kb-gateway
HTTP MCP gateway enabling remote agents to query a learning corpus combining Pinecone vector search and Neo4j graph database through tools like route_query, query_namespace, and graph_query.
README
kb-gateway
HTTP MCP gateway for the learning corpus — Pinecone + Neo4j + agentic router.
Cole — start here (KeyFlo org)
MCP endpoint: https://kb-mcp.waytie.com/mcp
git clone git@github.com:KeyFlo-ai/kb-gateway.git
cd kb-gateway
gh auth login
./scripts/setup-mcp.sh # pulls KB_GATEWAY_MCP_* from GitHub variables
# paste config/mcp.json → Cursor Settings → MCP
→ Full guide: docs/COLE-SETUP.md · GitHub variable COLE_SETUP points here.
HTTP API (no MCP): KeyFlo-ai/knowledge-base · https://kb-api.keyflo.ai
| Audience | Start here |
|---|---|
| Cole / KeyFlo collaborators | docs/COLE-SETUP.md |
| Friends (external) | docs/FRIEND-SETUP.md · Request: https://kb-access.waytie.com |
| External collaborators | James-Server-Admin/kb-gateway |
| LLMs / agents | AGENTS.md |
| Discovery | llms.txt |
Production: https://kb-mcp.waytie.com/mcp
What it does
Remote agents call MCP tools instead of holding Pinecone/Neo4j credentials:
| Tool | Purpose |
|---|---|
route_query |
Default — auto-pick graph vs vector vs both |
query_namespace |
Semantic RAG (patterns, course-transcripts, langchain-docs) |
graph_query |
Neo4j coverage / disputes / topic depth |
list_namespaces |
Corpus inventory |
health |
Dependency check |
Quick start (server operator)
source /mnt/blockstorage/env/load.sh kb-gateway
/root/.venv-langchain-course/bin/python -m kb_gateway --transport streamable-http
# binds 127.0.0.1:8790 — public via kb-mcp.waytie.com nginx
Architecture
ARCHITECTURE.md · RUNBOOK.md · docs/client-setup.md
Related
KeyFlo-ai/knowledge-base— parallel HTTP APIokrealai/langchain-course— router runtime deps
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.