Skip to main content
📖 The AI Tool Bible

Setoku

Open-source MCP knowledge server that makes any AI fluent in your company data

Free· Free / open-source (Apache-2.0). Self-hosting cost only: ~$5-12/mo VPS. No SaaS tier and no per-token inference charges from Setoku itself.RAGModel-agnostic (MCP); commonly paired with Claude / Claude Code
Visit website →
Best for

Small engineering-led startups already using Claude Code or Claude Desktop who want a self-hosted, MCP-native way to give their AI grounded access to Postgres, GitHub, Slack and finance data without paying a SaaS analytics vendor.

Skip if

Non-technical teams without ops capacity to run a VPS, enterprises needing SOC2-grade vendor support, or shops standardized on non-MCP AI stacks like bare OpenAI Assistants or Gemini with no client-side MCP layer.

Setoku is an open-source, self-hosted Model Context Protocol (MCP) knowledge server from Hedgy Labs that acts as a governed bridge between AI assistants (Claude Code, Claude Desktop, or any MCP client) and a company's operational data. It runs on a cheap VPS and mirrors PostgreSQL databases, GitHub activity, Vercel/Render deploy logs, Slack messages, and Mercury banking into a unified ClickHouse data lake, then exposes that data through read-only MCP tools plus a maintained layer of metric definitions, entity documentation, and semantic context that improves with use. Because inference happens inside whatever MCP client the user already runs, Setoku never charges for tokens; it is infrastructure, not a model wrapper. Typical workflows include asking Claude to answer ad-hoc analytical questions with live company numbers, generating shareable live-data dashboards from natural-language prompts, letting non-technical employees query governed data without SQL, and giving coding agents grounded context (issues, commits, deploys, incidents) when planning changes. The project ships an opinionated bootstrap script (./deploy/bootstrap.sh) for a fresh Ubuntu box, a Claude Code plugin marketplace entry (/plugin marketplace add Hedgy-Labs/setoku followed by /setoku:onboard), and prompt-driven skills that let an agent scaffold new connectors when a source isn't yet supported. It targets small-to-mid engineering-led teams that want data-sovereign RAG-over-business-data without adopting a closed vendor stack.

Editor's take

Setoku is one of the more coherent takes on 'MCP as a company data plane' I've seen: instead of another closed text-to-SQL SaaS, it's a boring, cheap VPS mirroring your systems into ClickHouse and speaking MCP. If you already live in Claude Code, the /setoku:onboard flow is genuinely slick. It's early, narrow on connectors, and demands sysadmin comfort - but the Apache-2.0 licence and zero inference markup make it a low-risk bet.

— The AI Tool Bible editorial team

Pros

  • ✅ Fully open-source under Apache-2.0 with source on GitHub (Hedgy-Labs/setoku), avoiding vendor lock-in
  • ✅ Model-agnostic via MCP - works with Claude, Claude Code, or any conforming client
  • ✅ Zero server-side inference cost; runs on a $5-12/mo VPS since compute stays in the client
  • ✅ Unified ClickHouse data lake ingests Postgres, GitHub, Vercel, Render, Slack and Mercury out of the box
  • ✅ Governed, read-only access layer suitable for exposing sensitive data to non-technical staff
  • ✅ First-class Claude Code plugin install path (/setoku:onboard) turns setup into a chat flow
  • ✅ Ships agent-friendly skills so a coding assistant can wire up missing connectors itself

Cons

  • ⚠️ No hosted SaaS - teams must be comfortable running and maintaining a Linux VPS
  • ⚠️ Small, young project from Hedgy Labs with limited third-party ecosystem or community track record
  • ⚠️ Read-only by design; not a workflow or write-back tool for updating source systems
  • ⚠️ Connector list is narrow (six sources); anything outside Postgres/GitHub/Vercel/Render/Slack/Mercury requires DIY
  • ⚠️ Value is tightly coupled to Claude/MCP tooling - teams standardized on non-MCP AI stacks get less benefit
  • ⚠️ Documentation is early-stage; no published pricing, SLAs, or enterprise support offering

Use cases

MCP knowledge server for Claude CodeRAG over company PostgresNatural-language dashboards on live dataGoverned data access for non-technical staffGrounding coding agents in GitHub and deploy historySlack message search from an AI assistantMercury banking Q&A via ClaudeSelf-hosted alternative to closed analytics copilotsMetric and entity definition layer for LLM analytics

Explore related

Setoku alternatives →All RAGOpen-source toolsTools with an APIFree trial availableMore free tools

Compare with similar tools

All in RAG →
Compare
Setoku vs Pinecone
Side-by-side breakdown
Compare
Setoku vs LlamaIndex
Side-by-side breakdown
Compare
Setoku vs Elasticsearch Vector Search
Side-by-side breakdown

Pinecone

Featured
RAG · Hosted vector DB (not an LLM)
8.8

Managed vector database for production-scale similarity search.

Freemium· Free starter; serverless pay-as-you-go from $0.33/1M readsmanaged vector DBproduction RAG

LlamaIndex

Featured
RAG · BYO (Claude / GPT / open)
8.7

Data framework for connecting LLMs to your data.

Freemium· Free open-source; LlamaCloud paidRAGdata ingestion

Elasticsearch Vector Search

RAG · BYO embeddings (OpenAI, Cohere, Hugging Face, Mistral, Bedrock, Vertex, Azure) plus Elastic's built-in ELSER sparse model and E5 dense model
8.7

Hybrid vector + keyword search in the enterprise-grade Elasticsearch engine

Freemium· Free self-managed open-source core; Elastic Cloud Serverless usage-based (VCU-priced); Elastic Cloud Hosted from ~$95/mo (Standard) with Gold/Platinum/Enterprise tiers; custom Enterprise pricing.RAG chatbot over enterprise docsHybrid semantic + keyword product search

Snowflake Cortex

RAG · Anthropic Claude, Meta Llama, Mistral Large 2, Snowflake Arctic
8.7

Generative AI and RAG built into the Snowflake data cloud

Enterprise· Consumption-based via Snowflake credits; requires a Snowflake account. Free trial available at signup.snowflake.com. LLM function usage priced per credit per million tokens; Cortex Search and Analyst billed separately by credits consumed.Enterprise RAG chatbot over governed dataNatural-language SQL for business analysts

DataStax Astra DB

RAG · Bring-your-own embeddings; integrates with OpenAI, Cohere, Hugging Face, Mistral, NVIDIA NIM, and Vertex AI via server-side vectorize
8.6

Serverless vector and document database for production RAG and AI agents

Freemium· Free tier with generous monthly credits; Pay-as-you-go serverless consumption pricing (compute + storage + data transfer); Provisioned Capacity Units (PCUs) for predictable workloads; Enterprise plans with committed spend and private deployment options.RAG chatbot over enterprise documentsAgent long-term memory store

MongoDB Atlas Vector Search

RAG · Bring-your-own embeddings (OpenAI, Cohere, open models); native Voyage AI embeddings and rerankers
8.6

Vector search built into the operational database you're already using.

Freemium· Free M0 shared cluster / Pay-as-you-go on dedicated Atlas clusters (compute + storage + optional Search Nodes) / Enterprise Advanced self-managed licensingRAG over enterprise documentsProduct and content recommendation engines