MCP Server for Z.AI - A Model Context Protocol server that provides AI capabilities
Nothing to run from here
agent-tools (x402 + MCP + A2A directory) 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
5
downloads a day
local
or remote
108
downloads in 30d
What it does
Discover x402 services, MCP servers and A2A agents by intent — agent-tools.cloud directory.
Quickstart
Install it the way its author documents:
1. claude mcp add agent-tools -- uvx agent-tools-mcp@latest
The full guide: https://pypi.org/project/agent-tools-mcp/
Publisher
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one can run either way — at an address its publisher runs, or as a process under your own user, with your files and your network — and this marketplace is in the path of neither.
Install it the way its author documents:
1. claude mcp add agent-tools -- uvx agent-tools-mcp@latest
The full guide: https://pypi.org/project/agent-tools-mcp/
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Find x402 / MCP services matching an intent or filter set.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| intent | string | no | What the agent wants to do (English or Chinese). Optional when at least one structured filter is set. Synonym expansion covers twitter↔X↔推特, whale↔巨鲸, price↔价格 etc. |
| top_k | integer | no | Max services to return (default 5, hard cap 25). |
| max_price_usd | number | no | Upper bound on per-call price in USD. |
| category | string | no | Filter (see list_categories). |
| chain | string | no | "base", "polygon", "solana", "arbitrum", ... |
| min_confidence | number | no | Minimum confidence (0.0–1.0). 0.8+ keeps only services x402scan rates as high-quality. |
| has_mcp | boolean | no | When true, return only services with a callable MCP endpoint. Use this when the agent wants to chain another MCP server rather than perform raw HTTP+x402. |
Ask for the best x402/MCP services for an agent intent.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| intent | string | yes | Natural-language job the agent wants to accomplish. |
| top_k | integer | no | Max recommendations to return (1-10). |
| max_price_usd | number | no | Optional per-call budget cap. |
| category | string | no | Optional directory category filter. |
| chain | string | no | Optional payment network filter, e.g. "base" or "solana". |
| require_healthy | boolean | no | When true, only consider services marked health=ok. |
| min_confidence | number | no | Optional x402scan quality floor (0.0-1.0). |
| has_mcp | boolean | no | When true, only consider services with MCP endpoints. |
| use_llm | boolean | no | Set false for deterministic retrieval-only fallback. |
Get full details + ready-to-paste call template for a service.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | Service slug as returned by search items. |
List all available service categories in the directory.
Takes no parameters.
High-level stats about the directory: total services, healthy count, sources.
Takes no parameters.
Find MCP servers in the directory.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| intent | string | no | Natural-language description of the tool/capability needed. |
| top_k | integer | no | Max servers to return (1-20). |
| chain | string | no | Optional payment-network filter for paid MCP servers. |
| require_healthy | boolean | no | When true, only return servers marked health=ok. |
Get the full card for one MCP server by slug.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | — |
Find A2A agents you can delegate a task to.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| intent | string | no | Natural-language description of the task to delegate. |
| top_k | integer | no | Max agents to return (1-20). |
| x402_only | boolean | no | When true, only return agents that advertise x402 payment. |
Unified search across x402 services, MCP servers and A2A agents.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| intent | string | no | Natural-language query. |
| protocol | string | no | Optional filter: "x402", "mcp" or "a2a". |
| top_k | integer | no | Max resources to return (1-50). |
Self-register an x402 / MCP service in the agent-tools directory.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | Public HTTPS URL of the service (the x402-payable endpoint or its homepage). Required. |
| name | string | no | Human-friendly name. Defaults to the URL hostname. |
| description | string | no | One-paragraph description (max ~2000 chars). |
| mcp_url | string | no | If the service speaks MCP, its streamable-http endpoint. |
| category | string | no | Free-form (e.g. "defi", "search", "social"). Use list_categories to align with existing taxonomy. |
| chains | array | no | Networks the service accepts payment on (e.g. ["base", "solana"]). |
| price_min_usdc | number | no | Lower bound of per-call price in USDC. |
| price_max_usdc | number | no | Upper bound of per-call price in USDC. |
| contact | string | no | Optional email / handle the directory team can reach you on for clarifications. |
Check an MCP server for malware / prompt-injection lures by its endpoint URL.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| endpoint_url | string | yes | The MCP server's streamable-http URL (required). This is the identity we look up / index by. |
| name | string | no | Optional advertised name (used when the server is new and gets added; falls back to the URL host). |
| description | string | no | Optional description / README blurb (scanned when new). |
| tools_text | string | no | Optional tool names + descriptions; used only if the live probe cannot fetch the server's tools/list. |
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
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 Apache-2.0
- 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 agent-tools (x402 + MCP + A2A directory) 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 0.4.0 · scanned 29 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 digest8e10acffb39885b966b2ddc1c79a315dc8bb70fd1a475cabd7f57dc9cb298986
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 surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (14 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. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| search | no tags | |
| get | no tags | |
| list_categories | no tags | |
| search_mcp_servers | no tags | |
| get_mcp_server | no tags | |
| search_agents | no tags | |
| get_agent | no tags | |
| search_all | no tags | |
| stats | no tags | |
| ask | no tags | |
| recommend | no tags | |
| prepare_paid_verification | no tags | |
| execute_paid_verification | no tags | |
| get_paid_verification | 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 digest8e10acffb39885b9
Scanned2026-10-29
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 0.4.0. Pin a release below and the command asks for exactly that one.
0.4.0
29 Oct 2026
latestNo release note was published with this version.
0.3.0
29 Oct 2026
- Works with mcp 1.x and 2.x (no more pinning mcp<2); new ask and recommend tools for plain-language and price-capped picks.
—
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 agent-tools (x402 + MCP + A2A directory) 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.