How do I install Kernal?

Copy the stdio config for Cursor, Claude Desktop, Claude Code, or VS Code on this page. It uses the publisher's install, not a PlugMCP proxy.

Does Kernal need an API key?

No required environment variable is listed on this record.

What transport does Kernal use?

Kernal runs locally over stdio.

When was Kernal last checked?

Last checked 2026-11-10. Graph-native memory for AI agents: a knowledge graph built from conversation, via MCP.

Kernal MCP server

Power your agent

Add this server

The publisher's own command. Not a PlugMCP endpoint.

Add to Cursor Add to VS Code Run on PlugMCP

Host a copy with our keys and logs.

Local command

npx -y [email protected]

Claude Code has no install link for a local command. Copy the command below and run it in a terminal.

shClaude Code

1claude mcp add io.github.pintomatic-kernal-mcp -- npx -y kernal-mcp@0.2.1

Run in a terminal.

jsonClaude Desktop

1{2  "mcpServers": {3    "io.github.pintomatic-kernal-mcp": {4      "command": "npx",5      "args": [6        "-y",7        "[email protected]"8      ]9    }10  }11}

claude_desktop_config.json

Local · npmPublisher installStep-by-step: add this in Claude

Remote URL or a command on your machine? How the two installs differ

Run on PlugMCP

Host a copy with our keys and logs.

A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.

Launch

Server facts

Local

Transport: stdio
Version: 0.2.1
Last checked

Tools

No tool list yet. Remote servers get one after the first health check.

FAQ

Questions

Kernal

Open-source knowledge graph for professionals. Auto-extracts entities and relationships from natural conversation via MCP.

Talk to Claude naturally about your meetings, calls, and interactions. Kernal stores people, organizations, topics, and relationships — building a knowledge graph you own.

What's Included (Open Source)

Everything you need to run Kernal locally on your own machine:

13 MCP tools — ingestion, CRUD, query, corrections (see full list below)
SQLite database — local-first, your data never leaves your machine
LLM-driven extraction — Claude reads your text, decides what to extract, and calls structured write tools
Entity resolution — fuzzy matching + Levenshtein distance prevents duplicates
CLI — init, serve, status, export
Cloud server — Express.js with API key auth, rate limiting, CORS, session management
Dashboard — React app with network graph, timeline, action items, overview
50 tests — comprehensive test suite

This is a fully functional knowledge graph you can run yourself, for free, forever.

What Andes Provides (Managed Service)

For teams and professionals who want more, Andes offers:

Cloud hosting — access your knowledge graph from any device, no self-hosting
Dashboard — hosted interactive visualizations powered by your data
Multi-user — team features, shared knowledge bases, role-based access
Onboarding & support — we set it up for you and help your team get value from day one
Industry workflows — pre-built patterns for executive search, consulting, professional services

The open-source core is the engine. Andes wraps it with infrastructure, UX, and support.

Quick Start

npx kernal-mcp init

This creates a SQLite database at ~/.kernal/kernal.db and prints the config to add to Claude Desktop.

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "kernal": {
      "command": "npx",
      "args": ["-y", "kernal-mcp", "serve"]
    }
  }
}

Restart Claude Desktop. Then talk naturally:

"I had lunch with Jonas Lindberg from Nordvik Energy today. He's their VP of Digital. We discussed their cloud migration — targeting Q3."

Claude extracts Jonas, Nordvik Energy, the cloud migration topic, and stores them via Kernal's write tools. Then ask:

"What do I know about Nordvik Energy?" → Full briefing with people, interactions, topics
"Who should I follow up with?" → Open action items with owners and due dates
"Show me everyone at Nordvik Energy" → Contact list filtered by organization

How It Works

Kernal uses an LLM-driven extraction pattern:

You tell Claude about a meeting, call, or interaction
Claude calls kernal_remember with the raw text
Kernal stores the text as a note and returns extraction instructions + existing entities (for dedup)
Claude reads the text intelligently and calls structured write tools (kernal_add_person, kernal_add_org, kernal_add_activity, etc.)
Each write goes through entity resolution to prevent duplicates
The LLM makes all extraction decisions — no regex guessing

The MCP server is a clean data store. The LLM is the brain.

MCP Tools

Ingestion (write)

Tool	Description
`kernal_remember`	Store raw text, get extraction instructions and existing entity list for dedup
`kernal_add_person`	Create or update a person (auto-deduplicates by fuzzy name match)
`kernal_add_org`	Create or update an organization (auto-deduplicates)
`kernal_add_activity`	Log an interaction with participant and org linking
`kernal_add_action`	Create a follow-up or task, optionally assigned to a person
`kernal_link`	Create a relationship between any two entities (person, org, or topic)

Query (read)

Tool	Description
`kernal_recall`	Search the knowledge base by keyword across all entity types
`kernal_people`	List/search contacts — filter by name, org, role
`kernal_orgs`	List/search organizations — filter by type, industry
`kernal_activities`	Recent interactions — filter by type, person, date
`kernal_actions`	Open follow-ups — filter by status, owner, due date
`kernal_context`	Full briefing on a person or org — timeline, network, topics

Corrections

Tool	Description
`kernal_correct`	Update fields, delete entities, merge duplicates, or reset the database

What Gets Stored

From a single paragraph like "Had coffee with Sofia Andersen from Arctura Tech. She's their VP of Sales. We discussed their expansion into APAC. I need to send her the partner proposal by Friday.", Claude will call:

kernal_add_person — Sofia Andersen, VP of Sales, at Arctura Tech
kernal_add_org — Arctura Tech
kernal_add_activity — Coffee meeting, today, participants: [Sofia Andersen], orgs: [Arctura Tech]
kernal_add_action — "Send partner proposal to Sofia", due Friday, owner: Sofia Andersen
kernal_link — Sofia → works_at → Arctura Tech

Each call is a deliberate, structured decision by the LLM — not a regex guess.

CLI Commands

kernal init      Create database + print Claude Desktop config
kernal serve     Start MCP server (stdio transport)
kernal status    Show database stats
kernal export    Export database to a file
kernal help      Show help

Dashboard

The repo includes a React dashboard (dashboard/) with four views:

Overview — entity counts, most connected people, activity breakdown
Network — interactive force-directed graph (people + organizations)
Timeline — chronological activity feed with participants and summaries
Actions — follow-ups grouped by urgency (overdue, this week, upcoming)

Natural language command bar routes queries to views ("Show me my network" → graph).

# Start the cloud API server
KERNAL_API_KEY=your-key KERNAL_DB_PATH=~/.kernal/kernal.db npm run cloud

# Start the dashboard (separate terminal)
cd dashboard && npm run dev

Data Model

Kernal stores 6 entity types connected by a generic relationship graph:

People ←→ Organizations
  ↕           ↕
Activities ←→ Topics
  ↕
Actions ←→ Notes

All entities can link to any other entity via the relationships table, enabling queries like:

"Who has Sofia met with?" (person → activities → other people)
"What topics come up with Nordvik Energy?" (org → people → activities → topics)
"What's the connection between Jonas and Arctura Tech?" (path through graph)

Security

All SQL queries use parameterized statements (no injection risk)
API key auth with constant-time comparison (crypto.timingSafeEqual)
CORS restricted to configured origins
Rate limiting (120 req/min per IP, configurable)
MCP session timeout (30 min idle eviction)
No secrets in code — all config via environment variables
React dashboard auto-escapes all rendered data (no XSS)

Development

git clone https://github.com/pintomatic/kernal.git
cd kernal
npm install
npm run build
npm test        # 50 tests

Self-Hosting the Cloud Server

KERNAL_API_KEY=your-secret KERNAL_DB_PATH=~/.kernal/kernal.db npm run cloud

A Dockerfile is included. Environment variables:

Variable	Default	Description
`KERNAL_DB_PATH`	`~/.kernal/kernal.db`	SQLite database path
`KERNAL_API_KEY`	(required for cloud)	API key for authentication
`KERNAL_CORS_ORIGIN`	`http://localhost:5174`	Allowed CORS origins (comma-separated)
`KERNAL_RATE_LIMIT`	`120`	Max requests per minute per IP
`PORT`	`3001`	Server port

Seed Demo Data

npx tsx scripts/seed-demo.ts

Creates 12 contacts, 18 orgs, 19 activities with 123 relationships — a realistic professional services scenario.

License

MIT

Add this server

Host a copy with our keys and logs.

Server facts

Tools

Questions

How do I install Kernal?

Does Kernal need an API key?

What transport does Kernal use?

When was Kernal last checked?

Documentation

Kernal

What's Included (Open Source)

What Andes Provides (Managed Service)

Quick Start

How It Works

MCP Tools

Ingestion (write)

Query (read)

Corrections

What Gets Stored

CLI Commands

Dashboard

Data Model

Security

Development

Self-Hosting the Cloud Server

Seed Demo Data

License