Skip to main content
Glama
mcp-server-test

mcp-server-test

by JussCubs

Vector GraphQL MCP Server

This MCP server provides tools for querying the Vector GraphQL API:

  • fetch_leaderboard: Get Vector leaderboard data

  • fetch_profile: Get detailed trader profile data

  • fetch_token_data: Get trending Solana tokens

  • fetch_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]" httpx

If 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.txt

Related 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.py

Troubleshooting

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 tools
fetch_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

    A3.7/5.0

    Scored across 4 tools

    Disambiguation5/5

    Each tool has a unique purpose: leaderboard, profile, token broadcasts, and token data. There is no overlap between fetching different data types.

    Naming Consistency5/5

    All tools follow a consistent 'fetch_' prefix with descriptive nouns (leaderboard, profile, token_broadcasts, token_data) in snake_case.

    Tool Count4/5

    4 tools is a reasonable number for a focused data retrieval server. It covers key endpoints without being excessive or too sparse.

    Completeness4/5

    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