MCP App Store
by KeenEthics
Empirical Memory icon

Empirical Memory MCP Server for ChatGPT

By Empirical

Overview

Memory Infrastructure For AI Memory that follows you everywhere. Own your AI memory. Empirical gives AI systems persistent memory across tools and sessions. It stores events, entities, goals, and reflections as connected nodes so context stays portable instead of being locked to one model or one chat.

How to connect

  1. ChatGPT: Open the Empirical Memory listing in the ChatGPT app directory and choose Connect. ChatGPT listing Empirical Memory exposes 38 tools here.

Tools

acknowledge_reminder

ChatGPT
Close a reminder the user has seen: marks the memory's reminder acknowledged (or cancelled) and clears its alerts across surfaces, stopping further pending reminder delivery. This closes alert state and has no undo operation in this tool. Call only when the user says the reminder is done, handled, or no longer needed. The memoryId is in the reminder notice; the stored memory content is preserved.

add_note_by_query

ChatGPT
Append a note to an existing stored memory resolved by semantic query or explicit memoryId. Memory-editing only; not for external information tasks.

attach_file_to_memory

ChatGPT
Attach a file to a memory (25MB per file, 20 files per memory). Give ONE of: url, a public https:// URL the server fetches and stores, for a file that lives on the public web; or content, the file's text, for a file you produced yourself (an HTML page, a markdown document, JSON, code), up to 1MB, with mimeType and filename. It cannot take binary bytes as an argument, and it cannot read a local path: a file on the user's own machine is attached with the CLI instead, empirical memory attachment add --memory-id <id> --file <path>. Attachments need a paid plan.

claim_blueprint

ChatGPT
Claim entitlement to a free blueprint. Required before installing, unless you use install_blueprint, which claims automatically for free blueprints.

confirm_guided_setup

ChatGPT
Confirm and install a guided interview that ends with a draft to review (the Writing Voice setup). Pass the draftHash that came with the draft the person just reviewed. This writes memories to their workspace and replaces their previous voice once the install succeeds, so call it only after you have shown them the draft and they clearly said yes. It fails if the draft changed after they saw it.

continue_guided_setup

ChatGPT
Record the answer to the current question (if any) and return the next question, or completion with an installId once every question is answered.

create_workspace

ChatGPT
Create a new shared workspace. Use this when the person asks you to set up a workspace, a board, a pipeline or a tracker. It is created EMPTY, with no kinds of item: call set_workspace_shape next to decide how it is organised. It does not switch the current workspace; use set_current_workspace for that. If the plan does not allow another workspace, the call is refused and the error says why.

delete_memory_attachment

ChatGPT
Delete one file from a memory. This is a soft delete: the file stays restorable for 30 days with restore_memory_attachment, and the response says the date its bytes get purged. Requires confirm=true, and the user must have asked for the file to be deleted.

delete_memory_by_query

ChatGPT
Delete a stored memory resolved by semantic query or explicit memoryId (requires confirm=true). Use only when user explicitly asks to remove their memory.

finish_guided_setup

ChatGPT
End a guided interview before every question is answered. Unanswered slots use their defaults. Triggers install.

get_blueprint

ChatGPT
Full detail for one blueprint: description, outcomes, compatibility, node/relationship estimates, and whether you own/have installed it.

get_blueprint_install_status

ChatGPT
Poll the status of an install. Use this if install_blueprint returned jobStatus "running" (still installing past its own bounded wait).

get_current_workspace

ChatGPT
Get current workspace selection for this OAuth client.

get_empirical_policy

ChatGPT
Read the authenticated user's normalized Empirical behavior policy. This is read-only and reflects the current installer/settings preferences.

get_memory

ChatGPT
Retrieve a specific memory by ID. Returns the full summary and notes; use it when a query result shows summaryTruncated.

get_memory_attachment

ChatGPT
Read one file attached to a memory. A text file (html, markdown, json, csv, code, plain text) comes back in full in the result, up to maxInlineBytes (default 512KB, at most 1MB). An image comes back as an image. Anything else, or anything larger, comes back as metadata plus a download link that works for ten minutes and a resource URI you can read with resources/read. Find the attachmentId with list_memory_attachments. Identify the memory by memoryId, or by a query that resolves to exactly one memory.

get_memory_neighbors

ChatGPT
Get related memories and edges for a memory node (incoming, outgoing, or both).

get_memory_tree

ChatGPT
Get one item and every item nested under it, at any depth, as a readable markdown document plus the list of nodes. Use this instead of walking the graph with get_memory_neighbors when you want a whole idea with its sub-ideas: it returns the complete subtree in one call, in the order the tree is arranged. Items nest only in a workspace that has a shape; for an ordinary memory this returns just that memory.

get_user

ChatGPT
Get the authenticated Empirical profile/account context for the connected user. Not a source for weather, web facts, or general knowledge.

install_blueprint

ChatGPT
Install a blueprint into your memory graph. Automatically claims first if the blueprint is free and not yet owned. Waits for the install to finish (up to ~20s) and returns the final status.

list_blueprints

ChatGPT
Browse the blueprint catalog. Returns a compact summary per blueprint (not full detail — use get_blueprint for that). Optionally filter by category.

list_guided_setups

ChatGPT
List available guided-interview blueprint setups. Locked entries require a paid plan.

list_installed_blueprints

ChatGPT
List every blueprint currently installed for you, with node/relationship counts and whether an update is available.

list_memories

ChatGPT
List memories to review and pick targets for follow-up actions. Use this for recent/latest/today requests; follow nextCursor while hasMore is true.

list_memory_attachments

ChatGPT
List the files attached to a memory, with filename, size, type and upload date. Identify the memory by memoryId, or by a query that resolves to exactly one memory. Set includeDeleted to also see files that were deleted but are still inside the 30-day restore window, each with the date its bytes get purged.

list_workspaces

ChatGPT
List selectable workspaces for this OAuth client (Default Brain first).

memory_usage_guide

ChatGPT
Read the memory usage policy for when to create, query, update, or delete memories.

preview_blueprint_install

ChatGPT
Preview what installing a blueprint would create: node/relationship counts and duplicate-candidate count against your existing memories.

query_memories

ChatGPT
Search previously stored personal memories by semantic query and/or filters (category, tags, dates, location, graph fields). Use only when the user asks about their saved context; not for weather, web lookup, or general knowledge.

record_graph_memory

ChatGPT
Create or merge user memory from conversation context (journal notes, preferences, plans, reflections, and ongoing personal/project context). Not intended for one-off calculations, general knowledge answers, weather, or web lookup results.

restore_memory_attachment

ChatGPT
Restore a file that was deleted from a memory, if it is still inside the 30-day retention window. Find the id with list_memory_attachments and includeDeleted set to true.

set_current_workspace

ChatGPT
Set current workspace selection for this OAuth client.

set_workspace_shape

ChatGPT
Give a workspace its kinds of item, their stages and their fields, which is what turns it from a list of memories into a board or a pipeline. ASK THE PERSON WHAT THEY TRACK AND SHOW THEM THE PLAN BEFORE CALLING THIS: a kind of item takes its permanent key from its singular label, and later you can ADD kinds, stages and fields but never remove one. Only for a workspace that has no shape yet. After this, pass itemType when recording memories here, because nothing is classified automatically from the caller's side.

start_guided_setup

ChatGPT
Start a guided interview for a blueprint. Returns the first question and a sessionId.

uninstall_blueprint

ChatGPT
Uninstall a blueprint. Untouched memories are deleted; anything you edited is preserved (detached from the blueprint, not deleted).

update_blueprint

ChatGPT
Update an installed blueprint to a newer version when requested by the user. Untouched memories from the old version are removed from active recall along with graph edges to those memories; anything you edited is preserved (detached from the blueprint). This tool has no undo operation for the removed memories or edges.

update_memory_by_query

ChatGPT
Update an existing stored memory resolved by semantic query or explicit memoryId. Memory-editing only; not for external information tasks.

update_memory_relationships

ChatGPT
Add, remove, or replace relationships on a memory node accessible in the current workspace. Removal discards matching edges; replace=true overwrites the entire relationship list. This tool has no undo operation. Use only for relationship changes requested by the user.

Capabilities

WritesInteractive

Example Prompts

Click any prompt to copy it.

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/empirical"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/empirical)