codex-worker-runtime
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@codex-worker-runtimedelegate code review of PR #42 to qwen"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Codex Worker Runtime
Role-based external LLM delegation for Codex.
Codex stays the orchestrator and delegates bounded work through four MCP tools:
delegate_worklist_workersworker_healthget_worker_run
Current routes
Role | Worker | Adapter |
|
| OpenAI-compatible API |
|
| guarded Grok CLI |
|
| opencodex Responses API |
|
| opencodex Responses API |
Kimi is reached only through the worker runtime. The main Codex provider, history, CLI shim, account pool, and native subagent catalog do not need to be changed.
Guarantees
External workers cannot edit local files or execute Codex commands.
secretandcredentialrequests are rejected before dispatch.Worker results are normalized into a stable transport and semantic contract.
completed + rejectedis preserved and is never overwritten by another provider.Unavailable or timed-out workers return control to Codex according to policy.
Requests, attempts, and results are stored in a local SQLite audit ledger.
Prepared requests and raw provider responses stay out of the normal result.
Configuration
The runtime loads the first available policy:
CODEX_WORKER_CONFIG~/.codex/codex-worker-runtime/workers.tomlbundled
config/workers.toml
Relative worker commands are resolved from the policy file. ~/ paths expand
to the current user home directory.
The bundled policy expects:
an OpenAI-compatible Qwen endpoint at
http://127.0.0.1:8081Grok Build installed at
~/.grok/bin/grokGrok privacy settings that pass
runtime/grok/grok_privacy_guard.pyopencodex listening on
127.0.0.1:10100with thekimiprovider authenticated
Start only the local proxy server used by the Kimi worker, without Codex model injection, history synchronization, a CLI shim, or a background service:
npm run start:kimi-proxyTo keep a custom policy outside the plugin, copy the file, update any relative
worker commands for its new location, and set CODEX_WORKER_CONFIG to its
absolute path.
Development
npm install
npm run check
npm run test:allLocal personal-plugin install
The installer creates named backups, stages the plugin, verifies source/target/cache hashes, and checks plugin activation.
node scripts/install-personal.mjs --dry-run
node scripts/install-personal.mjsOptional environment variables:
CODEX_WORKER_CODEX_ROOTCODEX_WORKER_CODEX_CLICODEX_WORKER_INSTALL_TARGETCODEX_WORKER_MARKETPLACECODEX_WORKER_AUDIT
Coexistence with opencodex
opencodex and Codex Worker Runtime can coexist because they operate at different layers:
opencodex proxies the main Codex Responses API transport.
Codex Worker Runtime delegates selected roles through MCP.
Recommended policy:
keep the main Codex provider explicit
avoid routing the same job to both a native routed subagent and an MCP worker
review
~/.codex/config.tomlafter runningocx initor installing its shimlet only one installer manage the Codex provider configuration and CLI shim
keep credentials in each provider's own configuration; do not copy them into
workers.toml
The runtime uses stdio MCP and does not bind opencodex's default port 10100.
Its bundled Qwen example uses port 8081.
Adding a worker
Add the worker and role to
config/workers.toml.Reuse an existing adapter or add a dedicated adapter.
Normalize the response into the common result contract.
Add health, timeout, failure, audit, and redaction tests.
License
MIT
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/ykanbe/codex-worker-runtime'
If you have feedback or need assistance with the MCP directory API, please join our Discord server