Back to search
mcp_server
MCP serverGitHub
A local Model Context Protocol (MCP) server that connects an AI client to a PostgreSQL-based English-to-Hindi dictionary.
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Checked today
Badge for your README
Markdown
[](/listings/krishnagondaliya34-cell--mcp-server)HTML
<a href="/listings/krishnagondaliya34-cell--mcp-server"><img src="/api/listings/krishnagondaliya34-cell--mcp-server/badge.svg" alt="findsafeskills safety rating" /></a>Install
i
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
python -m pip install --upgrade pip python -m pip install -r requirements.txt
The `uv` package is included because the MCP Inspector development command may use it to launch the server.
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
README.md · README · 160 lines
- # English-to-Hindi Dictionary MCP Server
- A local Model Context Protocol (MCP) server that connects an AI client
- to a PostgreSQL-based English-to-Hindi dictionary.
- The server currently provides two tools:
- - `lookup_word`: looks up an English word and returns its Hindi
- meaning.
- - `save_translation`: inserts a new English-to-Hindi translation. The
- database prevents duplicate English words from being inserted.
- > **Save approval:** The `save_translation` tool is intended to be
- > called only when the user explicitly asks the AI client to add, save,
- > or store a translation. The tool description communicates this
- > instruction to the AI client. The client must still follow that
- > instruction; the server itself does not independently verify the
- > user's conversational approval.
- ## Project structure
- A typical project folder looks like this:
- ``` text
- hindi-dictionary/
- ├── .venv/ # Python virtual environment (not committed)
- ├── .env # Local database credentials (not committed)
- ├── .gitignore
- ├── requirements.txt
- ├── README.md
- └── server.py
- ```
- ## Requirements
- - Python 3.10 or newer
- - PostgreSQL
- - A PostgreSQL database and user with permission to create/read/write
- the dictionary table
- - An MCP-compatible client, such as Claude Desktop or Gemini CLI
- The project uses the MCP 1.x FastMCP API. The requirements file
- intentionally constrains the MCP package to versions below 2 because the
- server code imports `FastMCP` from `mcp.server.fastmcp`.
- ## 1. Create and activate a virtual environment
- From the project directory in Windows PowerShell:
- ``` powershell
- python -m venv .venv
- .\.venv\Scripts\Activate.ps1
- ```
- If PowerShell blocks activation, you can run the virtual-environment
- Python directly, or follow your organization's PowerShell execution
- policy guidance.
- ## 2. Install dependencies
- ``` powershell
- python -m pip install --upgrade pip
- python -m pip install -r requirements.txt
- ```
- The `uv` package is included because the MCP Inspector development
- command may use it to launch the server.
- ## 3. Create the PostgreSQL database and table
- Create a database named `hindi_dictionary` in PostgreSQL if it does not
- already exist.
- Connect to that database, then execute:
- ``` sql
- CREATE TABLE IF NOT EXISTS translations (
- id INTEGER GENERATED ALWAYS AS IDENTITY PRIMARY KEY,
- english_word VARCHAR(200) NOT NULL UNIQUE,
- hindi_meaning TEXT NOT NULL,
- created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
- );
- ```
- Verify the table exists:
- ``` sql
- SELECT * FROM translations;
- ```
- You can run these SQL commands in pgAdmin's Query Tool after selecting
- the `hindi_dictionary` database.
- ## 4. Configure the `.env` file
- Create a file named `.env` in the same folder as `server.py`:
- ``` env
- DB_HOST=localhost
- DB_PORT=5432
- DB_NAME=hindi_dictionary
- DB_USER=postgres
- DB_PASSWORD=your_postgresql_password
- ```
- Replace `your_postgresql_password` with the password for your PostgreSQL
- user.
- Do not commit or share `.env`. It contains credentials. Add the
- following to `.gitignore`:
- ``` gitignore
- .env
- .venv/
- __pycache__/
- *.pyc
- ```
- ## 5. Run the MCP server
- The server uses standard input/output (STDIO) transport:
- ``` powershell
- python server.py
- ```
- A STDIO MCP server normally waits for an MCP client and may not print a
- friendly "server started" message. Keep the process running when testing
- it directly. When an MCP client launches the server, the client manages
- that process.
- ## 6. Test with MCP Inspector
- With the virtual environment activated, run:
- ``` powershell
- mcp dev server.py
- ```
- Open the Inspector URL shown in the terminal. Connect using the STDIO
- transport and confirm that these tools are listed:
- - `lookup_word`
- - `save_translation`
- Test `save_translation` with a new word and Hindi meaning, then test
- `lookup_word` with that English word. Test the duplicate case by
- attempting to save the same English word again; the existing translation
- should remain unchanged.
- If the Inspector reports that it cannot spawn `uv`, verify that `uv` is
- installed in the active environment:
- ``` powershell
- python -m pip install uv
- uv --version
- ```
- Restart the Inspector after installing it.
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.