Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

agent-tools (x402 + MCP + A2A directory)

PYPI · AGENT-TOOLS-MCP · 2 COMPONENTS

Discover x402 services, MCP servers and A2A agents by intent — agent-tools.cloud directory.

+4 this week 76 Trust /100

Last scanned (21 hours ago)

Scores higher than 69% of PyPI servers

Category Search and Retrieval

Recent critical change

GHSA-6q48-6c7w-9gw2 affects this package (21 Oct 2026). See the changelog before you install this server.

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs hatchling.build at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
  • 1 of 31 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability66
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 1843 tokens (~115/item across 16 items; 16 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management77
  • Stability observed for 23 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage71
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 0% of tool parameters carry a description.Fail
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "execute_paid_verification" implies "execute" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 17 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
What we tested

Checks we ran (16)

  • Malware scan
  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 21 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

  • 19 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.

  • 17 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.

  • 15 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

  • 14 Nov 26 0
    • Package version: 0.5.1 → 0.5.2 functional
  • 13 Nov 26 0
    • Schema quality: 1580 → 1843 ▼ functional
    • Package version: 0.4.0 → 0.5.1 functional
  • 12 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

  • 10 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Analysed pypi/agent-tools-mcp@0.5.2

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem pypi
Reason No attestation published

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend Known build tool hatchling.build

Background: Why install scripts are a supply-chain risk →

Dependencies 31 packages
Packages resolved 31
No linked repository 1
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 16 exposed · ~1,691 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
ask ~225

Ask in plain language which **x402 / MCP services** best fit a task. Returns a short written `answer` plus the ranked services it is based on. Use this when you want a recommendation, not just a raw search list. Args: question: The task, e.g. "translate a document to Japanese under $0.05". top_k: Max number of recommended services (default 5, max 10). max_price_usd: Optional upper bound on per-call price in USD. chain: Optional settlement chain filter (e.g. "base", "solana"). category: Optional category filter (see `list_categories`). require_healthy: Only consider services whose latest probe was healthy. use_llm: Set false for a faster deterministic ranking without the written answer.

NameTypeReqDescription
category–––
chain–––
max_price_usd–––
questionstringyes–
require_healthyboolean––
top_kinteger––
use_llmboolean––

Structured output declared, but exposes no named fields.

No examples provided.

create_api_key ~106

Create a free agent-tools.cloud account API key. No sign-up needed. The key is returned once and cannot be recovered. Store it (for example as AGENT_TOOLS_API_KEY); do not print it back to the user or into logs. It unlocks complete `directory_stats` lists and paid verification. A few keys per IP per day. Args: name: Optional label to recognise the key later, e.g. your agent name.

NameTypeReqDescription
name–––

Structured output declared, but exposes no named fields.

No examples provided.

directory_stats ~157

Daily statistics on the agent-tool ecosystem as seen by our probes. Counts (indexed, reachable, protocol-verified, ready), findings, probe outcomes and top searches. With an account key the topic and search lists are complete; without one they are shortened. Args: view: "all", "mcp", "x402" or "a2a". topic: Optional topic word (e.g. "payment", "weather") for that topic instead. month: Optional "YYYY-MM" for that monthly report instead. api_key: Optional; defaults to AGENT_TOOLS_API_KEY.

NameTypeReqDescription
api_key–––
month–––
topic–––
viewstring––

Structured output declared, but exposes no named fields.

No examples provided.

execute_paid_verification ~116

Send the signed payment to the service once and score the result. Aborts without paying if price or recipient changed. Never retried; a timeout returns `indeterminate`. Args: id: `id` from `prepare_paid_verification`. signature: 0x EIP-712 signature of its `typed_data` by the payer. api_key: Optional; defaults to AGENT_TOOLS_API_KEY.

NameTypeReqDescription
api_key–––
idstringyes–
signaturestringyes–

Structured output declared, but exposes no named fields.

No examples provided.

get ~35

Get full details (URL, price, schema, call template) of an x402 service by slug.

NameTypeReqDescription
slugstringyes–

Structured output declared, but exposes no named fields.

No examples provided.

get_agent ~37

Get the full A2A agent card (endpoint, skills, auth, x402 info) by slug.

NameTypeReqDescription
slugstringyes–

Structured output declared, but exposes no named fields.

No examples provided.

get_mcp_server ~35

Get full details (endpoint URL, transport, capabilities) of an MCP server by slug.

NameTypeReqDescription
slugstringyes–

Structured output declared, but exposes no named fields.

No examples provided.

get_paid_verification ~55

Read one of your own paid verifications. Args: id: Verification id. api_key: Optional; defaults to AGENT_TOOLS_API_KEY.

NameTypeReqDescription
api_key–––
idstringyes–

Structured output declared, but exposes no named fields.

No examples provided.

list_categories ~19

List all available x402 service categories in the directory.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

prepare_paid_verification ~143

Quote a sponsored paid verification of an x402 service. You pay the service once from your own wallet (Base USDC, <= $1; funds go to its payTo). Sign the returned `typed_data` (EIP-712), then call `execute_paid_verification` before `valid_before`. Never signs or pays for you. Args: slug: Service slug from `search` / `get`. payer: 0x address of the paying wallet. api_key: Optional; defaults to AGENT_TOOLS_API_KEY.

NameTypeReqDescription
api_key–––
payerstringyes–
slugstringyes–

Structured output declared, but exposes no named fields.

No examples provided.

recommend ~172

Get a **scored shortlist of x402 services** with price and payment hints. Each recommendation carries a `score`, `price_hint` and `pay_hint`. This is discovery only: nothing is paid; settle with your own x402 client. Args: intent: What the agent wants to do, plain language. top_k: Max number of recommendations (default 5, max 20). max_price_usd: Optional upper bound on per-call price in USD. chain: Optional settlement chain filter (e.g. "base"). require_healthy: Only include services whose latest probe was healthy.

NameTypeReqDescription
chain–––
intentstringyes–
max_price_usd–––
require_healthyboolean––
top_kinteger––

Structured output declared, but exposes no named fields.

No examples provided.

search ~162

Find **x402 paid services** matching a natural-language intent. x402 services are HTTP APIs the agent pays for per call (USDC on Base etc.). Args: intent: What the agent wants to do, in plain English or Chinese (e.g. "fetch user tweets", "check on-chain whale activity"). top_k: Max number of services to return (default 5, max 25). max_price_usd: Hard upper bound on per-call price in USD. Services whose cheapest call exceeds this are filtered out. category: Optional category filter (see `list_categories`).

NameTypeReqDescription
category–––
intentstringyes–
max_price_usd–––
top_kinteger––

Structured output declared, but exposes no named fields.

No examples provided.

search_agents ~137

Find **A2A agents** (peer agents) the agent can delegate a task to. A2A agents publish an agent-card and an A2A JSON-RPC endpoint; use this when the task is better handed off to another agent than called directly. Args: intent: The task or capability to delegate, plain language. top_k: Max number of agents to return (default 5, max 25). x402_only: If true, only return agents that accept x402 payment.

NameTypeReqDescription
intentstringyes–
top_kinteger––
x402_onlyboolean––

Structured output declared, but exposes no named fields.

No examples provided.

search_all ~134

Unified search across **x402 services, MCP servers and A2A agents**. Use this when you don't yet know which resource type fits best — it ranks all three together and tags each result with its `protocol`. Args: intent: What the agent wants to accomplish, plain language. protocol: Optional filter, one of "x402", "mcp", "a2a". Omit for all. top_k: Max number of results to return (default 8, max 50).

NameTypeReqDescription
intentstringyes–
protocol–––
top_kinteger––

Structured output declared, but exposes no named fields.

No examples provided.

search_mcp_servers ~132

Find **MCP servers** (tool/context servers) matching an intent. Use this when the agent wants extra tools or context via the Model Context Protocol, rather than a one-shot paid HTTP call. Args: intent: What capability the agent is looking for, plain language. top_k: Max number of servers to return (default 5, max 25). chain: Optional chain filter for x402-capable MCP servers (e.g. "base", "solana").

NameTypeReqDescription
chain–––
intentstringyes–
top_kinteger––

Structured output declared, but exposes no named fields.

No examples provided.

stats ~26

Directory-wide stats across all protocols: x402 services, MCP servers, A2A agents.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

Install

How do I install the agent-tools (x402 + MCP + A2A directory) server?

agent-tools (x402 + MCP + A2A directory) runs locally as a PyPI package, launched with uvx agent-tools-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · agent-tools-mcp

# add to Claude Code
claude mcp add agenttools-cloud-agent-tools-mcp -- uvx agent-tools-mcp
Common questions

What is the agent-tools (x402 + MCP + A2A directory) server?

agent-tools (x402 + MCP + A2A directory) is listed in the public MCP registry as io.github.AgentTools-Cloud/agent-tools-mcp. Discover x402 services, MCP servers and A2A agents by intent, agent-tools.cloud directory. This page covers its PyPI package (agent-tools-mcp).

Is the agent-tools (x402 + MCP + A2A directory) server safe to use?

agent-tools (x402 + MCP + A2A directory) scores 76 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the agent-tools (x402 + MCP + A2A directory) server expose?

agent-tools (x402 + MCP + A2A directory) exposes 16 tools: search, get, list_categories, search_mcp_servers, get_mcp_server, and 11 more. Their descriptions and schemas cost roughly 1,691 tokens of context every time the server is loaded.

Is the agent-tools (x402 + MCP + A2A directory) server still maintained?

agent-tools (x402 + MCP + A2A directory) is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the agent-tools (x402 + MCP + A2A directory) server under?

agent-tools (x402 + MCP + A2A directory) declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

What did VerifyMCP test on the agent-tools (x402 + MCP + A2A directory) server?

VerifyMCP ran 16 checks on agent-tools (x402 + MCP + A2A directory), covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.