Open Source MCP Server

Your AI already knows
what you care about.

Persnally is an MCP server that learns from your conversations with Claude. It builds a private interest graph and sends you a personalized digest — no setup, no surveys, just chat.

claude desktop

you: I'm building a real-time data pipeline with Kafka and Rust. Trying to decide between rdkafka and kafka-rust...

claude: Let me compare both libraries for your use case...

persnally tracked: Rust async programming (0.9), Kafka data pipelines (0.8), systems architecture (0.5)

No raw messages stored. Only structured signals.

How It Works

Persnally runs silently alongside your AI conversations. No behavior change required.

01

Install the MCP server

One npm install, add to your Claude Desktop config. Takes under 2 minutes. Persnally runs locally on your machine.

02

Chat like you normally do

As you discuss topics with Claude, Persnally extracts structured signals — topics, intent, sentiment, depth. Claude IS the NLP engine.

03

Get your personalized digest

Daily or weekly, Persnally curates content matched to your interest graph and sends it via email. Real links, real articles, zero filler.

The key insight

Every other recommendation engine asks you to fill out surveys, rate things, or connect accounts. Persnally doesn't need any of that.

When you talk to Claude about Rust async programming, startup fundraising, or LLM fine-tuning — Claude already understands the context, sentiment, and depth. Persnally just gives it a structured way to report what it observed. Zero extra AI cost. Zero NLP pipeline.

Your conversations are the most honest signal of what you care about. Not what you say you like — what you actually spend time on.

A living interest graph

Not a static preference list. A weighted, decaying, sentiment-aware graph that evolves as you do.

Exponential Decay

Topics you discussed months ago fade naturally. What you talked about yesterday carries more weight. 7-day half-life keeps the graph fresh.

Sentiment Awareness

"I hate CSS" and "I love CSS" are very different signals. Negative sentiment deprioritizes topics — no frustrated content in your digest.

Depth Scoring

A brief mention of React scores differently than a 30-minute deep dive on React Server Components. Depth matters.

Balanced Allocation

Your digest covers multiple interest categories proportionally. No echo chambers — technology, business, career, science all get fair weight.

Topic Normalization

"React.js", "React JS", and "ReactJS" all map to the same node. The graph handles synonyms so you get clean, deduplicated interests.

Intent Tracking

Are you learning, building, researching, or debugging? Intent shapes what content gets surfaced — tutorials vs deep dives vs release notes.

Privacy by architecture

Not privacy by policy. By architecture. Raw conversations never leave your machine.

What IS stored

  • +Topic name (e.g., "Rust async")
  • +Weight (0.1 to 1.0)
  • +Category, intent, sentiment
  • +Entity names (e.g., "tokio", "axum")

What is NEVER stored

  • ×Your messages or conversations
  • ×Claude's responses
  • ×Code snippets or file contents
  • ×Personal information or secrets

Your interest graph is a JSON file on your machine. You can read it, edit it, or delete it anytime.
Use persnally_forget to remove any topic, or clear everything.

Get started in 2 minutes

Install the MCP server and add it to Claude Desktop.

1. Install globally
$ npm install -g persnally
2. Add to Claude Desktop config
{
  "mcpServers": {
    "persnally": {
      "command": "persnally",
      "args": []
    }
  }
}
3. Set your email
Tell Claude: "Set my Persnally email to me@example.com"
4. Just chat

That's it. Persnally will start learning from your conversations automatically. Ask Claude "show my Persnally interests" anytime to see what's been tracked.

5 tools, zero complexity

Persnally exposes 5 MCP tools that Claude calls automatically during your conversations.

persnally_track

Extracts topics, intent, and sentiment from the current conversation. Called automatically by Claude.

persnally_interests

Shows your current interest profile — what Persnally has learned, grouped by category.

persnally_digest

Generates and sends your personalized digest email based on your interest graph.

persnally_config

Set your email, digest frequency (daily/weekly), and API preferences.

persnally_forget

Remove a specific topic or clear all data. Your data, your control.

Open source. Local first. Yours forever.

Persnally is fully open source under MIT. Your interest graph lives on your machine. No vendor lock-in, no data silos.