add_knowledgeLABSCO SUMMARY
Knowledge and voice are stored as different things.
That separation is the design decision worth understanding: a meeting transcript is what you know, your email style is how you say it, and a good follow-up email needs both. search_for_creation returns them as separate result sets for exactly that reason, which a single similarity search cannot do.
What it is
A hosted MCP server holding a personal RAG database with semantic search that you shape from conversation: you define the types and tags, store knowledge and voice separately, and retrieve either with the source cited. Two layers sit behind it — Postgres via Supabase for structured records with provenance, Pinecone for the vector embeddings.
What you get
- Storing (5) —
add_knowledge,add_voice_note,add_documentwith automatic chunking,add_from_url,add_reference_record - Retrieving (5) —
search_twinacross all knowledge,search_for_creationwhich returns skills and knowledge as separate result sets,get_by_type,get_by_tag,list_recent - Understanding (4) —
get_schemafor your types and item counts,get_sources,find_patternsfor recurring themes,synthesiseacross items on a topic - Managing (5) —
get_welcome,update_knowledge,add_schema_type,update_schema_type,delete_knowledge - Of the 19: 10 read-only, 8 write, and 1 destructive —
delete_knowledge. Every tool carriestitle,readOnlyHintanddestructiveHintannotations - Every result is cited with source and date and tagged personal, organisational or external
Requirements
An account at https://myaitwin.lutolearn.com, then either the personal MCP URL from /create pasted into your client as a custom connector, or the canonical endpoint https://myaitwin.lutolearn.com/mcp. Transport is Streamable HTTP; authentication is OAuth 2.1 with PKCE (S256) and dynamic client registration, with bearer tokens hashed at rest. A client with MCP capability is needed — the README names Claude Pro, Claude Team and ChatGPT Pro. Each account lives in its own namespace with rate limiting per tenant and an append-only audit log on every tool call. Free during early access.
Setup effort
Add the hosted endpoint plus credentials — paste it into your client, then supply credentials
USE CASES
01
Drafting something that sounds like you wrote it
Retrieve the relevant knowledge and your voice separately, then let the model use both.
02
Capturing what you know as you work
Store typed, tagged items, a voice note, a long document or a web page.
03
Making sense of what has accumulated
Surface recurring patterns and synthesise across items on one topic.
04
Shaping the structure to your own work
Define new knowledge types and update existing ones as your thinking changes.
19 tools
Listed in project docs. Your client may show a different list.
add_voice_noteadd_documentadd_from_urladd_reference_recordsearch_twinsearch_for_creationget_by_typeget_by_taglist_recentget_schemaget_sourcesfind_patternssynthesiseget_welcomeupdate_knowledgeadd_schema_typeupdate_schema_typedelete_knowledgeBEFORE YOU INSTALL
What to know first
Tools you get
19 tools named in the project's documentation. Of the 19, 10 read, 8 write and 1 is destructive.
Requires
- Sign up at https://myaitwin.lutolearn.com/ with your email
- a client with MCP capability
INSTALLATION
Connect your client
Paste it into your client, then supply credentials.
Server setup
Setup
Sign up at https://myaitwin.lutolearn.com/ with your email.
Click the magic link, then copy your personal MCP URL from /create.
In Claude Desktop: Settings → Connectors → Add custom connector → paste your URL.
Hosted endpoint
ENDPOINT URL
https://myaitwin.lutolearn.com/mcpAdd this hosted endpoint to your MCP client using the credentials listed under Requirements.
