mcpField
C
CovaSyn Chemistry Tools

CovaSyn Chemistry Tools

VerifiedFeaturedRemote
covasyn.comData & Analytics0Updated 2w ago

About CovaSyn Chemistry Tools

CovaSyn provides verified chemistry and analytics evaluations for pharma, biotech, and chemical labs, with methods and limitations stated for expert review. This repository contains configuration examples and minimal MCP clients for connecting AI assistants to the commercial service.

Key features

  1. 01Evaluate chemistry and analytical questions
  2. 02Assess impurities under ICH M7
  3. 03Analyze spectra and stability
  4. 04Support analytical method development
  5. 05Provide connection examples for MCP clients

Use cases

  1. 01Connect Claude Desktop or Cursor to CovaSyn
  2. 02Run a custom Python or TypeScript MCP client
  3. 03Review chemistry evaluations with stated methods and limits

MCP support

CovaSyn offers chemistry and analytics capabilities to MCP clients. This repository provides setup snippets for clients including Claude Desktop, Cursor, VS Code, Python, and TypeScript.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://mcp.covasyn.com/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

CovaSyn MCP Examples

Configuration snippets for connecting CovaSyn to common Model Context Protocol clients.

CovaSyn delivers verified chemistry and analytics evaluations for pharma, biotech and chemical labs: impurity assessment under ICH M7, stability under ICH Q1, spectra interpretation, method development and more. Every result comes with its method and limits stated, so your experts can check and sign it off.

Benchmark headline

On the MolecularIQ benchmark (Klambauer Lab, JKU Linz, 3,540 symbolically verified chemistry tasks), results were 14 to 41 % correct without CovaSyn and 76 to 92 % with CovaSyn. Methodology: covasyn.com/en/benchmark.

What's in here

ExampleClientDescription
claude-desktop/Claude Desktopclaude_desktop_config.json snippet
cursor/Cursor IDE.cursor/mcp.json snippet
vscode/VS Code with MCP extensionsettings.json snippet
python-agent/Custom Python agentminimal stdio MCP client
typescript-agent/Custom TypeScript agentminimal MCP TS client
curl/Direct HTTPshell snippets for connecting

Getting access

Create an account at workspace.covasyn.com and generate a key under API keys. Plans and terms are shown in the workspace.

If you would rather receive the finished evaluation than run it yourself, or need it inside your own infrastructure, maintained by CovaSyn: book an introductory call.

Compliance posture

Designed for GxP environments (EU Annex 11, 21 CFR Part 11), with audit trail and EU data residency. Details: covasyn.com/en/trust.

License

The example snippets in this repository are released under the MIT License.

CovaSyn itself is commercial software and is operated and maintained by CovaSyn GmbH. See covasyn.com for terms.

Questions

[email protected]

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.