Kernal Mcp
This is a local-first knowledge graph that treats conversation as structured data. It exposes 13 MCP tools for Claude to extract people, organizations, activities, and action items from natural language and store them in a local SQLite database. The pattern is clever: you tell Claude about a meeting, it calls kernal_remember with the raw text, then Claude decides what entities to extract and calls structured write tools like kernal_add_person and kernal_add_org. Entity resolution with fuzzy matching prevents duplicates. Query tools like kernal_context give you full briefings on contacts and companies, kernal_actions surfaces follow-ups, and kernal_recall searches everything. Reach for this if you want to build a personal CRM from conversational updates without sending data to a third party service.
- GitHub stars
- 2
- tools
- 13
- transport
- STDIO
- last updated
- May 28, 2026
Tools
13 toolsPublic tool metadata for what this MCP can expose to an agent.
kernal_rememberStore raw text, get extraction instructions and existing entity list for dedup
Store raw text, get extraction instructions and existing entity list for dedup
No parameter schema in public metadata yet.
kernal_add_personCreate or update a person (auto-deduplicates by fuzzy name match)
Create or update a person (auto-deduplicates by fuzzy name match)
No parameter schema in public metadata yet.
kernal_add_orgCreate or update an organization (auto-deduplicates)
Create or update an organization (auto-deduplicates)
No parameter schema in public metadata yet.
kernal_add_activityLog an interaction with participant and org linking
Log an interaction with participant and org linking
No parameter schema in public metadata yet.
kernal_add_actionCreate a follow-up or task, optionally assigned to a person
Create a follow-up or task, optionally assigned to a person
No parameter schema in public metadata yet.
kernal_linkCreate a relationship between any two entities (person, org, or topic)
Create a relationship between any two entities (person, org, or topic)
No parameter schema in public metadata yet.
kernal_recallSearch the knowledge base by keyword across all entity types
Search the knowledge base by keyword across all entity types
No parameter schema in public metadata yet.
kernal_peopleList/search contacts — filter by name, org, role
List/search contacts — filter by name, org, role
No parameter schema in public metadata yet.
kernal_orgsList/search organizations — filter by type, industry
List/search organizations — filter by type, industry
No parameter schema in public metadata yet.
kernal_activitiesRecent interactions — filter by type, person, date
Recent interactions — filter by type, person, date
No parameter schema in public metadata yet.
kernal_actionsOpen follow-ups — filter by status, owner, due date
Open follow-ups — filter by status, owner, due date
No parameter schema in public metadata yet.
kernal_contextFull briefing on a person or org — timeline, network, topics
Full briefing on a person or org — timeline, network, topics
No parameter schema in public metadata yet.
kernal_correctUpdate fields, delete entities, merge duplicates, or reset the database
Update fields, delete entities, merge duplicates, or reset the database
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
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)
Details
- Repository
- github.com/pintomatic/kernal
- Categories
- AI & LLM Tools, Documents & Knowledge
- Package
kernal-mcp- Transport
- STDIO
- Registry
- MCP registry, active
Related AI & LLM Tools MCP servers
View all
Sprintrasprintra-io/sprintra-mcpThe project brain for AI coding agents — memory, decisions, sprints, knowledge base via MCP.2stars
fmrltoogreatwtf/fmrl-pluginYour agent's outbox. Ask it to publish to fmrl and get a shareable link, no account required.0stars
Redis MCP Serveryawlabs/redis-mcpRead-first Redis MCP: SCAN key explorer, keyspace/TTL/memory/slowlog stats, DBA advisor2stars
Whisper Mcpjwulff/whisper-mcpLocal audio transcription using whisper.cpp. Transcribe with OpenAI Whisper models.2stars
Mcp Christensenm2ai-mcp-servers/mcp-christensenClayton Christensen persona agent for strategic advisory using disruption theory2stars
Nota Fiscalmcp-dir/notafiscal-mcpIssue and manage Brazilian service invoices (NFS-e) by chatting with your agent, platform-hosted, no2stars