# PubChem

> Use this tool when you need to access comprehensive chemical data and perform informatics workflows, such as similarity searches, ADMET prediction, and toxicity analysis. It solves problems in drug discovery, chemical research, and regulatory compliance by providing detailed molecular descriptors, 3D conformer data, and safety classifications. With inputs including compound names, SMILES, InChI, and CAS numbers, and outputs of detailed chemical information, it is ideal for chemistry and pharmacology applications.

Canonical page: https://skillsregistry.net/skills/augmented-nature-pubchem  
JSON: https://api.skillsregistry.net/v1/skills/augmented-nature-pubchem

## Description

This MCP server provides comprehensive access to the PubChem chemical database through 30 specialized tools covering compound search, structure analysis, property calculation, bioassay data, safety information, and cross-references to external databases. Built by Augmented Nature using TypeScript and the PubChem REST API, it enables chemical informatics workflows including similarity searches, ADMET prediction, drug-likeness assessment, toxicity analysis, and batch processing of up to 200 compounds. The implementation supports multiple search methods (name, SMILES, InChI, CAS numbers), provides detailed molecular descriptors and 3D conformer data, and integrates safety classifications with literature references, making it valuable for drug discovery, chemical research, regulatory compliance, and educational applications in chemistry and pharmacology.

## Trust

- **Trust score (0–1):** 0.99
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/augmented-nature-pubchem)
- **Repository:** <https://github.com/augmented-nature/pubchem-mcp-server>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "augmented-nature-pubchem"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/augmented-nature-pubchem` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/augmented-nature-pubchem/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt