Integration

Mem integration

Mem is an AI note-taking workspace. Capture raw text with Mem It (Mem turns it into an organised note), create, read, update, trash, restore and delete markdown notes, list notes with date and content filters, run free-text searches, find semantically related notes, and organise notes into collections (create, rename, add, remove or move notes, search collections). Calendar, MCP, agent chat, attachment, session and legacy v0/v1 routes are not exposed. Authentication is a Mem API key, created in the API section of the Mem settings, sent as a Bearer token in the Authorization header.

Connect Mem How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Mem.Built from the 20 Mem tools below, on the connection you add once.

What you can do with Mem

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Note, 7 operations

add_note_to_collectionAdd note to collectionPUTAdd an existing note to an existing collection. Only creates the membership link; the note and collection contents are unchanged.
create_noteCreate notePOSTCreate a markdown note; the first line of content becomes its title. Returns the note id and version (pass both to update_note). Optionally link it to collections by id or title.
delete_noteDelete noteDELETEPermanently delete a note. Hard-deleted notes cannot be restored. For recoverable removal, use `trash_note`.
get_noteGet noteGETGet one note by id with its full markdown content, title, collection ids, attachment metadata and version (the version update_note needs). A trashed note is still returned, with trashed_at set.
list_notesList notesGETList notes with cursor pagination, ordered by updated_at (default) or created_at. Pass the returned next_page as page for the next page. Set include_note_content=true for full markdown; otherwise results carry snippets.
remove_note_from_collectionRemove note from collectionDELETERemove a note from a collection; both the note and the collection are kept.
update_noteUpdate notePATCHReplace a note's whole markdown body. Pass the full desired content (not a partial patch) and the exact version from get_note or the last write. A trashed note must be restored with restore_note first.

Collection, 5 operations

create_collectionCreate collectionPOSTCreate a collection (a named group of notes) with a title and optional description. Returns its id, which add_note_to_collection and create_note take. A caller-provided id that already exists returns a conflict.
delete_collectionDelete collectionDELETEPermanently delete a collection. To only unlink a note from it, use remove_note_from_collection instead.
get_collectionGet collectionGETGet one collection's metadata by id: title, description, note count and timestamps. It does not list the notes; use list_notes with collection_id for that.
list_collectionsList collectionsGETList collections (id, title, description, note count) with cursor pagination. Pass the returned next_page as page to get the next page. For relevance-ranked lookup by text use search_collections.
update_collectionUpdate collectionPATCHRename a collection or change its description. Only the fields you pass change; leave one out to keep its current value.

Search, 2 operations

search_collectionsSearch collectionsPOSTSearch collections by free-text relevance, with optional date filters. Returns a bounded ranked list with no pagination; use list_collections to page through every collection.
search_notesSearch notesPOSTSearch notes by a required free-text query, with optional date, collection and content filters. Relevance-ranked within a 100-result window; for later pages pass the returned snapshot_id with offset.

Created at, 1 operation

set_note_created_atSet note created atPATCHBackdate a note's visible creation timestamp without changing its content. The new created_at needs a timezone offset, cannot be in the future, and cannot be later than when the note was originally created.

Mem it, 1 operation

mem_itMem itPOSTSend raw content (text, an email, a transcript, web page HTML) for Mem to process into organised notes in the background. Returns only a request_id; processing typically completes within minutes and its status cannot be tracked.

Move, 1 operation

move_note_to_collectionMove note to collectionPOSTMove a note from one collection to another: it is added to target_collection_id, then removed from the source collection. Contents are unchanged.

Related note, 1 operation

find_related_notesFind related notesGETFind notes semantically related to the current content of a note, each with a relevance score and snippet. Works on newly created or updated notes before indexing catches up.

Restore, 1 operation

restore_noteRestore notePOSTRestore a trashed note to the active notes, so it can be updated again. Only reverses trash_note; a note removed with delete_note cannot be restored.

Trash, 1 operation

trash_noteTrash notePOSTMove a note to trash (recoverable). Undo with restore_note; for irreversible removal use delete_note.

Use Mem from Claude Code, Cursor or Codex

Connect Mem in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Mem operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Mem

Create your workspace
Sign up free. Nothing to install.
Connect Mem once
Add your Mem connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.