# Ontoflow

> Ontoflow is a freemium MCP server for knowledge and memory. Query a knowledge graph of your notes, with contradictions and gaps, in your own database. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Freemium
- **Starting price:** $15 a month
- **Platforms:** Web, API
- **Website:** https://ontoflow.app
- **Repository:** https://github.com/moayo-app/ontoflow-obsidian
- **MCP Registry name:** io.github.Moayo-app/ontoflow
- **Categories:** knowledge and memory
- **Listing updated:** 2026-11-14

## About

The engine reads notes, extracts concepts, decisions and relations using a closed set of verbs such as supports, contradicts, is part of and causes, and builds a graph. What it surfaces are findings rather than a chat: two notes that contradict each other, a concept with many links but no note explaining it, and the same idea written in two places. These land in a weekly report and a review inbox, and nothing is applied until you accept it. Judgments you make are kept and are not overwritten when notes are re-extracted.

The graph lives in SQLite inside your Obsidian vault or in a PostgreSQL you own, and can be exported as JSON-LD or GraphML. Processing is hosted with zero data retention by default, or you can bring your own local model endpoint such as Ollama, vLLM or LM Studio. Other note sources, such as Logseq, Bear, Evernote and Google Drive, can be connected.

The remote MCP connection is the part this server provides, letting Claude or GPT read your graph. The pricing page puts remote MCP on the Pro and Team Standard plans, and says MCP reads cost no credits. The site notes it is preparing for release to the Obsidian plugin marketplace.

## Features

- **Contradiction and gap insights:** Finds conflicting notes, under-explained concepts and duplicated ideas.
- **Review inbox:** Every machine suggestion waits for your accept or reject.
- **Your own database:** Graph stored in local SQLite or your PostgreSQL, exportable as JSON-LD or GraphML.
- **Local-model option:** Use your own Ollama, vLLM or LM Studio endpoint so note content stays on your machine.
- **Expert finder:** Shows team members who marked knowledge on a topic as shared.
- **MCP access:** Lets external AI clients query the graph.

## Good for

- Find contradictions between notes in an Obsidian vault
- Give Claude or GPT memory that stays in a database you own
- Locate the teammate who knows about a topic
- Review a weekly report of gaps in team documentation

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http ontoflow https://hub.ontoflow.app/v1/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://hub.ontoflow.app/v1/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "ontoflow": {
      "url": "https://hub.ontoflow.app/v1/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "ontoflow": {
      "type": "http",
      "url": "https://hub.ontoflow.app/v1/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "ontoflow": {
      "serverUrl": "https://hub.ontoflow.app/v1/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "ontoflow": {
      "type": "http",
      "url": "https://hub.ontoflow.app/v1/mcp"
    }
  }
}
```

## FAQ

### Where is my data stored?

In local SQLite inside your vault or in your own PostgreSQL; export to JSON-LD or GraphML is free.

### Is there a free plan?

Yes: one initial index, 30 credits a month and a weekly report, with no time limit.

### Which plan includes remote MCP?

Pro at $29 a month, or Team Standard and above for workspaces.

### Can notes stay local?

Yes, by pointing to your own local model endpoint.

### Is Ontoflow free?

Ontoflow has a free plan, with paid plans for more usage or features. Paid plans start at $15 a month.

### How do I add Ontoflow to Claude Code?

Run this command in your terminal: claude mcp add --transport http ontoflow https://hub.ontoflow.app/v1/mcp

### What are the best alternatives to Ontoflow?

The closest alternatives to Ontoflow are Codebase Memory, XERJ, Claude Code Ultimate Guide, Nautilus Compass Memory and note1.

## Alternatives

- [Codebase Memory](https://ai-powered.com/mcp/codebase-memory): Codebase Memory is an open-source MCP server for knowledge and memory.
- [XERJ](https://ai-powered.com/mcp/xerj): XERJ is an open-source MCP server for knowledge and memory.
- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.
- [Nautilus Compass Memory](https://ai-powered.com/mcp/nautilus-compass-memory): Nautilus Compass Memory is an open-source MCP server for knowledge and memory.
- [note1](https://ai-powered.com/mcp/note1): note1 is an MCP server for productivity.
- [MedXpert 图书馆连接器（通用版）](https://ai-powered.com/mcp/medxpert): MedXpert 图书馆连接器（通用版） is an open-source MCP server for knowledge and memory.
- [Context Nest](https://ai-powered.com/mcp/context-nest): Context Nest is a freemium MCP server for knowledge and memory.
- [Tulsa Ecosystem Map](https://ai-powered.com/mcp/tulsa-ecosystem-map): Tulsa Ecosystem Map is a free MCP server for knowledge and memory.

---
Source: https://ai-powered.com/mcp/ontoflow
