MCP server to allow LLMs to read MDX/MDD dictionary files directly
Project description
MDict MCP Server
Installation
git clone https://github.com/cdpath/mdict-mcp
cd mdict-mcp
uv sync
Usage
- Place your MDX dictionary files in the
/path/to/mdicts/directory - Start the MCP server:
uv run mdict-mcp -d /path/to/mdicts/
- Connect from your MCP client (Claude Desktop, Chatwise, etc.)
Chatwise:
uv --directory $HOME/Developer/mdict-mcp run mdict-mcp --log-level INFO --dictionary-dir /path/to/mdicts/
Available Tools
Core Dictionary Tools
lookup_word - Look up a word in the loaded dictionaries
Request:
{
"word": "science",
"dictionary": "optional_specific_dictionary_name"
}
Response:
{
"word": "science",
"found": true,
"dictionary": null,
"definition": "<HTML definition content>",
"success": true
}
search_words - Search for words matching a pattern
Request:
{
"pattern": "sci",
"limit": 10,
"dictionary": "optional_specific_dictionary_name"
}
Response:
{
"pattern": "sci",
"limit": 10,
"dictionary": null,
"count": 5,
"words": ["science", "scientist", "scissors", "scintillate", "scimitar"],
"success": true
}
find_similar_words - Find words similar to a given word using fuzzy matching
Request:
{
"word": "science",
"dictionary": "optional_specific_dictionary_name",
"limit": 10,
"max_distance": 2
}
Response:
{
"word": "science",
"dictionary": null,
"limit": 10,
"max_distance": 2,
"total_found": 15,
"returned": 10,
"similar_words": [
{
"word": "sciences",
"dictionary": "Webster",
"edit_distance": 1,
"similarity_score": 0.875
}
],
"success": true
}
Dictionary Management Tools
list_dictionaries - List all loaded dictionaries with metadata
Request:
{}
Response:
{
"count": 2,
"dictionaries": [
{
"name": "Webster",
"path": "/path/to/webster.mdx",
"description": "Webster's Dictionary",
"version": "1.0"
}
],
"success": true
}
scan_dictionaries - Scan the dictionary directory for new MDX files and load them
Request:
{}
Response:
{
"directory": "./mdicts",
"total_files": 5,
"already_loaded": 2,
"new_loaded": 3,
"failed": 0,
"successfully_loaded": ["./mdicts/oxford.mdx"],
"failed_files": [],
"success": true
}
get_dictionary_metadata - Get detailed metadata information for a specific dictionary
Request:
{
"dictionary": "dictionary_name"
}
Response:
{
"dictionary": "Webster",
"metadata": {
"title": "Webster's Dictionary",
"description": "English Dictionary",
"version": "1.0",
"entries": 50000
},
"success": true
}
get_dictionary_keys - Get all available keys (words) from a dictionary or sample of keys
Request:
{
"dictionary": "dictionary_name",
"limit": 100,
"prefix": "optional_prefix"
}
Response:
{
"dictionary": "Webster",
"prefix": "sci",
"total_keys": 50000,
"filtered_keys": 25,
"returned_keys": 10,
"limit": 10,
"keys": ["science", "scientist", "scientific"],
"success": true
}
Dependencies
- mcp: Model Context Protocol implementation
- mdict-utils: MDX/MDD file parsing
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
mdict_mcp-0.1.0.tar.gz
(28.2 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
mdict_mcp-0.1.0-py3-none-any.whl
(10.7 kB
view details)
File details
Details for the file mdict_mcp-0.1.0.tar.gz.
File metadata
- Download URL: mdict_mcp-0.1.0.tar.gz
- Upload date:
- Size: 28.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.12.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
aa59d73a5c47e58608747d2fa6d86ea6f651629a2ae3ee01e390ac13a444159e
|
|
| MD5 |
1cf63cc99d3e2d9447ebfe2551b8cf9d
|
|
| BLAKE2b-256 |
8df3882d67da59917c57849e79d1dbd9dd2a416c7d55216384f33695d6f29878
|
Provenance
The following attestation bundles were made for mdict_mcp-0.1.0.tar.gz:
Publisher:
python-publish.yml on cdpath/mdict-mcp
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
mdict_mcp-0.1.0.tar.gz -
Subject digest:
aa59d73a5c47e58608747d2fa6d86ea6f651629a2ae3ee01e390ac13a444159e - Sigstore transparency entry: 230503166
- Sigstore integration time:
-
Permalink:
cdpath/mdict-mcp@d61fc2a6bcab935bef796083fb3e773d0abc3263 -
Branch / Tag:
refs/tags/v0.1 - Owner: https://github.com/cdpath
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
python-publish.yml@d61fc2a6bcab935bef796083fb3e773d0abc3263 -
Trigger Event:
release
-
Statement type:
File details
Details for the file mdict_mcp-0.1.0-py3-none-any.whl.
File metadata
- Download URL: mdict_mcp-0.1.0-py3-none-any.whl
- Upload date:
- Size: 10.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.12.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
986334683664fa3561559b07ae8a24db9a86c98c432ed1211d7ad21a00b07f58
|
|
| MD5 |
aee5325cc72c517c1218577e63a5f966
|
|
| BLAKE2b-256 |
4b3f7d4a523d00b311443801e8b58a49eebc0cd926bc8b1f13d6278fcb31cc6e
|
Provenance
The following attestation bundles were made for mdict_mcp-0.1.0-py3-none-any.whl:
Publisher:
python-publish.yml on cdpath/mdict-mcp
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
mdict_mcp-0.1.0-py3-none-any.whl -
Subject digest:
986334683664fa3561559b07ae8a24db9a86c98c432ed1211d7ad21a00b07f58 - Sigstore transparency entry: 230503167
- Sigstore integration time:
-
Permalink:
cdpath/mdict-mcp@d61fc2a6bcab935bef796083fb3e773d0abc3263 -
Branch / Tag:
refs/tags/v0.1 - Owner: https://github.com/cdpath
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
python-publish.yml@d61fc2a6bcab935bef796083fb3e773d0abc3263 -
Trigger Event:
release
-
Statement type:
