Khint speaksboth directions
Your AI tools read the work session you are in right now. And the palette reaches into Jira, Confluence, Linear, Notion, Slack and Gmail, pulling work in and writing results back without you opening any of them. Every call leaves from your own machine.
Every integration,
in both directions
Some tools read Khint. Khint reads and writes the others. Each one has a page of its own with what it adds to the palette, how to connect it, and what it will refuse to do.
Use Khint in your AI tools3
Khint is an MCP server. Your assistant reads the session you are working in, and can write back into it.
Claude Desktop
Ask Claude what you are working on and it answers out of your live Khint session, with no pasting.
Codex
One config file covers the Codex CLI, the desktop app and the IDE extension. Same session, same five tools.
Any MCP client
The khint-mcp binary ships inside the app. Point any MCP-compatible client at it and you get the same five tools.
Pull your work into Khint6
Connect a tool once and its rows appear in the palette: pull an issue, a page or a thread into your session, and file the result back without leaving the app you are in.
Jira
Pull an issue, your active sprint or a JQL search into your session. Create issues, comment, change status.
Confluence
Pull a page into your session. Publish a new one, comment, or append to an existing page without touching what is already there.
Linear
Turn anything you have selected into a Linear issue with a written title and description, filed in your default team.
Notion
Create a page in your database, append to an existing one, or pull a page and a search into your session.
Slack
Post an update to a channel. Pull a channel, a thread or a search back into the session you are working in.
Soon
Gmail
Draft or send an email from what you selected, and pull a thread into your session. Sending always asks first.
On your Mac1
One companion that talks to an app on your machine rather than to an API.
The session in the middle
A pull is not a viewer and a write is not an export. Both ends meet in the work session Khint is already keeping, which is what turns six connectors into one loop.
The Slack thread you pulled is in your session, so the agent that drafts the ticket writes with it in hand, and the issue it files goes back into the same session as a receipt. Your AI client reads that session too, which is how Claude ends up knowing about a ticket nobody told it about.
Khint is itself an MCP server
How the server worksFive tools, over stdio
list_sessions, get_session, get_active_context, search_session_entries and add_session_entry. The binary ships inside the app, so any MCP-compatible client can use them.
Reads are read-only
The four read tools open the local database through a read-only handle. There is no code path from a read to a write, whatever a chat asks for.
Writes announce themselves
A write is proxied through a loopback server with bearer-token auth and a 60-per-minute limit, then raises an OS notification and lands in an audit log. Nothing is injected into your memory silently.
Connectors that run on your Mac, not on ours
Every hosted automation platform has to hold your credentials, because it calls your tools while your laptop is shut. Khint calls them while you are there, which removes the reason to hold anything.
A hosted connector platform
- Your tokens live on their infrastructure, because they have to
- An admin connects it once, for everyone, at workspace scope
- Their outage is your integration's outage
- What it read and when is something you have to trust
- Access is re-mapped from your tools, and re-mapping can be wrong
Khint
- Tokens in your operating system's keychain, on your machine
- You connect your own account, with your own permissions
- Nothing between your Mac and Jira, so nothing else to be down
- It calls a tool when you press a row, and never otherwise
- Nothing to re-map: it reaches exactly what you can already open
The rest of Khint
Integrations are where the work comes in and goes out. These three are what happens in between.
Common questions about Khint's integrations
Do these integrations run on Khint's servers?
No, and that is the whole design. Every credential goes into your operating system's keychain and every call goes from your Mac straight to Jira, Slack or Notion. Khint's backend never holds a token, never proxies an integration call, and has no connector infrastructure to breach. A hosted automation platform works the opposite way: it stores your credentials so it can call your tools while your laptop is closed.
What can my AI assistant actually see?
Your Khint work sessions, and only those: the list of them, one by id, the live compacted state of the active one, and a search across their entries. Claude Desktop and Codex do not get a Jira tool or a Slack tool. If they see a ticket, it is because a palette row pulled it into your session first.
Does connecting a tool copy my data anywhere?
Not by default. A pull lands in a local Memory session, which lives in a SQLite file on your Mac and is never synced. If you switch Knowledge on for Jira, Confluence, Notion or Linear, Khint keeps a full-text index of those tools, still on your machine and still never on our servers. Turning a source off deletes its copy on the spot.
Do I need an admin to install any of this?
For Jira, Confluence, Linear and Notion, no: you create a personal token or an internal integration on your own account and it carries your own permissions. Slack asks for a small app of your own, which some workspaces require an admin to approve. Claude Desktop and Codex need nothing at all beyond Khint itself.
What does an integration cost to run?
The API calls are free: pulls, searches and every picker make no AI call at all. What costs is the writing, when a row hands your selected text to an agent to turn it into an issue, a page or an update. That is one normal agent run against your monthly credits, the same as any other action.
What happens when I turn an integration off?
It pauses. The rows leave the palette, workflows stop using it, and the credentials stay in your keychain for an instant reconnect. Clearing them is a separate, deliberate two-click Forget credentials button, and for the four indexed tools it also deletes their local Knowledge copy.
Connect the tools you already have open
Free with 300 credits a month. No credit card. macOS 13+ or Windows 10 22H2+.