Fuzzy Match MCP

A Python-based Model Context Protocol (MCP) server for deterministic fuzzy text matching.

It can normalize text, compare strings, rank possible matches, group duplicate values, and explain why two values match or differ. The server uses RapidFuzz for similarity scoring and can be used from MCP clients such as Cursor.

Features

• Normalize text before comparison

• Compare two strings using multiple similarity algorithms

• Rank the best matches from a list

• Detect and group probable duplicates

• Explain matching results using token overlap

• Use specialized matching profiles for companies, products, and addresses

• Select different scoring strategies

• Run locally through MCP over stdio

• Testable with pytest

Related MCP server: EntityIdentification

Available MCP tools

normalize_text

Normalizes a text value before fuzzy matching.

Example input:

{
  "value": "  Müller & Söhne GmbH!  ",
  "profile": "general"
}

Example result:

{
  "original": "  Müller & Söhne GmbH!  ",
  "profile": "general",
  "normalized": "muller and sohne gmbh"
}

compare_strings

Compares two strings and returns detailed similarity scores.

Example input:

{
  "first": "Deutsche Bank AG",
  "second": "Deutsche Bank Aktiengesellschaft",
  "threshold": 90,
  "profile": "company",
  "strategy": "strict"
}

The response includes:

• Normalized values

• Individual similarity scores

• Selected strategy

• Final selected score

• Match decision

find_best_matches

Ranks candidate strings according to their similarity with a query.

Example input:

{
  "query": "Samsung Galaxy S24",
  "choices": [
    "Apple iPhone 15",
    "Samsung Galaxy S24 128GB",
    "Galaxy S24 Smartphone",
    "Google Pixel 9"
  ],
  "limit": 3,
  "threshold": 40,
  "profile": "product",
  "strategy": "weighted"
}

find_duplicate_groups

Groups values that probably represent the same entity.

Example input:

{
  "values": [
    "Deutsche Bank AG",
    "Deutsche-Bank Aktiengesellschaft",
    "Deutsche Bank",
    "Commerzbank AG",
    "Commerz Bank",
    "Amazon Germany GmbH"
  ],
  "threshold": 80,
  "profile": "company",
  "strategy": "strict"
}

This is useful for:

• Customer-data cleanup

• Product-catalog deduplication

• Company-name matching

• Imported CSV cleanup

• Contact-list deduplication

explain_match

Compares two values and explains the result using normalized tokens and score information.

Example input:

{
  "first": "Samsung Galaxy S24 128GB Black",
  "second": "Galaxy S24 Black 128 GB",
  "threshold": 75,
  "profile": "product",
  "strategy": "strict"
}

The response includes:

• Common tokens

• Tokens found only in the first value

• Tokens found only in the second value

• Token-overlap percentage

• A deterministic explanation

• Final match decision

Matching profiles

The server supports the following normalization profiles.

Company-profile example

Deutsche Bank AG
Deutsche Bank Aktiengesellschaft

Both normalize approximately to:

deutsche bank

Product-profile example

Samsung Galaxy S 24 128 GB

Normalizes to:

samsung galaxy s24 128gb

Matching strategies

The strict strategy excludes partial_ratio from the final composite score because partial matching can be misleading when a short string appears inside a much longer string.

Thresholds

Similarity scores range from 0 to 100.

• 90–100: very strict

• 80–89: useful default for names and product titles

• 70–79: more permissive

• Below 70: may create more false-positive matches

A result is considered a match when:

selected_score >= threshold

The ideal threshold depends on the dataset and the acceptable false-positive rate.

Project structure

fuzzy-match-mcp/
├── .cursor/
│   └── mcp.json
├── fuzzy_match_mcp/
│   ├── __init__.py
│   ├── grouping.py
│   ├── matching.py
│   ├── server.py
│   ├── tools.py
│   └── validators.py
├── tests/
│   ├── __init__.py
│   └── test_matching.py
├── main.py
├── pyproject.toml
├── README.md
└── uv.lock

Requirements

• Python 3.10 or newer

• uv

• MCP Python SDK

• RapidFuzz

• pytest for development

Installation

Clone the repository:

git clone <your-repository-url>
cd fuzzy-match-mcp

Install the dependencies:

uv sync

If you are creating the project from scratch:

uv add "mcp[cli]" rapidfuzz
uv add --dev pytest

Running the tests

uv run pytest

Running with MCP Inspector

Use MCP Inspector during development:

uv run mcp dev main.py

This opens an MCP development interface where the registered tools can be inspected and called.

Running as a local stdio server

uv run python main.py

The process waits for MCP JSON-RPC messages through standard input.

Do not type into the terminal while the server is running over stdio. A blank terminal input is not a valid MCP JSON-RPC message.

Do not use ordinary print() statements in the server because standard output is reserved for MCP communication. Use logging through standard error instead.

Cursor configuration

Create:

.cursor/mcp.json

Use the following configuration on Windows:

{
  "mcpServers": {
    "fuzzy-match": {
      "type": "stdio",
      "command": "${workspaceFolder}/.venv/Scripts/python.exe",
      "args": [
        "${workspaceFolder}/main.py"
      ]
    }
  }
}

Then:

1. Open the repository root in Cursor.

2. Open Customize → MCPs.

3. Enable fuzzy-match.

4. Click Reload after changing the registered tools.

5. Use Cursor Agent to call the MCP tools.

Cursor starts the Python process automatically. Do not manually run main.py at the same time.

Example Cursor Agent prompts

Normalize text

Use the fuzzy-match normalize_text tool to normalize:

"  Müller & Söhne GmbH!  "

Use the general profile.

Compare company names

Use the fuzzy-match compare_strings tool.

Compare:
- Deutsche Bank AG
- Deutsche Bank Aktiengesellschaft

Use:
- profile: company
- strategy: strict
- threshold: 90

Rank product matches

Use the fuzzy-match find_best_matches tool.

Query:
Samsung Galaxy S24

Choices:
- Apple iPhone 15
- Samsung Galaxy S24 128GB
- Galaxy S24 Smartphone
- Google Pixel 9

Use the product profile and return the best three matches.

Group duplicates

Use the fuzzy-match find_duplicate_groups tool with:

- Deutsche Bank AG
- Deutsche-Bank Aktiengesellschaft
- Deutsche Bank
- Commerzbank AG
- Commerz Bank
- Amazon Germany GmbH

Use:
- profile: company
- strategy: strict
- threshold: 80

Explain a match

Use the fuzzy-match explain_match tool to compare:

- Samsung Galaxy S24 128GB Black
- Galaxy S24 Black 128 GB

Use:
- profile: product
- strategy: strict
- threshold: 75

How it works

The request flow is:

MCP client
    ↓
MCP tool in tools.py
    ↓
Input validation in validators.py
    ↓
Matching or grouping logic
    ↓
RapidFuzz
    ↓
Structured JSON result

Normalization happens before similarity scoring. It can include:

• Unicode case folding

• Accent removal

• Punctuation replacement

• Whitespace cleanup

• Profile-specific transformations

Performance notes

find_best_matches compares one query against each candidate.

find_duplicate_groups performs pairwise comparisons. Its approximate comparison count is:

n × (n - 1) / 2

For this reason, duplicate grouping is intentionally limited to 500 values in the current version.

The grouping implementation uses union-find. If A matches B and B matches C, all three values can be placed in the same group even when A and C do not directly exceed the threshold.

Current limitations

• Duplicate grouping is pairwise and is not intended for very large datasets.

• Company suffixes and address aliases are rule-based and may not cover every country.

• Product normalization supports only a small set of common units.

• Fuzzy matching does not prove that two real-world entities are identical.

• Thresholds should be evaluated against domain-specific examples before automatic merging.

Planned improvements

• Structured record matching

• Batch matching

• Threshold evaluation

• Custom normalization options

• Additional international company suffixes

• CSV import and export

• Better canonical-value selection

• More matching profiles

• MCP resources and reusable prompts

Contributing

Contributions are welcome.

Suggested workflow:

git checkout -b feature/my-change
uv sync
uv run pytest

Before submitting a change:

• Add tests for new behavior

• Keep MCP tools focused

• Avoid writing to standard output

• Preserve structured JSON responses

• Document new profiles and strategies

License

Add your chosen license before publishing the project.

A common choice for an open-source MCP server is the MIT License.