MCP Server

Your memory and knowledge, in every AI client.

Akumi speaks MCP. Connect Claude Desktop, Claude Code, or any MCP client and it can recall, store, and search your organization's memory and knowledge, over OAuth and scoped to one organization. Every call is metered, audited, and held in the EU.

Start free Read the docs

one OAuth connection · scoped to one org · every call audited

Claude, or any MCP client

Connected

api.akumi.cloud/mcp

Acme GmbH

EU-resident

Authorized at consent · bound to one organization

Tools

recall

read

remember

write

forget

write

knowledge.search

fail-closed

metered · audited · EU-resident

AI clients are hungry for context. Your data is regulated.

Your team lives in Claude and other AI clients now, and they are most useful when they know your context: the past decision, the house fact, the document that answers the question. The easy way to give them that context is to paste it in, or wire up a memory server that hands your data to whatever connects, wherever it happens to run. For a regulated EU team, that is an unlogged transfer waiting to happen. You want the assistant to remember. You cannot afford for it to remember somewhere you cannot see.

Governed memory, over a protocol clients already speak.

MCP is the open protocol Claude and other clients use to reach external tools. Akumi implements it as a server, so connecting is a standard OAuth flow and everything behind it is the same governed Memory and RAG your API already uses.

Recall, remember, and forget Clients read and write your organization's long-term memory through the recall, remember, and forget tools. The same governed store as the API, injected before anything leaves the region.
Search your knowledge, fail-closed The knowledge.search tool answers from your EU-resident collections. It stays shut unless the organization firewalls personal data or has accepted external processing, so knowledge never leaves the EU by accident.
One OAuth connection, scoped to an org Connecting is Dynamic Client Registration plus OAuth 2.1. The user picks one organization at consent, and the token is bound to it. Switching organizations means reconnecting, on purpose.

terminal MCP over HTTP

$ claude mcp add --transport http \ akumi https://api.akumi.cloud/mcp

Authorize in the browser, pick your organization, and the client discovers the tools:

recall read a fact from memory

remember store a fact in memory

forget remove a fact from memory

knowledge.search search EU-resident collections

Governed the same way, everywhere.

Metered and audited

Every recall, write, and search is metered on its own line and written to the audit trail, with the client and the acting user recorded. The MCP surface is not a side door.

Scoped to one organization

A connection is bound to the organization chosen at consent. A client only ever sees that organization's memory and knowledge, never another tenant's.

EU-resident by default

Personal facts and knowledge stay in the region. The consent screen names the transfer and the egress guard enforces it, the same as the rest of the platform.

Not just another memory server.

Anyone can stand up an MCP server that stores text. The question a regulated team has to answer is where that text goes and who can prove it.

Consent is the transfer control The user authorizes one organization on a screen that names the transfer, not a token pasted into a config file with no record.
Knowledge egress fails closed knowledge.search stays shut unless the data is firewalled or external processing is accepted. No silent leak of your knowledge base.
Same governance as the API Entitlements, metering, audit, and residency come from the same services your inference already uses. One set of rules, not two.
Provable A metadata-only trail records which client called which tool, for which organization, and when. Hand the reviewer the log.

Bring your memory to your AI client.

Create a key, enable Memory, and connect Claude in a couple of minutes.

Start free Read the docs