AskChem

Documentation

AskChem is API-first. Every feature available in the web interface is also available via REST API. For AI agent integration, see the Agents tab. For benchmark results, see the Benchmark tab.

Authentication & Rate Limits

Error Codes

Versioning

The stable API lives at /v1/ (mirrors search, claims, views, tree, sources, stats, submit, temporal, evolution, authors, feed). The /api/ prefix is the latest version and may include experimental endpoints. Use /v1/ for production integrations.

Endpoints

Search & Discovery

curl "https://askchem.org/api/search?q=suzuki+coupling&limit=5"

Hierarchy & Browse

curl "https://askchem.org/api/tree/by_reaction_type/Cross-Coupling?depth=2"

Claims & Papers

curl "https://askchem.org/api/sources/10.1038/s41586-024-00001-1"

Authors

Submission & Quality

Schema Examples

Claim Object

{
  "claim_id": "a1b2c3...",
  "claim_type": "experimental_result",
  "title": "Ni SA-N2-C achieves 98% FECO",
  "verbatim_quote": "The Ni SA-N2-C catalyst exhibited...",
  "source_doi": "10.1002/anie.201914977",
  "source_paper_title": "Single-Atom Nickel...",
  "confidence": "high",
  "extraction_model": "gpt-5.4",
  "extraction_version": "deep_v1",
  "view_paths": {
    "by_reaction_type": "Electrocatalysis/CO2 Reduction",
    "by_substance_class": "Inorganic Compounds/Metals/Nickel",
    "by_technique": "Electrochemistry/Linear Sweep Voltammetry"
  }
}

Tree Node Object

{
  "name": "Cross-Coupling",
  "path": "Cross-Coupling",
  "view_id": "by_reaction_type",
  "total_claims": 12450,
  "children": [
    {"name": "Suzuki-Miyaura", "path": "Cross-Coupling/Suzuki-Miyaura", "total_claims": 4230},
    {"name": "Heck", "path": "Cross-Coupling/Heck", "total_claims": 2180}
  ]
}

import requests

# Search for claims
r = requests.get("https://askchem.org/api/search", params={"q": "suzuki coupling", "limit": 10})
claims = r.json()["results"]

# Browse the hierarchy
r = requests.get("https://askchem.org/api/tree/by_reaction_type?depth=2")
tree = r.json()["tree"]

# Submit a new paper
r = requests.post("https://askchem.org/api/submit", json={"doi": "10.1038/..."})
print(r.json()["submission_id"])

Use AskChem with AI Agents

Let your AI coding assistant (Cursor, Claude, Copilot, etc.) use AskChem as a structured chemistry knowledge source. Full endpoint reference in Docs.

Try It Now

Copy this into your terminal and see structured chemistry claims:

curl -s "https://askchem.org/api/search?q=suzuki+coupling&limit=2" | python -m json.tool

{
  "results": [
    {
      "claim_id": "...",
      "claim_type": "experimental_result",
      "title": "Pd-PEPPSI-IPent catalyzes Suzuki coupling of aryl chlorides at room temperature",
      "source_doi": "10.1021/ja...",
      "verbatim_quote": "The Pd-PEPPSI-IPent catalyst system...",
      "view_paths": {"by_reaction_type": "Cross-Coupling/Suzuki-Miyaura", ...}
    }
  ],
  "total": 4230, "query": "suzuki coupling"
}

Cursor / Claude Prompt

Paste this into your agent's chat to integrate AskChem:

Save as AGENTS.md

Put this in your project root so tools that read AGENTS.md pick up AskChem automatically.

MCP Server

Use AskChem in Claude Code, Claude Desktop, or Cursor with just an API key — the standalone client talks to the public API. It requires Python 3.10+ and the MCP Python SDK, with support for both SDK 1.3+ and 2.x. Grab a key from your profile → API Keys.

curl -O https://askchem.org/static/askchem_mcp.py
python -m pip install --upgrade "mcp>=2.3,<3"

Upgrading from MCP 1? Download the current askchem_mcp.py too, then restart your MCP client. Set ASKCHEM_API_KEY in the configuration below to use your key's tier limits.

Download: askchem_mcp.py · tools: search, get_claim, source (by DOI), views, browse, authors, stats.

Claude Code (one command)

claude mcp add askchem --env ASKCHEM_API_KEY=ac-your-key -- python /path/to/askchem_mcp.py

Claude Desktop config (claude_desktop_config.json)

{
  "mcpServers": {
    "askchem": {
      "command": "python",
      "args": ["/path/to/askchem_mcp.py"],
      "env": { "ASKCHEM_API_KEY": "ac-your-key" }
    }
  }
}

Cursor config (.cursor/mcp.json)

{
  "mcpServers": {
    "askchem": {
      "command": "python",
      "args": ["/path/to/askchem_mcp.py"],
      "env": { "ASKCHEM_API_KEY": "ac-your-key" }
    }
  }
}

Self-hosting the full index? Once the source is public you can instead run the in-repo server python -m askchem.mcp_server (requires the local database).

OpenAI Function Calling

Wire AskChem as a tool in your OpenAI function-calling pipeline:

{
  "type": "function",
  "function": {
    "name": "search_chemistry_claims",
    "description": "Search AskChem for source-grounded chemistry claims with verified DOIs",
    "parameters": {
      "type": "object",
      "properties": {
        "query": {"type": "string", "description": "Chemistry search query"},
        "limit": {"type": "integer", "default": 10}
      },
      "required": ["query"]
    }
  }
}