# How to give Codex access to VSCode Shift+Enter Julia eval?

**URL:** https://discourse.julialang.org/t/how-to-give-codex-access-to-vscode-shift-enter-julia-eval/138838
**Category:** VS Code
**Created:** [August 16, 2026, 5:55am UTC](https://discourse.julialang.org/t/how-to-give-codex-access-to-vscode-shift-enter-julia-eval/138838 "2026-08-16T05:55:02Z")
**Posts on this page:** 6
**Page:** 1

<div class="post-metadata">

### Author: ![Alex1](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/alex1/32/11771_2.png) [@Alex1](https://discourse.julialang.org/u/Alex1)
#### Post date: [August 16, 2026, 5:55am UTC](https://discourse.julialang.org/t/how-to-give-codex-access-to-vscode-shift-enter-julia-eval/138838/1 "2026-08-16T05:55:03Z")

</div>

I’m currently using my own custom module that starts server and exposes socket to Codex Agent so it can call it and execute code in my VS Code julia session.

I wonder if there’s simpler way - given that Julia VS Code extension already does exactly that with Shift + Enter.

So, can AI Agent use Juila VS Code extension API instead of my custom server?

---

<div class="post-metadata">

### Author: ![Praxist](https://avatars.discourse-cdn.com/v4/letter/p/71c47a/32.png) [@Praxist](https://discourse.julialang.org/u/Praxist)
#### Post date: [August 16, 2026, 8:50am UTC](https://discourse.julialang.org/t/how-to-give-codex-access-to-vscode-shift-enter-julia-eval/138838/2 "2026-08-16T08:50:31Z")

</div>

Are you looking for [GitHub - kahliburke/Kaimon.jl: MCP server giving AI agents full access to Julia's runtime via a live Gate — code execution, introspection, debugging, testing, and semantic search · GitHub](https://github.com/kahliburke/Kaimon.jl)

---

<div class="post-metadata">

### Author: ![Alex1](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/alex1/32/11771_2.png) [@Alex1](https://discourse.julialang.org/u/Alex1)
#### Post date: [August 16, 2026, 2:33pm UTC](https://discourse.julialang.org/t/how-to-give-codex-access-to-vscode-shift-enter-julia-eval/138838/3 "2026-08-16T14:33:00Z")

</div>

Thanks, but julia is very slow to startup, so I would like to avoid loading any large package.

My current NetEval is just one page script and it works, but ideally I would like to remove it too and just use already existing VS Code without adding any extra dependency.

Maybe I’m missing something, I don’t know what advantages MCP server has over simple REPL access.

---

<div class="post-metadata">

### Author: ![Alex1](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/alex1/32/11771_2.png) [@Alex1](https://discourse.julialang.org/u/Alex1)
#### Post date: [September 14, 2026, 5:55am UTC](https://discourse.julialang.org/t/how-to-give-codex-access-to-vscode-shift-enter-julia-eval/138838/4 "2026-09-14T05:55:01Z")

</div>

I created VS Code extension that patches standard Julia VS Code extension [GitHub - al6x/julia-bridge: Gives AI Agent access to Julia VS Code julia terminal · GitHub](https://github.com/al6x/julia-bridge)

Ideally something like that should be part of standard Julia VS Code extension.

Ideas to improve/simplify welcomed.

P.S.

Also here’s AI instructions how to use it

```julia-auto
Don't run Julia unless explicitly asked, and never start a fresh process. Use static inspection by default. When asked,
run `/projects/julia-bridge/client.js --timeout 120 'code'` from the project root. It uses the existing VS Code REPL,
returns JSON, and interrupts Julia on timeout or Ctrl-C.

For nontrivial work, replace the body of `AgentEval.run()` in `./AgentEval.jl`, then evaluate
`import AgentEval; agent_result = Base.invokelatest(AgentEval.run)`. Revise reloads it before each request. After
changing `const` or `struct` definitions, explicitly run `Revise.revise(AgentEval)`. Return compact values, preferably
named tuples, and use files for large output. Use plain code and
don't use `eval` to monkey-patch package methods.

```

---

<div class="post-metadata">

### Author: ![hersle](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/hersle/32/211689_2.png) [@hersle](https://discourse.julialang.org/u/hersle)
#### Post date: [September 14, 2026, 11:55am UTC](https://discourse.julialang.org/t/how-to-give-codex-access-to-vscode-shift-enter-julia-eval/138838/5 "2026-09-14T11:55:14Z")

</div>

There is also [GitHub - marius311/julia-vscode-unofficial-mcp: Julia VSCode REPL for agents · GitHub](https://github.com/marius311/julia-vscode-unofficial-mcp) by @marius311, which exposes the Julia REPL in VSCode to an AI agent through MCP.

See also the thread in [Letting AI agents use the VSCode Julia REPL](https://discourse.julialang.org/t/letting-ai-agents-use-the-vscode-julia-repl/136805).

---

<div class="post-metadata">

### Author: ![greatpet](https://avatars.discourse-cdn.com/v4/letter/g/e495f1/32.png) [@greatpet](https://discourse.julialang.org/u/greatpet)
#### Post date: [September 14, 2026, 12:09pm UTC](https://discourse.julialang.org/t/how-to-give-codex-access-to-vscode-shift-enter-julia-eval/138838/6 "2026-09-14T12:09:15Z")

</div>

> [@Alex1](#):
>
> Thanks, but julia is very slow to startup, so I would like to avoid loading any large package.

Running `KaimonGate.serve()` in the VSCode REPL is very quick, taking less than 0.5 seconds before the connection with the Kaimon server is established. The Kaimon server itself, installed at `~/.julia/bin/kaimon`, takes longer to start, but you only need to do that once per boot and keep it running.

There’s also an option that appears more lightweight than Kaimon, though I haven’t tried:

> **[GitHub - hexaeder/MCPRepl.jl: Expose your repl via MCP!](https://github.com/hexaeder/MCPRepl.jl)**
>
> Expose your repl via MCP!
