tmbot12/meridian-edge-mcp
MCP server for real-time prediction market consensus data. 27,000+ markets, 100M+ data points, 14-second updates. Works with Claude Desktop, Cursor, VS Code, and any MCP client.
Platform-specific configuration:
{
"mcpServers": {
"meridian-edge-mcp": {
"command": "npx",
"args": [
"-y",
"meridian-edge-mcp"
]
}
}
}Add the config above to .claude/settings.json under the mcpServers key.
<!-- mcp-name: io.github.tmbot12/meridian-edge -->
[](https://pypi.org/project/meridian-edge-mcp/) [](LICENSE) [](https://modelcontextprotocol.io) [](https://registry.modelcontextprotocol.io)
Query real-time prediction market consensus data directly from Claude and other AI assistants via the Model Context Protocol.
Ask Claude: *"What does the prediction market say about the Lakers game tonight?"* and get a live answer.
---
This MCP server gives Claude access to Meridian Edge — aggregated prediction market consensus data from multiple regulated prediction markets, updated every 10 minutes.
5 tools available to Claude:
| Tool | What it returns | |------|----------------| | get_consensus | Aggregated consensus probabilities for sports/politics events | | get_opportunities | Events where prediction markets show notable divergence | | get_signals | Recent directional market moves | | get_markets | Active markets currently being tracked | | get_settlements | Recently settled events with verified outcomes |
---
{
"mcpServers": {
"meridian-edge": {
"command": "uvx",
"args": ["meridian-edge-mcp"]
}
}
}pip install meridian-edge-mcp{
"mcpServers": {
"meridian-edge": {
"command": "meridian-edge-mcp"
}
}
}git clone https://github.com/meridian-edge/meridian-edge-mcp
cd meridian-edge-mcp
pip install -e .{
"mcpServers": {
"meridian-edge": {
"command": "python",
"args": ["-m", "meridian_edLoading reviews...