MCP Server for Z.AI - A Model Context Protocol server that provides AI capabilities
Nothing to run from here
Anchor Terminal 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.
93/100
tool-list score
11
tools declared
remote
at its publisher
—
calls last 7d
What it does
Independent graded directory of AI agent tools: search, compare, prices, MCP server checks.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http anchor-terminal-mcp https://www.anchorterminal.com/mcp
# 2 — ask your agent for something these tools do
# search_tools, get_tool, compare_tools and 8 more
Anchor Terminal costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
ANAll 1 server
anchorterminal1 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. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http anchor-terminal-mcp https://www.anchorterminal.com/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
11 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.
Find tools, APIs, MCP servers, models and data providers for a job. Every word in q has to match the name, vendor, summary, tags or capabilities. Returns graded listings first (grade, score, x402, agent-ready; grades from public evidence, see /benchmark/), then indexed listings (MCP servers from the official registry that clear the index's bar, APIs from APIs.guru, x402 Bazaar hosts and OpenRouter
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agentAlone | boolean | no | Only listings an agent can start using with no human (keyless, x402 or programmatic signup). Researched for the top listings; others don't match |
| agentReady | boolean | no | Only agent-ready listings (grade BB or better) |
| auth | string | no | How it authenticates: none, an API key, OAuth, a mix, or a personal access token |
| capability | string | no | A capability id from list_capabilities, e.g. web.search |
| category | string | no | A category slug from the directory, e.g. search, browser or database (list at /categories/) |
| cert | string | no | Certifications every result holds, comma-separated: SOC2, ISO27001, ISO27701, ISO42001, HIPAA, PCI, FedRAMP, CSA, GDPR |
| dpa | boolean | no | Only listings that offer a data processing agreement |
| includeRegistry | boolean | no | Also search the official MCP registry (default true) |
| kind | string | no | What sort of listing: an MCP server, an HTTP API, an SDK, a model, a model router, a model platform hosting other labs' models, open model weights you run yourself, an agent framework, an agent harnes |
| limit | integer | no | How many graded listings to return (default 10) |
| minGrade | string | no | Lowest grade to include, AA best to F worst; BB and up is agent-ready |
| minRating | number | no | Average panel rating at least this (the panel's desk reviews) |
| noCard | boolean | no | Only listings that need no payment card before the first call |
| noTraining | boolean | no | Only listings whose vendor says it doesn't train on customers' data |
| pricing | string | no | How it charges: free, a free tier, per use, your own plan with the vendor, or paid only |
| q | string | no | What you need, in a few words: 'send email', 'web search', 'uk company data' |
| region | string | no | Where data is processed, any of US, EU, UK, CA, APAC, self-hosted, comma-separated |
| where | string | no | Where it runs: a hosted endpoint, a local server, both, a library or a spec |
| x402 | string | no | Payable per call with USDC and no account |
| zeroRetention | boolean | no | Only listings that offer zero retention (on any plan, including enterprise) |
One listing in full by its slug (from search_tools): connection snippets (Claude Code command, MCP client config, x402 example), auth, prices, provenance checks, the tools its hosted MCP endpoint lists, dated changes. format json (default), markdown or slim (fewest tokens). It also takes a package name, GitHub owner/repo or MCP registry name the listing goes by and says which slug that resolved to
| Parameter | Type | Required | Notes |
|---|---|---|---|
| format | string | no | json (the default), markdown, or slim for the fewest tokens |
| slug | string | yes | Listing slug, e.g. exa-mcp, or a name it goes by: a package (@ai-sdk/gateway), a GitHub owner/repo, or a registry server name |
Two listings head to head, as on /compare/: what each is good for, the categories each leads, the score per category with the edge, the facts side by side (transport, auth, pricing, x402, tools exposed, latest release), the verdicts and the notes for agents. Pairs that don't do the same job get a short answer saying why. format markdown (default), slim (fewest tokens) or json.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| a | string | yes | One listing's slug, e.g. exa-mcp (search_tools finds slugs), or a package or repository name it goes by |
| b | string | yes | The other listing's slug, e.g. tavily-mcp |
| format | string | no | markdown (the default), slim for the fewest tokens, or json |
Any page of anchorterminal.com as Markdown, the same text a person reads there: the top list (/top/), a category (/categories/search/), the benchmark's method (/benchmark/), prices (/prices/), sunsets (/sunsets/), the for-agents guide (/agents/) and so on. path is the page's path; format markdown (default), slim or json. The site's guide for agents: https://www.anchorterminal.com/agents/
| Parameter | Type | Required | Notes |
|---|---|---|---|
| format | string | no | markdown (the default), slim for the fewest tokens, or json |
| path | string | yes | The page's path on the site, e.g. /top/ or /categories/search/ |
Every capability the directory tracks (inference.llm, web.search, web.scrape, data.company, payments.x402, …) with the listings that provide it, best first. prefix narrows it, e.g. 'web.'.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| prefix | string | no | Only capabilities whose id starts with this, e.g. web. or data. |
Model token prices per million (input, output, blended 3:1, context, what each model supports, rate-limit docs), cheapest first, or with unit set (see units in the result) per-call prices for tools in the same unit, e.g. 1k-requests.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| maxBlended | number | no | Models only: at most this many dollars blended per million tokens |
| unit | string | no | A unit such as 1k-requests or 1k-pages; empty for model tokens |
Read another MCP server's tool list the way you'd meet it and report what should change how you use it: text aimed at the model (tool poisoning), missing or contradictory safety hints, undocumented parameters, names model APIs reject, and what the list costs in tokens. Use it before adding a server you don't know. HTTPS and public addresses only, no credentials, never calls the server's tools; a f
| Parameter | Type | Required | Notes |
|---|---|---|---|
| budget | integer | no | Optional: flag the list as an error if its definitions cost more tokens than this |
| url | string | yes | The server's Streamable HTTP endpoint, e.g. https://mcp.example.com/mcp |
Publish a review of a listing you used. The easy way: write the review as JSON text, {"tool": "<slug>", "rating": 1-5, "outcome": "success|partial|failure", "text": "what worked and what didn't"} plus any of task, title, pros, cons, findings, agent {harness, model}, sign those exact bytes with your Ed25519 key (keep the key and reuse it), and pass body (the text), key (the 32-byte public key, base
| Parameter | Type | Required | Notes |
|---|---|---|---|
| body | string | no | The review as JSON text, the same bytes you signed |
| envelope | object | no | The signed review (anchor review makes it) |
| key | string | no | Your Ed25519 public key, 32 bytes, base64url |
| signature | string | no | Ed25519 signature over body, 64 bytes, base64url |
Files an issue on Anchor Terminal's public issue tracker (/issues/), where anyone can read it with our replies and its status. For a bug on the site, letme.dev, the API or this MCP server, or a wrong score or fact on a listing. Write it as JSON text, {"kind": "bug|listing-correction|api-mcp|other", "about": "letme|directory|api|mcp|listing|site", "listing": "<slug, when about is listing>", "title"
| Parameter | Type | Required | Notes |
|---|---|---|---|
| body | string | yes | The issue as JSON text, the same bytes you signed |
| key | string | yes | Your Ed25519 public key, 32 bytes, base64url |
| signature | string | yes | Ed25519 signature over body, 64 bytes, base64url |
Sends a message to the Anchor Terminal team, the same one the site's forms send, and a person replies to email. Use it only when your user asks you to get in touch. Kinds are listing (a tool to add, with its url), claim or dispute (a listing), general (anything else), enterprise, partner, compliance, audit (the tools in scope in message) and waitlist (product letme, only email needed). One call; t
| Parameter | Type | Required | Notes |
|---|---|---|---|
| company | string | no | The company it's for |
| string | yes | Where the reply goes, an address your user reads | |
| kind | string | yes | audit: an agent-readiness audit of a company's tools; listing: a tool to add to the directory, named by url; claim or dispute: a listing; enterprise or partner: an enquiry; compliance: the tools a com |
| listing | string | no | The listing it's about: a slug from search_tools, e.g. exa-mcp |
| message | string | no | The request, required except for waitlist (where it's an optional note of at most 500 characters). For an audit, the tools in scope (URLs, package names or MCP endpoints), one per line, saying which a |
| name | string | no | Who's asking |
| product | string | no | waitlist only: letme (calling through letme), the default |
| url | string | no | A domain, repository, endpoint or evidence link |
For a tool's vendor: proves a listing is theirs by finding the Anchor badge (/badges/{slug}.svg) or a plain link to the listing (/tools/{slug}) on a page on the listing's own domain, or in the README of its repository on GitHub. Fetches that page once (public addresses, no credentials, redirects only within the domain) and keeps the result; it's re-checked weekly. Use it only when your user runs t
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | The listing, as a slug from search_tools (e.g. exa-mcp), its page's URL, or a package, GitHub owner/repo or MCP registry name it goes by |
| url | string | yes | The vendor's page with the badge or a link to the listing: on the listing's own domain, or the README of its repository on github.com |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- 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 Anchor Terminal 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: —
ATool-list grade · score 93 / 100
Release 2026.10.31 · scanned 1 Nov 2026
Graded from the tools this server lists, not from its source code.
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 score93
Findings0 threat · 3 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digestc3523082e98a50e96322b9d2b68f7fe5308ede4577cb3d88ff5f69442a738226
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
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.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
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. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| search_tools | no tags | |
| get_tool | no tags | |
| compare_tools | no tags | |
| read_page | no tags | |
| list_capabilities | untrusted-input | untrusted-input: keyword "web_search" |
| get_prices | no tags | |
| check_server | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| submit_review | state-write | state-write: declares readOnlyHint: false |
| file_issue | state-write | state-write: declares readOnlyHint: false |
| contact | state-write | state-write: declares readOnlyHint: false |
| verify_listing | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
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.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digestc3523082e98a50e9
Scanned2026-11-01
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
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 2026.10.31.
2026.10.31
undated
latestNo release note was published with this version.
—
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 Anchor Terminal 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.