The context and accounts your agents need, in one place you own.
Lanes Link is a private, self-hostable MCP that connects your accounts, memory and skills to every AI agent you use, behind Access Profiles you manage.
How it works
Your accounts, your memory, your rules. One endpoint.
01
Connect once, use everywhere
Bring all your accounts and context together, then make them available to any agent you authorise.
02
Control who can access what
Create separate Access Profiles, choose which accounts and actions each profile can access, and decide who may use them.
03
Use it from any agent
Claude, ChatGPT, Codex, OpenCode, or whatever ships next. Register the endpoint once and every one of them reaches the same accounts, memory and skills.
04
Deploy anywhere
Run Lanes Link on your machine, in your own cloud, or with us (Lanes Managed Cloud), using the same open source code.
Personal assistants
Connect your tools once and give every AI client the same context, memory and permissions wherever you work.
Company internal agents
Give each team an agent with only the access it needs, with permissions enforced centrally and every action logged.
Claude Tag management
Give each Slack channel exactly the accounts and actions it needs, through one connection instead of a service account per tool.
Agent builders
Focus on your product while Link handles authentication, credentials, access controls and integrations through a single endpoint.
Private hosted infrastructure
Run Link in your own cloud so your requests, credentials and data remain entirely under your control.
Outbound sales
Let agents research and draft outreach while people retain final approval over every message that gets sent.
Built-in features
The layer you own.
Every profile gets the accounts it may reach, the context it remembers, the credentials it may spend, and a record of everything it did.
Get started
Your context. Your accounts. Your call.
Frequently asked questions.
Built-in connectors work, but they belong to that AI client. Switch to another agent and you often start again: reconnect your tools, recreate your setup, and explain how you work. Lanes Link gives every AI you use the same foundation. Connect your accounts once, keep your memory, skills, permissions and context in one place, and make them available to any agent you trust. So you can move from Claude to ChatGPT to Cursor, or whatever comes next, without starting over. Your AI changes. Your context doesn't.
Yes, and that is the point. Everything is denied until you allow it, and the endpoint enforces that when a call is dispatched rather than asking the model to behave, so gmail.search = allow with gmail.send = deny holds whatever the agent was told. An account you did not grant a profile is not listed at all, so an agent never learns it exists. It limits the endpoint only, never your own tools.
No. Requests go from your machine straight to the provider, and the response comes back to your machine. Signing in is the one exception: trading an authorisation code for a token needs an OAuth client secret, which cannot ship inside software you run yourself. Register a client of your own with lanes link connect gmail --own-client and even that stops.
No. Lanes does not run a model and never receives your Google user data. When you ask an agent to read something, it goes from your machine to whichever AI provider you configured, on your own account with them. The scopes each product asks for, what reaches our servers and the full Limited Use statement are in
Nothing. Lanes Link is free and open source, and you run it yourself.