Computational Materials Science Platform

From Hypothesis
to Atomic Structure

Unified access to scientific literature, materials databases, DFT compute, and an AI research assistant — designed for materials scientists.

Free during preview · No credit card

8.4M+ indexed papers

Scroll to explore

The Problem

From 15 Tabs to One Question

Materials research today means juggling literature databases, property repositories, and simulation tools — hours of context-switching, data trapped in incompatible formats, insights lost between tabs. material.codes connects your entire research stack into a single, AI-powered workflow.

your browser — 15 tabs open
Google Scholar — 23 result tabs
materialsproject.org — search results
OQMD / JARVIS — property query
CIF → POSCAR converter
results_final_v7.xlsx
pseudopotentials forum thread
+9 more tabs
material.codes — research assistant
Loading…

Illustrative · loops automatically

The Platform

Four Modules. One Workflow.

Every tool a materials scientist needs — tightly integrated, so the output of one module feeds directly into the next.

Literature Intelligence

Semantic search over an indexed Semantic Scholar and OpenAlex corpus. Structured data extraction, AI summaries with citations.

"perovskite solar cell efficiency above 25% — last 2 years"

Materials Datasets

One interface to materials property databases. Query by composition, structure, or property; download structures in any format.

"cubic perovskites with bandgap 1.2–1.8 eV, stable at 300K"

Compute Engine

Submit DFT calculations without writing input files. Pseudopotentials, k-point grids, and convergence checks are automatic.

"optimize geometry of mp-2815 with PBE+U, U=3.5 on Fe"

Quantum ESPRESSO

AI Assistant

A domain-aware research assistant orchestrating all four modules from natural language. Keeps context, cites primary sources.

"compare Li-ion cathode candidates for high-temp applications"

Traceable by Design

Every Answer Traceable to Its Source

In R&D, an answer is only as trustworthy as the sources behind it. material.codes keeps the full chain visible — from raw measurement to final recommendation.

Built for teams that need to show where a decision came from — for internal review, IP defensibility, and regulatory scrutiny.

Source Links

Every property value links to its source database and measurement method.

Cited Answers

Every AI answer cites the primary sources it drew from.

Audit Trail

Exportable audit trail for compliance review.

Anchor Workflow

Battery Cathode Screening

The workflow we lead with: Li-ion cathode candidates from first-principles data, cross-referenced against literature, ranked, and validated with DFT — in one place.

"Find Li-ion cathode candidates with average voltage 3.5–4.3 V and energy above hull below 50 meV/atom"
  • Queries connected materials databases by voltage window and thermodynamic stability
  • Cross-references discharge capacities reported in the literature
  • Ranks candidates — thermodynamic stability first, then capacity and voltage fit
  • Runs DFT geometry relaxation on the shortlist

Top Result

LiNi0.8Mn0.1Co0.1O2 (NMC811)

V̄ = 3.86V 199 mAh/g

Pipeline Steps

Literature search
Materials DB query
DFT relaxation (queued)

Illustrative

Semiconductor Band Engineering

Same engine, different recipe: property filters, literature cross-reference, DFT validation — tuned for target band gaps.

"InGaN alloys with direct bandgap between 2.6 and 3.0 eV, lattice-matched to GaN"

Catalyst Surface Analysis

On the roadmap

Surface slabs, adsorption energies, and NEB reaction barriers will need a new class of compute — planned, not yet live.

Model Context Protocol

Plug Materials Data Into Your Own AI Stack

material.codes speaks MCP. Connect literature search, materials database queries, and DFT submission to Claude, Cursor, or any MCP-compatible client — from inside your team's own AI workflows.

mcp.json
{
  "mcpServers": {
    "material-codes": {
      "url": "https://material.codes/mcp",
      "headers": { "Authorization": "Bearer <your API key>" }
    }
  }
}

API keys are self-managed in the Lab once you have access.

Plans & Access

Choose your plan

Every plan unlocks the full platform. Higher plans lift monthly limits and quality.

Free · Available now

Explorer

Try every module

Free track
30 requests · 15m DFT / mo
Join the waitlist
Coming soon

Researcher

For active research

Academic & Industry
200 requests · 30m DFT / mo
Reranked results, deeper search
Join the waitlist
Coming soon

Computational

DFT & agentic workflows

Academic & Industry
1 000 requests · 2.5h DFT / mo
Agentic automation, priority compute
Join the waitlist
Coming soon

Principal

Lead a research program

All tracks, institutional
Unlimited requests & DFT / mo
Full orchestration, custom sources
Join the waitlist

Explorer is free and available now. Researcher, Computational, and Principal are coming soon. Academic pricing will be available for verified researchers.

Free Preview · Early Access

Get Free Access

Be among the first to use material.codes. Free while in preview.

No spam. We'll only reach out when your access is ready.

You're on the list!

We'll notify you at when your access is ready.

Already on the list!

is already waitlisted. We'll reach out when your access is ready.