Skip to content

Interface independence

Use Kelven
or bring Kelven with you.

The Kelven MCP Gateway lets a compatible AI application ask Kelven for context, under permissions you approve. Your memory, preferences and privacy rules stay in one place, whichever interface you happen to be using.

Six read-only capabilities

Safe outcomes, not database access.

Each capability answers a narrow question. None of them can change anything, and none of them will hand over your account wholesale.

Search memory

Find the few records relevant to a question. There is no capability that returns everything.

Get the context a task needs

The signature capability: state the task, receive the minimum context for it — not a profile.

Search projects

Find a project by name or description.

Get project context

One project's summary and the records attached to it, nothing further.

Read preferences

How you like answers written, formatted and delivered.

Read privacy rules

The limits Kelven enforces, so an assistant knows what it may not ask for.

The pipeline

Every request passes through six stages.

  1. 01 · Authorization

    You approved this application, and only the permissions shown.

  2. 02 · Relevance

    Only records related to the stated task are considered.

  3. 03 · Sensitivity filter

    Local-only records stop here. So does anything you excluded.

  4. 04 · Minimization

    What remains is trimmed to the few records the task needs.

  5. 05 · Tokenization

    Names, companies, amounts and addresses become typed placeholders.

  6. 06 · Result

    The assistant receives context plus a plain summary of what was withheld.

Local-only memory

Some memory never leaves your device. Ever.

A record you mark local-only cannot be returned through the Gateway. Not tokenized, not summarised, not "just this once". A connected application is told plainly: requested memory is stored locally and is not available to connected applications.

Kelven will never quietly upload local memory to make a connection work.

What this is not

Kelven controls what Kelven shares.

If you type a client's real name straight into another AI application, that application has it — Kelven cannot reach back and conceal it. What Kelven guarantees is narrower and real: everything that leaves Kelven has been minimized and tokenized first.

We also don't claim to work with every AI. The Gateway works with compatible MCP clients, and we only describe a host as verified once we've tested it end to end.

Compatibility matrix

Tested honestly, labelled honestly.

InterfaceStatus
Kelven appComplete experience
ClaudeIn testing
ChatGPTExperimental
Other MCP clientsCompatible

Nothing is marked Verified yet. Statuses change only after real end-to-end testing.

What is MCP?

The open standard behind the Gateway, in plain language.

Read the explainer

What an MCP server does

How a server exposes capabilities, and why narrow beats broad.

Read the explainer

See also how the privacy gateway minimizes every request.

The future isn’t another AI model. It’s an intelligence layer that’s yours.

Kelven is the user-controlled intelligence layer between you and AI — with one memory that’s always yours.

No spam. Just one note when early access opens.