# PubChem MCP for AI Agents AI Agent Connect

> PubChem MCP gives your AI agent direct access to the world's largest open chemistry database. It lets you search over 116 million compounds by name, formula, or CID to pull molecular weights, SMILES strings, and physicochemical properties. It's built for anyone needing accurate chemical data without manual searching.

## Overview
- **Category:** the-unthinkable
- **Price:** Free
- **Endpoint:** https://edge.vinkius.com/vk_preview_bfnYDABzlJ07TJu7Do9K5lCyve4Fg9F5YGb6KetY/ai-agent-connect
- **Tags:** chemistry, molecular-data, drug-discovery, scientific-database

## Description

This Connector connects your agent to the PubChem database, giving you a direct line to over 116 million chemical records. Instead of hunting through search results and copy-pasting formulas into your notes, you can just ask your agent to do the work. It handles the heavy lifting of finding molecular weights, SMILES strings, and physicochemical properties for you.

If you're working on drug discovery or biochemistry research, you know how much time gets wasted on manual data entry. You can tell your agent to look up a compound by its common name, like caffeine, or by a specific formula. It'll pull the data and show it clearly in your workspace. It's one of the most straightforward ways to use the Vinkius catalog to get real-world science data without the usual clicks.

Imagine you're in the middle of a study and need to know the hydrogen bond donor count for a specific lead compound. You can just ask your agent to fetch that number. It does the digging so you can stay focused on your analysis. You can check the solubility of a new molecule or find the SMILES notation of a common drug. This connection makes the process instant. You stop worrying about where the data lives and start focusing on what the data actually means for your research. You get the data you need, exactly when you need it, without the extra steps.

## Tools

### get_pubchem_compound
Get the full chemical profile for a specific compound using its PubChem CID. This is useful for deep dives into specific molecular data.

### search_pubchem_formula
Find all compounds that match a specific molecular formula. This helps you identify chemicals when you only have the formula.

### search_pubchem
Search for chemical compounds by common name. This lets you quickly get basic properties like molecular weight and SMILES strings.

## Prompt Examples

**Prompt:** 
```
What are the molecular properties of aspirin?
```

**Response:** 
```
### Aspirin (CID 2244)
- **Formula**: C9H8O4
- **Molecular Weight**: 180.16
- **SMILES**: `CC(=O)OC1=CC=CC=C1C(O)=O`
- **XLogP**: 1.2
- **H-bond donors**: 1
- **H-bond acceptors**: 4

**Note**: This compound passes Lipinski's Rule of Five and is classified as drug-like.
```

**Prompt:** 
```
Search for compounds with the molecular formula C8H10N4O2.
```

**Response:** 
```
I found the following compounds matching **C8H10N4O2**: 

1. **Caffeine (CID 2519)**
   - *Description*: An alkaloid found in coffee, tea, and chocolate.
   - *MW*: 194.19
   - *SMILES*: `CN1C=NC2=C1C(=O)N(C(=O)N2C)C`

2. **Theophylline (CID 2153)**
   - *Description*: Often used as a bronchodilator for asthma treatment.
```

**Prompt:** 
```
Get the full chemical details for PubChem compound CID 5090.
```

**Response:** 
```
### CID 5090: Metformin
- **Formula**: C4H11N5
- **Molecular Weight**: 129.16
- **SMILES**: `CN(C)C(=N)NC(=N)N`
- **XLogP**: -1.4 (highly water-soluble)
- **H-bond donors**: 3
- **H-bond acceptors**: 3
- **Molecular complexity**: 95

**Usage**: Widely used as a first-line treatment for type 2 diabetes.
```

## Capabilities

### Search compounds by name
Find specific chemicals using common names like aspirin or caffeine to get basic molecular data.

### Lookup compound data by CID
Pull full chemical profiles for any compound using its unique PubChem Compound ID.

### Find compounds by formula
Identify all chemical matches for a specific molecular formula like C9H8O4.

### Extract SMILES and InChI strings
Get the exact chemical notation needed for modeling and database entry.

### Get physicochemical properties
Access data on molecular weight, solubility, and hydrogen bond donors instantly.

### Identify drug-like characteristics
Check if a compound meets specific criteria for drug-like behavior and complexity.

## Use Cases

### Quickly checking drug-like properties
A chemist needs to know if a compound is viable for a drug. They ask their agent to check the properties of a lead compound using `search_pubchem`.

### Matching formulas to chemical names
A student has a molecular formula and needs the name. They ask their agent to find all matching compounds using `search_pubchem_formula`.

### Retrieving SMILES for modeling
A researcher needs the SMILES string for a specific CID. They ask their agent to pull the full data using `get_pubchem_compound`.

### Bulk chemical property lookups
A developer is building a chemistry app and needs to pull properties for common drugs like aspirin and caffeine via `search_pubchem`.

## Benefits

- Stop manual tab-switching by using `search_pubchem` to get SMILES and weights instantly.
- Get precise data on specific compounds using `get_pubchem_compound` for your reports.
- Identify multiple chemicals at once by using `search_pubchem_formula` for research.
- Verify drug-like characteristics like XLogP and hydrogen bond counts without searching.
- Access 116 million records through your agent to speed up your chemistry workflow.

## How It Works

The bottom line is you get instant access to 116 million chemical records without ever leaving your chat window.

1. Subscribe to the PubChem MCP on Vinkius.
2. Connect your preferred client like Claude or Cursor.
3. Ask your agent to find a compound by name or formula.

## Frequently Asked Questions

**Can I use PubChem MCP to find drug-like properties?**
Yes, the Connector lets your agent pull data like XLogP, hydrogen bond counts, and molecular complexity to help you evaluate drug-likeness.

**How do I find a compound if I only know the formula?**
You can ask your agent to search by molecular formula. It will find all matching chemicals in the database and list them for you.

**Can this help with my biochemistry homework?**
Absolutely. You can use it to look up drug structures, molecular weights, and chemical formulas quickly during your studies.

**Does the PubChem MCP require an API key?**
No, this Connector provides a direct connection to the database without requiring you to manage your own API keys.

**What kind of chemical data can my agent pull?**
Your agent can retrieve formulas, weights, SMILES strings, InChI codes, and various physicochemical properties for millions of compounds.

**Is the data in PubChem MCP up to date?**
It connects to the world's largest open chemistry database, which is maintained by the National Center for Biotechnology Information.

**Do I need an API key to use PubChem?**
No. PubChem PUG REST is completely free and open without any authentication. The only limitation is a rate limit of 5 requests per second and 400 requests per minute, which is more than sufficient for conversational AI usage.

**What molecular properties are returned for each compound?**
Each compound includes: CID, IUPAC name, molecular formula, molecular weight, canonical SMILES, InChI identifier, XLogP (lipophilicity), hydrogen bond donor count, hydrogen bond acceptor count, and molecular complexity score. These cover Lipinski's Rule of Five for drug-likeness assessment.

**Can I search by molecular formula instead of name?**
Yes! Use the formula search tool with standard notation (e.g., C8H10N4O2 for caffeine, C9H8O4 for aspirin, H2O for water). PubChem will return all compounds matching that exact formula with their names and properties.