kb-gateway
Allows querying a Neo4j graph database for coverage, disputes, topic depth, etc.
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., "@kb-gatewaysearch the corpus for LangChain agent tutorials"
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.
kb-gateway
HTTP MCP gateway for James's 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 | |
Friends (external) |
|
External collaborators | |
LLMs / agents | |
Discovery |
Production: https://kb-mcp.waytie.com/mcp
Related MCP server: kb-gateway
What it does
Remote agents call MCP tools instead of holding Pinecone/Neo4j credentials:
Tool | Purpose |
| Canonical structured answer — stable wrapper over routing/full-corpus retrieval with sanitized evidence |
| Default for broad research — full-corpus search with namespace-tagged sources |
| Use when graph vs vector routing matters, or the question is structural/ambiguous |
| Semantic RAG ( |
| Neo4j coverage / disputes / topic depth |
| Corpus inventory |
| Dependency check |
Browser/mobile query page: https://kb-access.waytie.com/query uses the same issued MCP bearer token and returns the answer_learning_kb contract without exposing Pinecone/Neo4j credentials.
For new agents, call answer_learning_kb first. Use intent="broad" for full-corpus research, intent="structural" for coverage/dispute questions, and namespace="research-papers" when external paper evidence is the target. Responses include retrieval_status, evidence.sources, and next_steps; do not make a no-context claim from one empty result.
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 nginxArchitecture
ARCHITECTURE.md · RUNBOOK.md · docs/client-setup.md
Related
KeyFlo-ai/knowledge-base— parallel HTTP APIokrealai/langchain-course— router runtime deps
This server cannot be deployed
Maintenance
Related MCP Connectors
Agent-native MCP server over the public saagarpatel.dev corpus. Read-only, stateless.
Cloud or self-hosted knowledge for AI agents: hybrid search, reranking, GraphRAG, scoped MCP tools.
NeuralBrain MCP Server - RAG, Vector Memory, LLM Routing, Agent Identity, x402 Payments
- UnifAPIOAuthcom.unifapi
Hosted MCP server for live public-data APIs and Skills for AI agents.
Related MCP Servers
- FlicenseNot gradedqualityFmaintenanceHTTP MCP gateway for a learning corpus with Pinecone, Neo4j, and agentic router, enabling remote agents to query via tools like route_query, query_namespace, graph_query, etc.-

kb-gatewayofficial
FlicenseNot gradedqualityBmaintenanceHTTP MCP gateway for a learning corpus that enables remote agents to perform semantic search, graph queries, and routing via Pinecone and Neo4j without direct database credentials.-- FlicenseBqualityDmaintenanceGraphRAG MCP server for querying SNOM CT medical terminology via Neo4j, offering graph_search_concept and graph_get_related tools to search and traverse concepts and relationships.2-
- FlicenseAqualityBmaintenanceExposes a Neo4j knowledge-graph index over personal markdown notes to LLM agents via MCP, enabling semantic search, tag navigation, and relationship discovery.6-