the computing across SymPy, Z3, Lean, mpmath and numba/CUDA. A typical session discovers capabilities, parses an expression, creates a context, then calls math_reason to solve and verify. Long sweeps go through async jobs. Every result carries a trust label and a derivation trail.
- How It Went
- The source gives no benchmark or outcome numbers. It documents the design: trust is capped at the weakest evidence, and decimal inputs drop a result to numeric, which blocks Lean and SMT proofs.
- Worth Knowing
- Lean 4 and Mathlib install on first server start unless MATHKERNEL_SKIP_LEAN_INSTALL=1 is set. CUDA needs the extra nvidia pip packages, otherwise it falls back to CPU.
Try it yourself with custom-built or unnamed agent
Connect the MCP server for [math tool, e.g. MathKernel or a computer algebra system] to this project, then use it to solve [math problem or set of equations] and show the result along with which engine produced it and how it was verified. If engines disagree, flag it and explain. Done means I get the answer, the evidence for it, and a note on any assumptions you made.