← Registry

General Tools

agent-tools.cloud

Discover and query MCP services in a directory.

1 endpoint11 known toolsFirst detected July 25, 2026Last detected August 29, 2026

ENDPOINT 1

https://agent-tools.cloud/mcp-discovery

No auth detected

MCP server metadata

Name
agent-tools
Version
1.27.1
Capabilities
experimentalpromptsresourcestools
Server instructions

Directory of x402-paid + MCP services on agent-tools.cloud. Built for AGENT consumers — humans use the website, agents use these tools. Typical flow: 1. `ask_services(intent=...)` for an LLM-ranked recommendation, or `search(intent=..., has_mcp=True)` to manually inspect candidates. 2. Inspect `match_reason` + `confidence` + `tx_30d` on each item to judge quality. Prefer `popular+healthy` items. 3. `get(slug)` to fetch the service card: payment, call, quality, resource samples, and ready-to-paste MCP/x402 call hints. 4. Use `list_categories` to discover the taxonomy and `stats` for directory size + health. 5. `scan_mcp_safety(endpoint_url)` screens an MCP server for malware / prompt-injection lures: returns our latest stored verdict if it is already indexed, otherwise probes + scans it live and adds it to the directory.

Known tools 11

search

Find x402 / MCP services matching an intent or filter set.

Inferred read-only
ask_services

Ask for the best x402/MCP services for an agent intent.

Inferred read-only
get

Get full details + ready-to-paste call template for a service.

Inferred read-only
list_categories

List all available service categories in the directory.

Inferred read-only
stats

High-level stats about the directory: total services, healthy count, sources.

Inferred read-only
search_mcp_servers

Find MCP servers in the directory.

Inferred read-only
get_mcp_server

Get the full card for one MCP server by slug.

Inferred read-only
search_a2a_agents

Find A2A agents you can delegate a task to.

Inferred read-only
search_resources

Unified search across x402 services, MCP servers and A2A agents.

Inferred read-only
register

Self-register an x402 / MCP service in the agent-tools directory.

Inferred read-only
scan_mcp_safety

Check an MCP server for malware / prompt-injection lures by its endpoint URL.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.agent-tools]
url = "https://agent-tools.cloud/mcp-discovery"
enabled = true
Claude Code

.mcp.json

{
  "mcpServers": {
    "agent-tools": {
      "type": "http",
      "url": "https://agent-tools.cloud/mcp-discovery"
    }
  }
}
Claude Desktop

Settings → Connectors → Add custom connector

Name: agent-tools
Remote MCP URL: https://agent-tools.cloud/mcp-discovery

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "agent-tools": {
      "url": "https://agent-tools.cloud/mcp-discovery"
    }
  }
}
Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code
{
  "servers": {
    "agent-tools": {
      "type": "http",
      "url": "https://agent-tools.cloud/mcp-discovery"
    }
  }
}
Generic MCP

Client-specific MCP configuration

{
  "name": "agent-tools",
  "transport": "streamable-http",
  "url": "https://agent-tools.cloud/mcp-discovery"
}
MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for agent-tools.cloud was fetched 2026-08-27T23:52:37.263Z.

Trust status Neutral

agent-tools.cloud is assessed as Neutral: No suspicious signals found, but no strong positive signal either

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.