PolyBridge is answering right now. Last checked 14 min ago. It exposes 2 tools.
Calibrated probabilistic foresight for AI agents, powered by live prediction-market signal.
Today is the operative word: we check PolyBridge every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 14 min ago.
claude mcp add polybridge-mcp --transport http https://mcp.polybridge.ai/mcp
{
"mcpServers": {
"polybridge-mcp": {
"url": "https://mcp.polybridge.ai/mcp"
}
}
}
[mcp_servers.polybridge-mcp]
url = "https://mcp.polybridge.ai/mcp"
{
"mcpServers": {
"polybridge-mcp": {
"url": "https://mcp.polybridge.ai/mcp"
}
}
}
{
"mcpServers": {
"polybridge-mcp": {
"url": "https://mcp.polybridge.ai/mcp"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
polybridge_forecast
polybridge_search
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://mcp.polybridge.ai/mcp | streamable-http | answering | 178 ms | 14 min ago |
AI-powered vector knowledge graph MCP server for agents. Supports add node, add edge, semantic node
Ingest, manage, and retrieve documents for RAG-powered AI applications
BM25 search + tree navigation over markdown docs for AI agents. No embeddings, no LLM calls.
Self-hosted long-term memory for AI agents over MCP — hierarchical recall backed by pgvector
Associative key-graph memory for LLM agents — recall by association, not vector similarity.
Semantic code search for AI agents — hybrid BM25+vector, call-graph, 20+ languages.
Deterministic SVG perception for LLM agents — measures, never guesses. MCP server.
Shared memory + orchestration for your coding agents. Local-first MCP, vector RAG.
Answers built from our own checks of this server.