Documentation | NovoMCP

Documentation

Everything you need to connect Claude to molecular intelligence.

Quick Start

NovoMCP is a remote MCP server that works on all Claude platforms: web, desktop, mobile, and API.

Claude.ai (Web) or Mobile — Easiest

  1. Go to Settings > Connectors
  2. Click "Add custom connector"
  3. Enter URL: https://novomcp.com/mcp/sse
  4. Add header: X-API-Key = your API key

Claude Desktop

Add to your config file:

{ "mcpServers": { "novomcp": { "url": "https://novomcp.com/mcp/sse", "headers": { "X-API-Key": "your-api-key" } } } }

Config file locations:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json

Restart Claude Desktop after saving.

Platform support: Claude.ai web (Pro/Max/Team/Enterprise), Claude Desktop (all plans), Claude Mobile iOS/Android (Pro/Max/Team/Enterprise), Claude API, plus ChatGPT, Gemini, and Microsoft Copilot (all support MCP).

Authentication

All requests require an API key passed in the X-API-Key header. Keys are tied to an organization and determine your access tier.

Getting a Key

Request access via email. Keys are provisioned within 24 hours. Each key includes:

  • Organization ID and name
  • Access tier (Free, Pro, Team, or Enterprise)
  • Daily query limit based on tier

Key Format

Keys follow the format nmcp_[random]. Store securely—keys cannot be retrieved after creation.

Rate limits: Requests are rate-limited per organization. Free tier: 100/day. Pro: 1,000/day. Team: 10,000/day. Enterprise: unlimited.

Tool Reference

NovoMCP exposes tools via the Model Context Protocol. Claude can invoke these directly.

get_molecule_profile
Retrieve comprehensive molecular profile including properties, ADMET predictions, and regulatory compliance status.
Parameters: identifier (SMILES, CID, or name) | Tier: Free
get_molecule_info
Basic molecular properties via RDKit: molecular weight, LogP, TPSA, hydrogen bond donors/acceptors, rotatable bonds.
Parameters: smiles | Tier: Free
search_similar
Find structurally similar molecules using Tanimoto similarity. Returns top matches with similarity scores.
Parameters: smiles, threshold (0.0-1.0), limit | Tier: Pro
filter_molecules
Filter database by property ranges. Supports molecular weight, LogP, QED, TPSA. Exclude controlled substances.
Parameters: filters (object), limit | Tier: Pro
batch_profile
Profile multiple molecules in a single request. Up to 100 compounds per call.
Parameters: identifiers (array) | Tier: Pro
optimize_molecule
Generate optimized molecular variants using NVIDIA MolMIM. Target specific properties. All outputs screened for compliance.
Parameters: smiles, target_qed, target_logp, num_variants | Tier: Team
predict_structure
Predict 3D protein structure from amino acid sequence via OpenFold3. Async—returns job ID.
Parameters: sequence, name | Tier: Team
check_compliance
Full FAVES regulatory assessment with context-aware evaluation for intended use case.
Parameters: smiles, context | Tier: Enterprise

Example

Ask Claude a question that triggers tool use:

"What's the ADMET profile of ibuprofen? Is it hepatotoxic?"

Claude invokes get_molecule_profile with identifier "ibuprofen" and receives:

Response
{ "properties": { "cid": 3672, "smiles": "CC(C)CC1=CC=C(C=C1)C(C)C(=O)O", "molecular_weight": 206.28, "logp": 3.97, "tpsa": 37.3, "qed": 0.72 }, "admet": { "hepatotoxicity_probability": 0.12, "cardiotoxicity_probability": 0.08, "bbb_permeant": true, "cyp2d6_inhibitor": false, "human_intestinal_absorption": 0.98 }, "compliance": { "status": "clear", "is_dea_controlled": false, "is_fda_banned": false, "structural_alerts": [] } }

Claude synthesizes this into a natural response about ibuprofen's safety profile, noting the low hepatotoxicity risk (12% probability) and clear regulatory status.

Novel molecules: If a compound isn't in our database, NovoMCP computes properties on-the-fly using RDKit and runs FAVES screening. Response times may be slightly longer (~500ms vs ~50ms).