ChemGlyph

Publication-quality chemical structure and reaction rendering for AI agents. ChemGlyph is the KaTeX of chemistry: a rendering layer, a validation layer, and an MCP interface on top of RDKit.

Install

pip install chemglyph

Render a molecule

import chemglyph

result = chemglyph.render_molecule("c1ccccc1")  # benzene
open("benzene.svg", "w").write(result.data)

render_molecule takes SMILES, InChI, or molblock and returns SVG (or PNG) plus canonical_smiles, mol_formula, mol_weight, and warnings.

Styles

Three styles, same molecule (benzoic acid, caffeine, (S)-ibuprofen):

chemglyph.render_molecule(smiles, style="acs")  # black/white, ACS journal
chemglyph.render_molecule(smiles, style="modern")  # colored heteroatoms, screens
chemglyph.render_molecule(smiles, style="textbook-cn")  # bold monochrome, textbook

All styles default to a transparent background (transparent=True) and support fmt="png".

Reactions

spec = {
    "steps": [
        {
            "reactants": ["OC(=O)c1ccccc1O", "CC(=O)OC(C)=O"],
            "products": ["CC(=O)Oc1ccccc1C(=O)O", "CC(=O)O"],
            "conditions": {"above": "H₂SO₄ (cat.)", "below": "rt, 15 min"},
            "yield": "89%",
            "arrow": "forward",
        }
    ],
    "style": "modern",
}
svg = chemglyph.render_reaction(spec)

Conditions are pre-formatted Unicode text, so pass H₂SO₄, not H2SO4. ChemGlyph does not parse formulas out of text. The full schema (multi-step chains, equilibrium and retro arrows, line wrapping) is in docs/reaction_schema.md.

The aspirin demo writes a two-step route:

python examples/aspirin_synthesis.py  # writes examples/aspirin_synthesis.svg

Validation

validate_structure reports parse errors and applies four quick fixes: unmatched brackets and ring closures (reported, not guessed), kekulization failures of lowercase aromatic atoms, and nitrogen valence errors via a formal [N+]. Anything else passes RDKit's message through unchanged.

report = chemglyph.validate_structure("c1cccc1")
report.fixes[0].description  # 'lowercase aromatic atoms could not be kekulized...'
report.fixes[0].fixed_smiles  # 'C1CCCC1'

Naming

chemglyph.parse_name("aspirin")  # 'CC(=O)Oc1ccccc1C(=O)O'

English IUPAC and common names resolve offline through OPSIN (pip install 'chemglyph[opsin]', plus a Java runtime). Chinese names use the built-in dictionary, and the library API accepts a translator callable for names that are not in it:

chemglyph.parse_name("阿司匹林")  # 'CC(=O)Oc1ccccc1C(=O)O'
chemglyph.parse_name("六甲基苯", translator=to_english)

ChemGlyph itself never calls an online service, including for translation.

MCP server

Run the bundled console script (stdio transport):

chemglyph-mcp

Claude Desktop registration (macOS: ~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "chemglyph": {
      "command": "chemglyph-mcp"
    }
  }
}

One thing to know about clients. Some MCP clients, LM Studio included, only pass the text part of a tool result to the model and never display the attached image. The render tools write their PNG to ~/Downloads/chemglyph/ and return that path in the text, so you can always open the file yourself. If a model claims it rendered a figure but nothing shows up, ask it for the saved path rather than having it redraw the structure by hand.

Benchmarks

benchmarks/ holds the fixed 20-molecule blind test and a generator that writes shuffled, numbered PNG/SVG figures plus answer_key.json:

python benchmarks/generate_blind_test.py --seed 1234

The deck, methodology, and scoring tooling are all open-sourced: the fixed molecule list, the A/B deck generator (which pairs ChemGlyph against an open-source reference renderer), the runbook, and the scorer live in benchmarks/. Anyone can run the protocol and contribute results. The pass threshold and procedure are documented in benchmarks/RUNBOOK.md.

Blind test vs ChemDraw: pending. The image above is an author-generated comparison of ChemGlyph modern against the open-source reference renderer (Indigo, the engine behind Ketcher) - it is not an independent review.

Known limitations

• Blind-test figures for ferrocene (metal complex) and the free-base porphyrin (large conjugated macrocycle) are excluded from the benchmark denominator and recorded separately.
• RDKit has no clean 2D layout for paclitaxel: its gem-dimethyl substituent placement inside the central 8-membered ring is a documented layout limitation.
• Full automatic Chinese name-to-structure parsing is not implemented; Chinese names resolve through a small built-in dictionary plus an optional translator hook. English names resolve through OPSIN.

Roadmap

Work proceeds in phases, and each phase ships as a minor version once its exit criteria pass. The plan, the standards ChemGlyph follows, and the quality gates are in docs/SPEC.md; release notes are in CHANGELOG.md.

• 0.1.3: fixes and release hygiene.
• 0.2: molecules done right. One fixed physical scale for every drawing, style profiles measured against published standards (ACS Document 1996 settings first), a verification report with every render, automated layout checks, PDF and MOL output.
• 0.3: formulas and equations in mhchem syntax, with atom and charge balance checks.
• 0.4: reaction schemes on the shared scale, with compound numbering.
• 0.5: mechanism (curved) arrows anchored to atoms and bonds.

Non-goals

No structure editor GUI (Ketcher/ChemDraw competition), no 3D visualization, no retrosynthesis or property prediction, no online database queries, and no automatic mechanism generation. The full list is in the project specification.

Development

python -m venv .venv
.venv/bin/pip install -e ".[dev]"
.venv/bin/ruff check . && .venv/bin/ruff format . && .venv/bin/pytest

Python 3.11+, RDKit 2024.9+, MIT license. All errors derive from chemglyph.errors.ChemGlyphError.