mcp-server-test
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp-server-test fetch_profile for trader johndoe"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Vector GraphQL MCP Server
This MCP server provides tools for querying the Vector GraphQL API:
fetch_leaderboard: Get Vector leaderboard datafetch_profile: Get detailed trader profile datafetch_token_data: Get trending Solana tokensfetch_token_broadcasts: Get broadcasts for a specific token
Setup
# Clone the repository
git clone https://github.com/JussCubs/mcp-server-test.git
cd mcp-server-test
# Install dependencies with uv
uv add "mcp[cli]" httpxIf you don't have uv installed, you can install it following the instructions at https://github.com/astral-sh/uv.
Alternatively, you can use pip:
pip install -r requirements.txtRelated MCP server: mcp-server-cloudbrowser
Usage
# Run in development mode with the MCP Inspector
uv run mcp dev vector_server.py
# OR if you're using pip
mcp dev vector_server.py
# Install in Claude Desktop
uv run mcp install vector_server.py
# OR if you're using pip
mcp install vector_server.pyTroubleshooting
If you see a warning like The package 'mcp==X.X.X' does not have an extra named 'cli', you may need to install the CLI tools separately:
pip install mcp httpx "click>=8.0" "rich>=10.0" "typer>=0.9.0"Tool Documentation
fetch_leaderboard
Fetches Vector leaderboard data:
leaderboard_type: The type of leaderboard (default: 'PNL_WIN')
fetch_profile
Fetches detailed profile data for a Vector trader:
username: Vector username to fetch
fetch_token_data
Fetches trending Solana tokens from Vector. This tool has no parameters and returns trending tokens with 5-minute broadcast activity.
fetch_token_broadcasts
Fetches broadcasts for a specific token:
token_id: Vector token ID
Available Tools
4 toolsfetch_leaderboardB
Fetch Vector leaderboard data
Args:
leaderboard_type: Type of leaderboard (e.g., 'PNL_WIN', 'TRADE_VOLUME')
Returns:
JSON string with leaderboard data
Inputs: leaderboard_type. Returns: result
fetch_profileB
Fetch detailed profile data for a Vector trader
Args:
username: Vector username to fetch
Returns:
JSON string with profile data
Inputs: username (required). Returns: result
fetch_token_broadcastsB
Fetch broadcasts for a specific token
Args:
token_id: Vector token ID
Returns:
JSON string with token broadcasts
Inputs: token_id (required). Returns: result
fetch_token_dataA
Fetch trending Solana tokens from Vector
Returns:
JSON string with token data
Inputs: no named parameters. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool has a unique purpose: leaderboard, profile, token broadcasts, and token data. There is no overlap between fetching different data types.
All tools follow a consistent 'fetch_' prefix with descriptive nouns (leaderboard, profile, token_broadcasts, token_data) in snake_case.
4 tools is a reasonable number for a focused data retrieval server. It covers key endpoints without being excessive or too sparse.
The set covers major data categories for a trading platform (leaderboard, profile, token info, broadcasts). Missing details like token price or history, but sufficient for common queries.
Related MCP Connectors
Related MCP Servers
- MIT
- -
- MIT
- -