Agent skill

Molecular Similarity Search

by InternScience in InternScience/scp

Search for similar molecules using Tanimoto similarity with Morgan fingerprints to identify structurally related compounds.

MITAuto-check passedDatabases

Install Molecular Similarity Search

skills CLI
$ npx skills add InternScience/scp --skill molecular-similarity-search -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install InternScience/scp molecular-similarity-search --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/InternScience/scp.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/molecular-similarity-search .claude/skills/molecular-similarity-search && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
molecular-similarity-search
GitHub stars
170
Used in
1 other repo
Token cost
~1.4k tokens
SKILL.md length
237 words
Files
1
Skills in repo
73
Repo updated
First seen
Licence
MIT

At a glance

Search for similar molecules using Tanimoto similarity with Morgan fingerprints to identify structurally related compounds.

  • Works in 2 steps: MCP Server Definition → Molecular Similarity Search Workflow
  • Tasks that involve Vector databases
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Tasks that involve Drug discovery and cheminformatics

What it does

Molecular Similarity Search is an agent skill from InternScience/scp. Search for similar molecules using Tanimoto similarity with Morgan fingerprints to identify structurally related compounds.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Databases, covering Vector databases and Drug discovery and cheminformatics. The licence is MIT.

When your agent uses it

  • Tasks that involve Vector databases
  • Tasks that involve Drug discovery and cheminformatics

Example prompts

  • “/molecular-similarity-search”

Requirements

  • Python 3

Workflow steps

2 steps, taken from the step headings in SKILL.md.

  1. MCP Server Definition
  2. Molecular Similarity Search Workflow

What it can do on your machine

Read from SKILL.md and the folder at commit cea5398. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are python).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Molecular Similarity Search loads about 1.4k tokens when it runs. Until then it costs about 38 tokens; SKILL.md has 237 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~38
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from InternScience/scp at commit cea5398, republished under its MIT licence (© InternScience). 237 words, ~1,388 tokens.

Download SKILL.mdSave it as .claude/skills/molecular-similarity-search/SKILL.md (or your agent's skills folder).
name
molecular-similarity-search
description
Search for similar molecules using Tanimoto similarity with Morgan fingerprints to identify structurally related compounds.
license
MIT license
metadata.skill-author
PJLab

Usage

1. MCP Server Definition
python
import asyncio
import json
from mcp.client.streamable_http import streamablehttp_client
from mcp import ClientSession

class DrugSDAClient:
    """DrugSDA-Tool MCP Client"""

    def __init__(self, server_url: str, api_key: str):
        self.server_url = server_url
        self.api_key = api_key
        self.session = None

    async def connect(self):
        """Establish connection and initialize session"""
        print(f"server url: {self.server_url}")
        try:
            self.transport = streamablehttp_client(
                url=self.server_url,
                headers={"SCP-HUB-API-KEY": self.api_key}
            )
            self.read, self.write, self.get_session_id = await self.transport.__aenter__()

            self.session_ctx = ClientSession(self.read, self.write)
            self.session = await self.session_ctx.__aenter__()

            await self.session.initialize()
            session_id = self.get_session_id()

            print(f"✓ connect success")
            return True

        except Exception as e:
            print(f"✗ connect failure: {e}")
            return False

    async def disconnect(self):
        """Disconnect from server"""
        try:
            if self.session:
                await self.session_ctx.__aexit__(None, None, None)
            if hasattr(self, 'transport'):
                await self.transport.__aexit__(None, None, None)
            print("✓ already disconnect")
        except Exception as e:
            print(f"✗ disconnect error: {e}")

    def parse_result(self, result):
        """Parse MCP tool call result"""
        try:
            if hasattr(result, 'content') and result.content:
                content = result.content[0]
                if hasattr(content, 'text'):
                    return json.loads(content.text)
            return str(result)
        except Exception as e:
            return {"error": f"parse error: {e}", "raw": str(result)}
2. Molecular Similarity Search Workflow

This workflow searches for similar molecules using Tanimoto similarity calculated from Morgan fingerprints.

Workflow Steps:

  1. Define Target Molecule - Specify the query SMILES
  2. Define Candidate Molecules - Provide list of candidate SMILES
  3. Calculate Similarity - Compute Tanimoto scores for all candidates
  4. Rank Results - Sort by similarity score to find most similar molecules

Implementation:

python
## Initialize client
client = DrugSDAClient(
    "https://scp.intern-ai.org.cn/api/v1/mcp/2/DrugSDA-Tool",
    "<your-api-key>"
)

if not await client.connect():
    print("connection failed")
    exit()

## Input: Target molecule and candidate library
target = "CCO"  # Ethanol
candidates = [
    "CCCO",      # Propanol
    "CCCCO",     # Butanol
    "CC(C)O",    # Isopropanol
    "CCC(C)O",   # sec-Butanol
    "C1CC1",     # Cyclopropane
    "CC=O",      # Acetaldehyde
    "CCCOO"      # Propanoic acid
]

## Execute similarity calculation
result = await client.session.call_tool(
    "calculate_smiles_similarity",
    arguments={
        "target_smiles": target,
        "candidate_smiles_list": candidates
    }
)

result_data = client.parse_result(result)
similarities = result_data['similarities']

## Sort and display top 3 most similar molecules
top3_smiles = sorted(similarities, key=lambda x: x['score'], reverse=True)[:3]

print(f"Target molecule: {target}\n")
print("Top 3 most similar molecules:")
for i, item in enumerate(top3_smiles, 1):
    print(f"{i}. {item['smiles']} - Tanimoto score: {item['score']:.4f}")

await client.disconnect()
Tool Descriptions

DrugSDA-Tool Server:

  • calculate_smiles_similarity: Compute molecular similarity using Morgan fingerprints
    • Args:
      • target_smiles (str): Query molecule SMILES string
      • candidate_smiles_list (list): List of candidate molecule SMILES strings
    • Returns:
      • similarities (list): List of similarity scores
        • smiles (str): Candidate SMILES string
        • score (float): Tanimoto similarity (0-1)
Input/Output

Input:

  • target_smiles: SMILES string of the query molecule
  • candidate_smiles_list: List of SMILES strings to compare against

Output:

  • List of similarity results:
    • smiles: Candidate molecule SMILES
    • score: Tanimoto similarity coefficient (0-1)
      • 1.0 = identical molecules
      • 0.7 = highly similar

      • 0.4-0.7 = moderately similar
      • <0.4 = dissimilar
Similarity Interpretation
  • Score > 0.85: Very high similarity, likely same scaffold
  • Score 0.7-0.85: High similarity, similar pharmacophore
  • Score 0.5-0.7: Moderate similarity, related structures
  • Score < 0.5: Low similarity, different chemical space
Use Cases
  • Virtual screening and library filtering
  • Scaffold hopping in drug design
  • Chemical space exploration
  • Lead compound identification
  • Analog searching in compound databases
  • Structure-activity relationship studies
Performance Notes
  • Execution time: <1 second for up to 1000 candidates
  • Fingerprint: Morgan fingerprint (radius 2, 2048 bits)
  • Algorithm: Tanimoto coefficient for binary fingerprints
  • Scalability: Efficient for large compound libraries

© InternScience, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/molecular-similarity-search of InternScience/scp.

Open the folder on GitHubat commit cea5398

Used in 2 other repositories

We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in InternScience/scp, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Molecular Similarity Search next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Molecular Similarity Search compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Molecular Similarity Search this skillInternScience/scp1701 repos~1.4kAutomated safety check: PassMIT
Drugbank Databasedavila7/claude-code-templates33k10 repos~2.3kAutomated safety check: PassMIT
Bio Similarity SearchingFreedomIntelligence/OpenClaw-Medical-Skills3.1k—~1.7kAutomated safety check: PassNone
Pdb Databasejaechang-hits/SciAgent-Skills3741 repos~7.7kAutomated safety check: PassBSD-3-Clause
Chem Similarity Searchlearningmatter-mit/AtomisticSkills176—~614Automated safety check: PassMIT
Codebase Explorationgiancarloerra/SocratiCode3.3k1 repos~1.5kAutomated safety check: PassAGPL-3.0

Similar skills

  • Drugbank Database

    davila7/claude-code-templates

    Access and analyze comprehensive drug information from the DrugBank database including drug properties, interactions, targets, pathways, chemical structures, and pharmacology data.

    33k GitHub starsUsed in 10 repos~2.3k tokens
    Research & ScienceAuto-check passed
  • Bio Similarity Searching

    FreedomIntelligence/OpenClaw-Medical-Skills

    Performs molecular similarity searches using Tanimoto coefficient on fingerprints via RDKit.

    3.1k GitHub stars~1.7k tokensUpdated 2 mo ago
    Research & ScienceAuto-check passed
  • Pdb Database

    jaechang-hits/SciAgent-Skills

    Query RCSB PDB (200K+ structures) via the public REST + GraphQL APIs with plain requests (no SDK).

    374 GitHub starsUsed in 1 repo~7.7k tokens
    Research & ScienceAuto-check passed
  • Chem Similarity Search

    learningmatter-mit/AtomisticSkills

    Find structurally similar chemical compounds using PubChem's 2D fast similarity engine via the PUG-REST API.

    176 GitHub stars~614 tokensUpdated 3 days ago
    Backend & APIsAuto-check passed
  • Codebase Exploration

    giancarloerra/SocratiCode

    Explore and understand codebases using SocratiCode semantic search, dependency graphs, and context artifacts.

    3.3k GitHub starsUsed in 1 repo~1.5k tokens
    DatabasesAuto-check passed
  • FAISS Similarity Search

    Orchestra-Research/AI-Research-SKILLs

    Sets up FAISS for fast nearest-neighbor search over large collections of dense vectors, choosing between Flat, IVF, HNSW and product quantization indexes.

    13k GitHub starsUsed in 6 repos~1.3k tokens
    DatabasesAuto-check passed

More from InternScience/scp

All 73 skills in this repo
  • Given an rsID, query multiple databases (dbSNP, FAVOR, GWAS Catalog, ClinVar, gnomAD, PharmGKB, ClinGen) for comprehensive annotation.

    170 GitHub starsUsed in 1 repo~2.2k tokens
    Auto-check passed
  • Calculate atmospheric parameters including Coriolis parameter, geostrophic wind, heat index, potential temperature, and dewpoint for meteorology and climate science.

    170 GitHub starsUsed in 1 repo~2.1k tokens
    Auto-check passed
  • Biomedical Web Search

    InternScience/scp

    Search biomedical literature and web content using Tavily search engine for research and clinical information.

    170 GitHub starsUsed in 1 repo~598 tokens
    Auto-check passed
  • Calculate buoyancy forces and acceleration for fluid mechanics and hydrodynamics analysis.

    170 GitHub starsUsed in 1 repo~540 tokens
    Auto-check passed
  • Capacitance Calculation

    InternScience/scp

    Calculate electrical capacitance from geometric parameters and dielectric properties for circuit design.

    170 GitHub starsUsed in 1 repo~537 tokens
    Auto-check passed
  • Chembl Molecule Search

    InternScience/scp

    Search ChEMBL database for molecule information by name to retrieve bioactivity data and chemical structures.

    170 GitHub starsUsed in 1 repo~757 tokens
    Auto-check passed

Questions about Molecular Similarity Search

What does Molecular Similarity Search do?

Search for similar molecules using Tanimoto similarity with Morgan fingerprints to identify structurally related compounds. Molecular Similarity Search is an agent skill from InternScience/scp. Search for similar molecules using Tanimoto similarity with Morgan fingerprints to identify structurally related compounds.

When should I use Molecular Similarity Search?

Molecular Similarity Search fits situations like: tasks that involve Vector databases; tasks that involve Drug discovery and cheminformatics.

How do I install Molecular Similarity Search in Claude Code?

Run `npx skills add InternScience/scp --skill molecular-similarity-search -a claude-code`. Or copy the skill folder (skills/molecular-similarity-search in InternScience/scp) into .claude/skills/molecular-similarity-search in your project. Claude Code loads it when a task matches its description.

How do I install Molecular Similarity Search in Codex?

Run `npx skills add InternScience/scp --skill molecular-similarity-search -a codex`. Or copy the skill folder (skills/molecular-similarity-search in InternScience/scp) into .agents/skills/molecular-similarity-search in your project. Codex loads it when a task matches its description.

Can I use Molecular Similarity Search in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add InternScience/scp --skill molecular-similarity-search -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/molecular-similarity-search, .gemini/skills/molecular-similarity-search, .github/skills/molecular-similarity-search and .opencode/skills/molecular-similarity-search in your project.

What does Molecular Similarity Search need to run?

SKILL.md names no scripts, command-line tools or credentials: Molecular Similarity Search is instructions for the agent only. Our summary lists: Python 3.

Does Molecular Similarity Search access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Molecular Similarity Search safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Molecular Similarity Search use?

Molecular Similarity Search is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Molecular Similarity Search use?

About 1.4k tokens (SKILL.md is roughly 5.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Molecular Similarity Search?

Skills that share tags, products or a category with Molecular Similarity Search: Drugbank Database (davila7/claude-code-templates, 33k stars), Bio Similarity Searching (FreedomIntelligence/OpenClaw-Medical-Skills, 3.1k stars), Pdb Database (jaechang-hits/SciAgent-Skills, 374 stars) and Chem Similarity Search (learningmatter-mit/AtomisticSkills, 176 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Molecular Similarity Search?

InternScience (a GitHub organization) maintains it in InternScience/scp, which has 170 GitHub stars. The repository holds 73 skills in this directory. The repository was last updated on June 3, 2026.

Source: InternScience/scp on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.