Skip to content

ChemDataDoctor MCP

Open-source MCP server for local chemical data cleaning, CAS format and checksum validation, duplicate detection, and dataset quality checks through AI assistants.

Catalog updated ·

Overview

ChemDataDoctor MCP is an independent TypeScript server that exposes local chemical table checks over MCP stdio. It is a separate product entry from the ChemDataDoctor web application. Source package and server metadata identify version 0.1.0; the repository has no GitHub releases or tags at the time of review. Installation from source is documented; an npm registry release has not been verified.

It reads CSV, TSV, XLS, XLSX and JSON files, or small inline row arrays. JSON supports arrays of row arrays or flat objects; nested objects and arrays are rejected. A CAS column mapping is required; name and formula columns are optional. Cleaning writes new JSON reports and cleaned CSV/XLSX copies while preserving the source and retaining duplicate rows.

The server needs no account or API key and has no hosted-service dependency at runtime. Installation downloads dependencies, including SheetJS from its official CDN. The source contains no outbound requests or telemetry. MCP clients decide which tool inputs and outputs reach their model provider; local server execution alone does not guarantee an offline assistant. Dataset calls return counts by default; optional samples contain metadata, while local artifacts contain user data.

CAS validation checks format and checksum, not registration or substance identity. Name cleanup changes whitespace and invisible characters only, without synonym resolution or systematic naming. Formula checks cover a restricted grammar and do not establish chemical plausibility or correspondence between CAS, names and formulas. Charges, explicit isotopes and polymer notation are unverifiable. Duplicate detection does not merge identities or remove rows, and does not carry state across calls.

Files are bounded to 20 MiB, 50,000 data rows, 200 columns, 2,000,000 cells across sheets and 100 sheets. Inline input has at most 201 rows including an optional header. Processing reads bounded input into memory. The configured data root is an application path safeguard, not an operating-system sandbox. First-party code is MIT licensed; dependencies retain their own licenses.

Key Features

  • validate_cas: CAS format and checksum checks with optional conservative formatting fixes.
  • normalize_names: whitespace and invisible-character cleanup while preserving case and chemical notation.
  • validate_formulas: restricted formula grammar checks and atom counts.
  • detect_duplicates: repeated CAS/text detection with indexes; records remain intact.
  • clean_dataset: new local cleaned copies and reports; quality_report: inspection without file writes.

Use Cases

  • Check chemical inventory spreadsheets before import.
  • Inspect compound table quality through an MCP client.
  • Prepare local cleaned copies with traceable original values.

How to Use

Requires Node.js 22.12+ and npm. Replace the example data path with an existing dedicated directory. Configure the MCP client to launch node with the absolute path to dist/cli.js and --data-root; the process waits for stdio requests.

git clone https://github.com/chemaiatlas/chemdatadoctor-mcp.git
cd chemdatadoctor-mcp
npm ci --ignore-scripts
npm run build
node dist/cli.js --data-root /absolute/path/to/data

Call quality_report with this input first. To write cleaned copies, call clean_dataset; set applyFixes=true to enable conservative fixes. The default output directory is .chemdatadoctor-output under the data root.

{"path":"inventory.xlsx","sheetIndex":0,"columns":{"cas":0,"name":1,"formula":2}}

GitHub · ChemDataDoctor Web · README · MIT

Sources and verification

This entry describes capabilities documented by the linked project sources. Catalog edits are not evidence of a successful run, compatibility test or scientific performance evaluation.

Read the editorial and verification policy

Related resources

InChI

Open Source

InChI is the official repository of the IUPAC International Chemical Identifier project, providing source and releases of software that generates InChI and InChIKey strings, under the MIT license.

Open source

Cheminformatics · Scientific Data

OpenAI4S is an MIT-licensed scientific research agent combining JSON tool orchestration with persistent Python/R analysis and documented chemistry data connectors.

Open sourcePython

Cheminformatics · Literature & Research · Scientific Data

PubChem MCP (cyanheads) connects MCP clients to PubChem compound and bioassay data, with identifier and structure searches, property retrieval, safety records, cross-references and 3D conformers.

Open sourceTypeScript

Cheminformatics · Scientific Data

PubChem MCP (PhelanShao) is a Python MCP server that lets AI clients retrieve PubChem compound properties and structures by name or CID, with JSON, CSV, XYZ and downloadable structure-file outputs.

Open sourcePython

Cheminformatics · Scientific Data

PubChem PUG REST is an HTTP API for retrieving selected chemical records, properties and assay information, with documented identifier inputs, structure searches and operation-specific output formats.

Cheminformatics · Scientific Data

PubChemPy

Open Source

PubChemPy is a Python wrapper for the PubChem PUG REST API, supporting chemical searches, compound-property retrieval, standardization, file-format conversion and depiction.

Open sourcePython

Cheminformatics · Scientific Data

Related guides

Overview

MCP vs Skills vs Agents vs APIs: What's the Difference?

Understand how APIs, MCP servers, Skills, and agents divide interface, procedural guidance, execution, and planning responsibilities in chemistry workflows—and how to choose or combine them without confusing access with scientific validity.

Workflows

Building an AI Cheminformatics Workflow with RDKit

Design a traceable RDKit workflow for molecular validation, standardization, descriptors, fingerprints and chemical searches. Compare Python, MCP and Skill access, then add bounded PubChem enrichment without confusing tool execution with scientific validation.