How to Connect Codex to Linear (and What It Can't Do)
Yes — you can connect Linear to OpenAI Codex through Linear’s MCP server, and it does one thing: it gives the coding agent your issues and tickets as context to code from. Add the Linear MCP server to Codex’s config and it can read a ticket, understand the requirement, and implement it in your repo. That’s a real, useful capability — for a developer working issue-by-issue. What it is not is an assistant that manages Linear for you: it doesn’t watch for new issues to route, update statuses across a project on a schedule, or turn Linear activity into follow-ups across your other tools. And standing it up is a developer setup — editing config.toml, enabling the remote MCP client, running an OAuth login — not a toggle a non-technical person flips.
Here’s what the Codex Linear connection does, how to wire it up, where the limits are, and what to use if you want Linear work handled by an assistant instead of a coding agent.
What the Codex Linear integration does
Codex supports the Model Context Protocol (MCP), and Linear ships an official MCP server. Connect the two — OpenAI documents the flow in its Use Codex in Linear guide — and Codex can:
- Read issues and tickets as context — pull a Linear issue into a coding task so you don’t have to restate the requirement.
- Search your workspace — find the right issue or project via the MCP server’s tools while it works.
- Code from a ticket — keep the spec in Linear and let Codex consult it as it makes changes in your repo.
The point of the connection is to feed the coding agent — Linear is an input to a software task, not something Codex is managing on your behalf.
How to set it up
Setup is a developer task with prerequisites:
- A Plus, Pro, Business, Edu, or Enterprise ChatGPT plan and Codex installed (CLI or IDE extension).
- Open (or create) your Codex config file at
~/.codex/config.toml(or a project-scoped.codex/config.tomlin a trusted project). - Add the Linear MCP server — run
codex mcp add linear --url https://mcp.linear.app/mcp, or add an[mcp_servers.linear]entry manually. Because it’s a remote HTTP server, enable Codex’s remote MCP client feature (experimental_use_rmcp_client = true) if this is your first remote MCP. See the MCP docs. - Authenticate. Run
codex mcp login linearand sign in to connect your Linear account.
If you’re not running Codex against a codebase, there’s nothing for this to plug into — the connection assumes you’re driving software work and want Linear tickets as context.
The limits that actually matter
The Linear connection is built for one persona and one job. Three limits define it:
- It’s a context source, not a Linear manager. It exists to hand your tickets to a coding task. It won’t watch for new issues to triage, move a status when work ships, or turn a completed issue into a customer email — those aren’t things it does.
- It assumes a developer setup.
config.toml, a remote MCP client feature flag, OAuth login, a repo to work in. This is plumbing for engineers, not a five-minute connect for an exec or EA. - Codex is a coding agent at its core. Even with MCP support, its native surface is code, PRs, terminals, and environments. Pointing it at general project-tracking ops is using a build tool for a job it wasn’t shaped for.
So Codex-plus-Linear is great for “read this ticket and implement it” and not built for “watch our board and keep everything moving.”
If you want Linear work handled by an assistant: Carly
The moment you want Linear handled — a new issue that triggers a task or a message, a status that updates when something changes, a completed ticket that becomes a follow-up email — without editing config files or running an MCP server, you’ve crossed past what Codex is for.
That’s where Carly fits. Carly is an AI executive assistant built to act on triggers across your whole stack, set up by conversation instead of code:
- No-code setup. Tell Carly “when a Linear issue is marked done, email the requester and log it” in plain English; it interviews you and builds the workflow. No
config.toml, no MCP server to run. - Fires on events, 24/7, in the cloud — when Linear changes, Carly acts; nothing to keep running on your machine.
- Connects Linear to the rest of your work — turn issues and status changes into actions that also touch email, calendar, CRM, and tasks.
- Actually sends and updates — drafts and sends email (Gmail and Outlook), files and labels, manages tasks, updates your CRM, records meetings.
AI agents start at $35/month, and workflow steps that don’t use AI run free and unlimited. Carly connects to 200+ tools across 40+ categories — see integrations. By the way, Carly also integrates with Linear.
Codex’s Linear integration vs Carly
| Codex (Linear via MCP) | Carly | |
|---|---|---|
| Purpose | Feed tickets to a coding task | Handle Linear + ops work |
| Setup | Edit config.toml, MCP client flag, OAuth | Describe it in plain English |
| Reads issues & projects | Yes (as context) | Yes |
| Updates status / routes issues | No | Yes |
| Acts on triggers / events | No | Yes, on any event |
| Runs without your machine | Cloud tasks (dev) | Yes (cloud, 24/7) |
| Sends email as part of the flow | No | Yes (Gmail + Outlook) |
| Built for | Developers | Execs, EAs, operators |
| Pricing | Paid ChatGPT plan | AI agents from $35/mo |
Codex-plus-Linear is a coding agent reading your tickets. Carly is an assistant that works your Linear and the rest of your day.
Frequently Asked Questions
Does OpenAI Codex integrate with Linear?
Yes, via MCP. Codex supports the Model Context Protocol and Linear ships an official MCP server, so you can add it with codex mcp add linear --url https://mcp.linear.app/mcp and let Codex read your issues as context while it codes. OpenAI documents it in the Use Codex in Linear guide. It’s a developer configuration, not a one-click connect.
Can Codex manage my Linear issues or update statuses?
The MCP connection lets Codex read Linear as context for a coding task. It’s not built to watch for new issues, route them, or move statuses on its own as part of your ops. For an assistant that acts on Linear, you need an agent platform like Carly.
How do I connect Codex to Linear?
Add the Linear MCP server to your Codex config with codex mcp add linear --url https://mcp.linear.app/mcp (or a manual [mcp_servers.linear] entry), enable the remote MCP client feature if it’s your first, then run codex mcp login linear to authenticate. Full steps are in OpenAI’s MCP docs.
Is Codex the right tool for non-technical Linear automation?
Not really. Codex is a coding agent, and its Linear connection assumes config files, an MCP server, and a repo to work in. If you just want Linear issues to trigger tasks, updates, and emails, a no-code assistant like Carly is a better fit — set up by describing it, running 24/7 in the cloud.
More: Codex + GitHub · Codex + Notion · Codex + Jira · Codex + Slack · Codex alternatives · Best AI personal assistants
Ready to automate your busywork?
Carly schedules, researches, and briefs you—so you can focus on what matters.
See what people say
"Before Carly, I relied on a Calendly link, but the whole process felt impersonal and not very professional. Carly changed that by handling all the back-and-forth, so I'm no longer stuck in endless email threads trying to line up schedules.
Now Carly reaches out to candidates, shares my real-time availability, lets them pick a slot, then sends a Zoom link and drops it straight into my calendar. She sends reminders to both of us before each call, which has significantly reduced no-shows and last-minute confusion.
On top of scheduling, Carly acts like a full executive assistant, sending me my schedule the night before so I can prepare for each call. It reminds me of the old x.ai assistant, but Carly is noticeably smarter, faster, and better suited to my healthcare recruitment business."
