Back to MCP Servers

Chemical Molecular

5 toolsv1.0.0
Overview

About

Chemical molecular intelligence platform covering compound search, structure analysis, physicochemical property retrieval, and molecular interaction profiling.

Capabilities

ls_structure_search

Use this tool when the user wants to search compounds by chemical structure. The Python service only keeps the MCP request parameters and forwards the payload to the downstream chemical endpoint.

Arguments
include_isotopeboolean

bool, whether to include isotope variants in the search

offsetinteger

int, pagination offset, example 0

smiles* Requiredstring

str, query structure in SMILES format, example "CC(=O)OC1=C(C=CC=C1)C(O)=O"

include_chargeboolean

bool, whether to include charge variants in the search

include_multi_componentboolean

bool, whether to include multi-component compounds, valid for EXT type only, example true

limitinteger

int, page size, example 20

include_stereoboolean

bool, whether to include stereoisomers in the search

thresholdnumber

float, similarity threshold required for "SIM", example 0.99

type* Requiredstring

str, search type, supports "EXT" and "SIM"

include_radicalboolean

bool, whether to include radical variants in the search

ls_structure_fetch

Batch fetch full detail records by InChIKey. Maximum 100 identifiers per request.

/api/ls/structure/fetch

ls_patent_structure_fetch

Batch fetch chemical structures associated with a patent by patent ID or patent number. Supports pagination with offset and limit (max 100).

/api/ls/patent/structure/fetch

ls_chemical_mcs_analyze

Analyze fragment composition from multiple chemical structures. Use this tool when the user wants to analyze fragment distribution from a set of SMILES structures. It analyzes the frequent fragments and count how many times each fragment appears across the input structures.

/api/ls/chemical/mcs/analyze

ls_admet_predict

Predict ADMET properties for a list of molecules. Use this tool when the user wants to evaluate drug-likeness or pharmacokinetic properties of small molecules. It calls the ADMET-AI model to predict absorption, distribution, metabolism, excretion, and toxicity properties for each input SMILES.

/api/ls/admet/predict

What is Chemical Molecular MCP Server?

Chemical molecular intelligence platform covering compound search, structure analysis, physicochemical property retrieval, and molecular interaction profiling.

Capabilities

  • Use this tool when the user wants to search compounds by chemical structure. The Python service only keeps the MCP request parameters and forwards the payload to the downstream chemical endpoint.
  • Batch fetch full detail records by InChIKey. Maximum 100 identifiers per request.
  • Batch fetch chemical structures associated with a patent by patent ID or patent number. Supports pagination with offset and limit (max 100).
  • Analyze fragment composition from multiple chemical structures. Use this tool when the user wants to analyze fragment distribution from a set of SMILES structures. It analyzes the frequent fragments and count how many times each fragment appears across the input structures.
  • Predict ADMET properties for a list of molecules. Use this tool when the user wants to evaluate drug-likeness or pharmacokinetic properties of small molecules. It calls the ADMET-AI model to predict absorption, distribution, metabolism, excretion, and toxicity properties for each input SMILES.

How to connect

Get a Patsnap Open Platform API key, copy the MCP connection URL from the Connect panel on this page, and add the server to Cursor, Claude Desktop, or another Model Context Protocol-compatible AI agent client.

Example MCP configuration

{
  "mcpServers": {
    "chemical_molecular": {
      "url": "https://connect.patsnap.com/713886/logic-mcp?apikey={your_api_key}"
    }
  }
}

Use cases

  • Use Chemical Molecular MCP Server to let AI agents access Patsnap innovation intelligence inside agent conversations.

FAQ

What is Chemical Molecular MCP Server?
Chemical Molecular MCP Server is a Patsnap Open Platform Model Context Protocol server that exposes innovation intelligence tools for AI agents and LLM clients.
How does Chemical Molecular MCP Server work with AI agents?
An MCP-compatible client connects to the server URL with your Patsnap Open Platform API key, discovers available tools, and lets the model call Patsnap data and capabilities during conversations.
What tasks can Chemical Molecular MCP Server perform?
Chemical Molecular MCP Server exposes Patsnap tools through the Model Context Protocol so AI agents can retrieve patents, papers, and innovation intelligence during multi-step reasoning.
How do I connect this MCP server to an agent?
Get a Patsnap Open Platform API key, copy the MCP connection URL or JSON config from this page, and add it to your MCP-compatible client following the MCP Quick Start guide.