Currently, our `npm publish` logic is failing.
There were a number of things that were merged recently that seemed to
contribute to this situation, though I think we have fixed most of them,
but this one stands out:
https://github.com/openai/codex/pull/10115
As best I can tell, we tried to fix the pnpm version to a specific hash,
but we did not do it consistently (though `shell-tool-mcp/package.json`
had it specified twice...), so for this PR, I ran:
```
$ git ls-files | grep package.json
codex-cli/package.json
codex-rs/responses-api-proxy/npm/package.json
package.json
sdk/typescript/package.json
shell-tool-mcp/package.json
```
and ensured that all of them now have this line:
```json
"packageManager": "pnpm@10.28.2+sha512.41872f037ad22f7348e3b1debbaf7e867cfd448f2726d9cf74c08f19507c31d2c8e7a11525b983febc2df640b5438dee6023ebb1f84ed43cc2d654d2bc326264"
```
I also went and deleted all of the `corepack` stuff that was added by
https://github.com/openai/codex/pull/10115.
If someone can explain why we need it and verify it does not break `npm
publish`, then we can bring it back.
This updates the CI workflows for shell-tool-mcp to use the pnpm version
from package.json and print it in the build for verification.
I have read the CLA Document and I hereby sign the CLA
Historically, `accept_elicitation_for_prompt_rule()` was flaky because
we were using a notification to update the sandbox followed by a `shell`
tool request that we expected to be subject to the new sandbox config,
but because [rmcp](https://crates.io/crates/rmcp) MCP servers delegate
each incoming message to a new Tokio task, messages are not guaranteed
to be processed in order, so sometimes the `shell` tool call would run
before the notification was processed.
Prior to this PR, we relied on a generous `sleep()` between the
notification and the request to reduce the change of the test flaking
out.
This PR implements a proper fix, which is to use a _request_ instead of
a notification for the sandbox update so that we can wait for the
response to the sandbox request before sending the request to the
`shell` tool call. Previously, `rmcp` did not support custom requests,
but I fixed that in
https://github.com/modelcontextprotocol/rust-sdk/pull/590, which made it
into the `0.12.0` release (see #8288).
This PR updates `shell-tool-mcp` to expect
`"codex/sandbox-state/update"` as a _request_ instead of a notification
and sends the appropriate ack. Note this behavior is tied to our custom
`codex/sandbox-state` capability, which Codex honors as an MCP client,
which is why `core/src/mcp_connection_manager.rs` had to be updated as
part of this PR, as well.
This PR also updates the docs at `shell-tool-mcp/README.md`.
The existing version of `shell-tool-mcp/README.md` was not written in a
way that was meant to be consumed by end-users. This is now fixed.
Added `codex-rs/exec-server/README.md` for the more technical bits.
When running `npx @openai/codex-shell-tool-mcp`, the old code derived
`__dirname` from `process.argv[1]`, which points to npx’s transient
wrapper script in
`~/.npm/_npx/134d0fb7e1a27652/node_modules/.bin/codex-shell-tool-mcp`.
That made `vendorRoot` resolve to `<npx cache>/vendor`, so the startup
checks failed with "Required binary missing" because it looked for
`codex-execve-wrapper` in the wrong place.
By relying on the real module `__dirname` and `path.resolve(__dirname,
"..", "vendor")`, the package now anchors to its installed location
under `node_modules/@openai/codex-shell-tool-mcp/`, so the bundled
binaries are found and npx launches correctly.
This adds a GitHub workflow for building a new npm module we are
experimenting with that contains an MCP server for running Bash
commands. The new workflow, `shell-tool-mcp`, is a dependency of the
general `release` workflow so that we continue to use one version number
for all artifacts across the project in one GitHub release.
`.github/workflows/shell-tool-mcp.yml` is the primary workflow
introduced by this PR, which does the following:
- builds the `codex-exec-mcp-server` and `codex-execve-wrapper`
executables for both arm64 and x64 versions of Mac and Linux (preferring
the MUSL version for Linux)
- builds Bash (dynamically linked) for a [comically] large number of
platforms (both x64 and arm64 for most) with a small patch specified by
`shell-tool-mcp/patches/bash-exec-wrapper.patch`:
- `debian-11`
- `debian-12`
- `ubuntu-20.04`
- `ubuntu-22.04`
- `ubuntu-24.04`
- `centos-9`
- `macos-13` (x64 only)
- `macos-14` (arm64 only)
- `macos-15` (arm64 only)
- builds the TypeScript for the [new] Node module declared in the
`shell-tool-mcp/` folder, which creates `bin/mcp-server.js`
- adds all of the native binaries to `shell-tool-mcp/vendor/` folder;
`bin/mcp-server.js` does a runtime check to determine which ones to
execute
- uses `npm pack` to create the `.tgz` for the module
- if `publish: true` is set, invokes the `npm publish` call with the
`.tgz`
The justification for building Bash for so many different operating
systems is because, since it is dynamically linked, we want to increase
our confidence that the version we build is compatible with the glibc
whatever OS we end up running on. (Note this is less of a concern with
`codex-exec-mcp-server` and `codex-execve-wrapper` on Linux, as they are
statically linked.)
This PR also introduces the code for the npm module in `shell-tool-mcp/`
(the proposed module name is `@openai/codex-shell-tool-mcp`). Initially,
I intended the module to be a single file of vanilla JavaScript (like
[`codex-cli/bin/codex.js`](ab5972d447/codex-cli/bin/codex.js)),
but some of the logic seemed a bit tricky, so I decided to port it to
TypeScript and add unit tests.
`shell-tool-mcp/src/index.ts` defines the `main()` function for the
module, which performs runtime checks to determine the clang triple to
find the path to the Rust executables within the `vendor/` folder
(`resolveTargetTriple()`). It uses a combination of `readOsRelease()`
and `resolveBashPath()` to determine the correct Bash executable to run
in the environment. Ultimately, it spawns a command like the following:
```
codex-exec-mcp-server \
--execve codex-execve-wrapper \
--bash custom-bash "$@"
```
Note `.github/workflows/shell-tool-mcp-ci.yml` defines a fairly standard
CI job for the module (`format`/`build`/`test`).
To test this PR, I pushed this branch to my personal fork of Codex and
ran the CI job there:
https://github.com/bolinfest/codex/actions/runs/19564311320
Admittedly, the graph looks a bit wild now:
<img width="5115" height="2969" alt="Screenshot 2025-11-20 at 11 44
58 PM"
src="https://github.com/user-attachments/assets/cc5ef306-efc1-4ed7-a137-5347e394f393"
/>
But when it finished, I was able to download `codex-shell-tool-mcp-npm`
from the **Artifacts** for the workflow in an empty temp directory,
unzip the `.zip` and then the `.tgz` inside it, followed by `xattr -rc
.` to remove the quarantine bits. Then I ran:
```shell
npx @modelcontextprotocol/inspector node /private/tmp/foobar4/package/bin/mcp-server.js
```
which launched the MCP Inspector and I was able to use it as expected!
This bodes well that this should work once the package is published to
npm:
```shell
npx @modelcontextprotocol/inspector npx @openai/codex-shell-tool-mcp
```
Also, to verify the package contains what I expect:
```shell
/tmp/foobar4/package$ tree
.
├── bin
│ └── mcp-server.js
├── package.json
├── README.md
└── vendor
├── aarch64-apple-darwin
│ ├── bash
│ │ ├── macos-14
│ │ │ └── bash
│ │ └── macos-15
│ │ └── bash
│ ├── codex-exec-mcp-server
│ └── codex-execve-wrapper
├── aarch64-unknown-linux-musl
│ ├── bash
│ │ ├── centos-9
│ │ │ └── bash
│ │ ├── debian-11
│ │ │ └── bash
│ │ ├── debian-12
│ │ │ └── bash
│ │ ├── ubuntu-20.04
│ │ │ └── bash
│ │ ├── ubuntu-22.04
│ │ │ └── bash
│ │ └── ubuntu-24.04
│ │ └── bash
│ ├── codex-exec-mcp-server
│ └── codex-execve-wrapper
├── x86_64-apple-darwin
│ ├── bash
│ │ └── macos-13
│ │ └── bash
│ ├── codex-exec-mcp-server
│ └── codex-execve-wrapper
└── x86_64-unknown-linux-musl
├── bash
│ ├── centos-9
│ │ └── bash
│ ├── debian-11
│ │ └── bash
│ ├── debian-12
│ │ └── bash
│ ├── ubuntu-20.04
│ │ └── bash
│ ├── ubuntu-22.04
│ │ └── bash
│ └── ubuntu-24.04
│ └── bash
├── codex-exec-mcp-server
└── codex-execve-wrapper
26 directories, 26 files
```
