MCP Server for Z.AI - A Model Context Protocol server that provides AI capabilities
Nothing to run from here
Codex Supervisor is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
92/100
trust score
43
downloads a day
local
runs on your machine
4k
downloads in 30d
What it does
Parallel Codex CLI workers from any MCP client: one git worktree each, state in SQLite, web board.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user codex-supervisor-mcp '--' npx -y codex-supervisor-mcp
# 2 — ask your agent for something these tools do
# create_codex_worker, create_codex_followup_worker, resume_codex_worker and 18 more
Codex Supervisor costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
ZRAll 1 server
zriyox1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Codex Supervisor as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user codex-supervisor-mcp '--' npx -y codex-supervisor-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
Nothing is required, but it can take CODEX_BIN (Path to the codex CLI when it is not on PATH), SUPERVISOR_HOME (State directory, default ~/.codex-supervisor) if you want to set them.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
21 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Launch a Codex CLI worker with codex exec --json and track its events. ownedPaths and goal are required: ownedPaths reserves the files this worker may write, goal records what the worker is for.
No parameter schema on file.
Start a NEW Codex session seeded with the previous worker's prompt, status, and recent events. To continue the same session instead, use resume_codex_worker.
No parameter schema on file.
Continue the SAME Codex session for an existing worker via codex exec resume <thread_id>. Works from a different MCP process or a fresh client session as long as the task recorded a thread_id.
No parameter schema on file.
List tracked Codex workers. Defaults to active workers only.
No parameter schema on file.
Compact status table for every worker, budgeted to stay under ~2k tokens. This is the default read for an orchestrating main thread; fetch details per worker only when needed.
No parameter schema on file.
Block until selected Codex workers reach a terminal status, then return summaries. The wait budget bounds this call, not the workers: when it runs out you get a progress snapshot and the workers keep running, so call this again with the same task_ids to keep waiting. Keep the budget under your…
No parameter schema on file.
Every worker dispatched under one session_id, oldest first. This is the reconnect path: a main-thread session that died can list the whole batch it started without holding any of it in context.
No parameter schema on file.
Ask the npm registry whether a newer codex-supervisor-mcp is published, and whether the installed files match the published tarball. Returns installed and latest version, integrity check, and the install command. The same check runs on startup; call this to force a fresh one.
No parameter schema on file.
Record what a session is about: a one-line title and an optional note. Readers of the store (the web view, get_session_works) show these instead of the bare session id. Fields you omit are kept.
No parameter schema on file.
Substring search over title, goal, prompt and last message of every tracked worker, newest first. Use it to find an earlier work by keyword instead of paging through history.
No parameter schema on file.
Read the latest normalized status for one Codex worker: lifecycle, phase, current action, changed files, goal, recent commands, and the task prompt (clipped by default). Set includePrompt to read the prompt in full, or use get_codex_worker_events for the raw stream.
No parameter schema on file.
Read recent raw Codex JSONL events for one worker. limit, maxChars and kinds keep the read inside a context budget; maxChars truncates the middle of oversized strings the same way Codex truncates its own output.
No parameter schema on file.
Read the goal recorded for a worker, plus the native Codex thread goal when the thread has one (status, tokens used, time used).
No parameter schema on file.
One compact summary per worker: goal, status, changed files, last command, last message. Cheap enough for a main thread to read every worker at the end of a run.
No parameter schema on file.
Read a worker's own final report in full. The overview and the wait response clip the last message so a batch stays inside a context budget; this is the door for the actual conclusion. Returns the last N agent messages plus the status fields needed to tell a real finish from a crash.
No parameter schema on file.
The worker's actual changes as patches: everything between the commit its worktree started from and its working tree, committed or not, plus untracked files. This is the ground truth to check a worker's report against. maxChars bounds the whole answer: files past the budget come back listed but…
No parameter schema on file.
Ask a finished or running worker a question without touching its thread: the worker's Codex thread is forked once into a read-only side session (like Codex's own /btw), the question is asked there, and later questions resume that fork. The fork carries everything the worker saw and did, so 'why…
No parameter schema on file.
Cherry-pick the commits a worker made on its codex/<taskId> branch onto the current branch of the directory it was dispatched from. The target must be clean and is never switched to another branch; onto is a guard that names the branch you expect to be on. A conflict aborts the cherry-pick,…
No parameter schema on file.
Terminate a running Codex worker. Uses the in-process handle when available, otherwise the pid recorded on disk so a different MCP session can still cancel it.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Codex Supervisor or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 92 / 100
Release 0.9.1 · scanned 14 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score99
Client score92
Findings11 threat · 0 capability
Capabilityhigh
Coveragesource
Verificationrepo
Surface digest238ed6fd74180e993aa4027a71d512f162549b9725cfaeaaef8b6b1650021299
Score vectorthreat 99 → client 92
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (21 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| check_workers | no tags | |
| check_acceptance | no tags | |
| create_codex_worker | no tags | |
| create_codex_followup_worker | no tags | |
| resume_codex_worker | no tags | |
| list_codex_workers | no tags | |
| get_orchestration_overview | untrusted-input | untrusted-input: keyword "fetch" |
| wait_codex_workers | no tags | |
| get_session_works | no tags | |
| check_for_update | no tags | |
| describe_session | no tags | |
| search_works | no tags | |
| get_codex_worker_status | no tags | |
| get_codex_worker_events | no tags | |
| get_worker_goal | no tags | |
| get_worker_summary | no tags | |
| get_worker_result | no tags | |
| get_worker_diff | no tags | |
| ask_codex_worker | no tags | |
| land_codex_worker | no tags | |
| cancel_codex_worker | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest238ed6fd74180e99
Scanned2026-10-14
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.9.1. Pin a release below and the command asks for exactly that one.
0.9.1
14 Oct 2026
latestNo release note was published with this version.
0.8.0
8 Oct 2026
No release note was published with this version.
0.7.3
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Codex Supervisor can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.