MCP Server for Z.AI - A Model Context Protocol server that provides AI capabilities
Nothing to run from here
Apexapi 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.
99/100
trust score
18
downloads a day
local
runs on your machine
673
downloads in 30d
What it does
MCP server for ApexApi — call 120+ AI models and live web context (scrape/crawl/extract) from any MCP client with one ak- API key
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'APEXAPI_API_KEY=${APEXAPI_API_KEY}' --transport stdio apexapi-mcp '--' npx -y apexapi-mcp
# 2 — ask your agent for something these tools do
# chat, list_models, get_balance and 18 more
It needs APEXAPI_API_KEY: this reads it from your environment, so export it first.
Apexapi costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
APAll 1 server
apexapi1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Apexapi as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads APEXAPI_API_KEY (Your ApexApi API key (starts with 'ak-'). Get one at https://apexapi.dev or via agent self-registration per https://apexapi.dev/auth.md) from your environment each time it starts the server, so the value stays out of its config: export it in your shell profile (macOS, Linux), or run setx APEXAPI_API_KEY … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'APEXAPI_API_KEY=${APEXAPI_API_KEY}' --transport stdio apexapi-mcp '--' npx -y apexapi-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
It reaches a system of yours, so it needs your own credential rather than the publisher’s: APEXAPI_API_KEY — Your ApexApi API key (starts with 'ak-'). Get one at https://apexapi.dev or via agent self-registration per https://apexapi.dev/auth.md. You set it in your own client’s config, on your machine — this marketplace never holds it.
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.
Send a prompt to any of the 120+ models on ApexApi (OpenAI, Anthropic, Google, DeepSeek, Qwen, Mistral…). Use list_models to discover model slugs. Billed per token from the credit balance.
No parameter schema on file.
Live catalog of all ApexApi models with type, context window, and USD pricing (per 1M tokens for chat). Filter by type to keep the list short.
No parameter schema on file.
Current prepaid credit balance in USD. Balance is the only usage limit on ApexApi.
No parameter schema on file.
Fetch any URL as clean, LLM-ready markdown (or html/text). Anti-bot handling is automatic (auto-escalates to stealth). Billed at whichever rail actually ran ($0.002 standard, $0.008 stealth), including on failures such as a blocked page or one with no extractable content. This tool always…
No parameter schema on file.
Crawl same-domain pages from a seed URL into markdown. Waits up to 60s; if still running, returns a job id for check_job. Billed $0.005 per page, capped by limit. Full page set is at result_url.
No parameter schema on file.
Ready-made structured JSON from Amazon, Walmart, Crunchbase, G2, Google Maps, or Zillow product/company/listing URLs. Billed $0.01 per record; failures free. Scrapers: amazon-product, walmart-product, crunchbase-company, g2-product, google-maps-business, zillow-property.
No parameter schema on file.
Poll a crawl_site, extract_structured, generate_video, studio_generate, or async image job (POST /v1/images/jobs) by id.
No parameter schema on file.
Generate one or more images from a text prompt. Returns URLs (one per line). Pass image_urls to edit or condition on reference images. Models with an edit variant switch to it automatically; models without reference support return a clear 400. Use list_models with type=image for available models…
No parameter schema on file.
Text-to-speech via ElevenLabs. Returns an MP3 URL. Billed per 1,000 characters.
No parameter schema on file.
Generate a video from a text prompt (and optional starting image). ASYNC — returns a job id immediately (renders take minutes); poll with check_job { kind: "video", id } until status is "completed" (url) or "failed". Use list_models with type=video for slugs and per-second pricing. Duration is…
No parameter schema on file.
List the curated Marketing Studio catalog for turning a product into a video ad: presets (the ad archetype + the video model it routes to), hooks (the viral opening beat), and settings (the environment). Read this first, then pass the chosen ids to studio_generate. Read-only, free.
No parameter schema on file.
Register a product image so it can appear, consistently, across generated video ads. Pass an image URL (or data URI); it is stored permanently and returns a product_id to use with studio_generate. No render charge.
No parameter schema on file.
Register a consistent on-camera person (avatar) for talking-head ad presets. Provide an image_url of a face, OR just a text description to have a reference portrait generated for you (that generation is billed like an image). Returns an avatar_id for studio_generate.
No parameter schema on file.
Compose a studio ad WITHOUT rendering it: returns the exact prompt the video model would get, the model it routes to, the resolved duration, and predicted_usd for that composition. Free, no credits spent. Use it to show the user the price before studio_generate. reference_images and project_id are…
No parameter schema on file.
Turn a studio composition into a production-ready, shot-by-shot video prompt (with dialogue when the preset speaks). Billed as one small chat call (a fraction of a cent, reported as cost_usd). Show the script to the user, let them edit it, then pass it as final_prompt to studio_generate.
No parameter schema on file.
List the products you registered and the avatars you can cast (stock avatars first, then your own). Reuse the ids in studio_preview / studio_generate instead of registering again. Read-only, free.
No parameter schema on file.
Compose a video ad from the catalog: pick a preset + setting (+ optional hook), attach a registered product and/or avatar, and the server fills the prompt and routes to the right video model. ASYNC: returns a job id and predicted_usd immediately; poll with check_job { kind: "studio", id } until…
No parameter schema on file.
List your own completed image and video generations, newest first. Each row is "id | kind | model | url"; reuse a url as image_urls (image reference), video_url / video_urls (video reference) or an edit source in generate_image / generate_video. Pass the returned next_cursor to page further.…
No parameter schema on file.
Get a short-lived upload URL for an image, video or audio reference file (png, jpg, webp, gif up to 20MB; mp4, mov up to 100MB; mp3, wav, m4a up to 25MB). PUT the raw bytes to upload_url with the same content-type, then use public_url as image_urls, video_url or audio_urls. Use this when you can…
No parameter schema on file.
List your still-alive reference-file uploads (from upload_reference or POST /v1/uploads) with url, size and upload time. Uploads are retained for about 48 hours; anything listed here is still usable as image_urls / video_url. Read-only, free.
No parameter schema on file.
Upload a LOCAL image, video or audio file (png, jpg, webp, gif up to 20MB; mp4, mov up to 100MB; mp3, wav, m4a up to 25MB) from this machine and get back a hosted URL to use as image_urls, video_url or audio_urls in generate_image and generate_video (including video edit models). Files are…
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 Apexapi 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 99 / 100
Release 0.5.0 · 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 score100
Client score99
Findings0 threat · 0 capability
Capabilityminimal
Coveragesource
Verificationrepo
Surface digeste6b66865a9a642ddcdff0f328754c67765544a6c336466c5e2466478461b0359
Score vectorthreat 100 → client 99
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| 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 surfacenot available
Implementation sourceread
Package metadataread
Live transportnot available
No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, 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. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| No per-tool rows for this release — see the note below. | ||
No tool surface was enumerated, so there is nothing to attribute a capability to.
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 digeste6b66865a9a642dd
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 0.5.0. Pin a release below and the command asks for exactly that one.
0.5.0
29 Sep 2026
latestNo release note was published with this version.
0.4.5
17 Sep 2026
No release note was published with this version.
0.4.4
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 Apexapi 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.