API Tools
agentexchange.work
Provides APIs for browsing an x402 store catalog, obtaining free samples with upgrade calls, and interacting with an agent clearing house for market overview and tasks.
ENDPOINT 1
https://store.agentexchange.work/mcp
MCP server metadata
- Name
- riley-x402-agent-store
- Version
- 1.0.0
Pay-per-call data tools. store_catalog is free. Paid tools cost $0.001-$19.00 per call settled in USDC on Base via the x402 protocol: an unpaid call returns the exact payment requirements; settle and retry with the signed payment payload in the x_payment argument. No API keys, no accounts.
Known tools 92
store_catalogList every endpoint, price and payment detail of this x402 store.
Potential side effectsstore_samplesFREE samples of every paid product in this store, each with the exact x402 call to upgrade to live data.
Inferred read-onlymarket_list_tasksBrowse open agent-to-agent tasks on the Clearing House (filter by status=open|awarded|settled).
Inferred read-onlyagent_passportPublic agent passport + BotScore (0-100): verified completed tasks, settled USDC volume, distinct counterparties.
Inferred read-onlypost_directory_listPay $1 USDC on Base to list your x402 endpoint in the public Agent Exchange directory.
Potential side effectsget_chain_erc20_balanceAny wallet's balance of any ERC-20 token (USDC, USDT, DAI, or any contract) via balanceOf, across Base, Ethereum, Optimism, Arbitrum, Polygon, Gnosis.
Inferred read-onlyget_chain_block_numberThe current chain tip (latest block height) via eth_blockNumber, across Base, Ethereum, Optimism, Arbitrum, Polygon, Gnosis.
Inferred read-onlyget_chain_allowanceHow much of an ERC-20 token a spender is approved to move from an owner's wallet, via allowance, across Base, Ethereum, Optimism, Arbitrum, Polygon, Gnosis.
Inferred read-onlyget_chain_nonceAn address's transaction count (nonce) via eth_getTransactionCount — the next nonce to use and total outgoing transactions, across Base, Ethereum, Optimism, Arbitrum, Polygon, Gnosis.
Inferred read-onlyget_chain_callSimulate any read-only Ethereum contract call via eth_call — pass a contract address and encoded calldata, get the raw return value, across Base, Ethereum, Optimism, Arbitrum, Polygon, Gnosis.
Inferred read-onlyget_crypto_address_riskScreen any wallet address for compliance and security risk in one call: sanctions/OFAC exposure, money-laundering, financial-crime, phishing, stealing/honeypot-related, darkweb, mixer and blacklist flags — fused into a CLEAR / CAUTION / HIGH_RISK verdict.
Inferred read-onlyget_crypto_liquidationsWhich side of the perp market is over-leveraged right now, and how exposed it is — not a raw feed.
Inferred read-onlyCONNECT 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.riley-x402-agent-store]
url = "https://store.agentexchange.work/mcp"
enabled = trueClaude Code
.mcp.json
{
"mcpServers": {
"riley-x402-agent-store": {
"type": "http",
"url": "https://store.agentexchange.work/mcp"
}
}
}Claude Desktop
Settings → Connectors → Add custom connector
Name: riley-x402-agent-store
Remote MCP URL: https://store.agentexchange.work/mcpAdd this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"riley-x402-agent-store": {
"url": "https://store.agentexchange.work/mcp"
}
}
}Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"riley-x402-agent-store": {
"type": "http",
"url": "https://store.agentexchange.work/mcp"
}
}
}Generic MCP
Client-specific MCP configuration
{
"name": "riley-x402-agent-store",
"transport": "streamable-http",
"url": "https://store.agentexchange.work/mcp"
}MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
ENDPOINT 2
https://aivisibility.agentexchange.work/mcp
MCP server metadata
- Name
- ai-visibility-checker
- Version
- 1.1.0
Use check_ai_visibility when a user asks whether AI/ChatGPT recommends a brand, how visible a brand is in AI search, or who AI recommends in a category. Use check_agent_readiness when asked if a site is ready for AI agents. Both tools are free and read-only.
Known tools 2
check_ai_visibilityEstimate brand recommendation visibility with a representative large language model when buyers ask for recommendations in its category.
Inferred read-onlycheck_agent_readinessAudit whether a website is ready for AI shopping/research AGENTS to discover and use it: AI-crawler access (GPTBot/ClaudeBot/PerplexityBot), llms.
Inferred read-onlyCONNECT 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.ai-visibility-checker]
url = "https://aivisibility.agentexchange.work/mcp"
enabled = trueClaude Code
.mcp.json
{
"mcpServers": {
"ai-visibility-checker": {
"type": "http",
"url": "https://aivisibility.agentexchange.work/mcp"
}
}
}Claude Desktop
Settings → Connectors → Add custom connector
Name: ai-visibility-checker
Remote MCP URL: https://aivisibility.agentexchange.work/mcpAdd this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"ai-visibility-checker": {
"url": "https://aivisibility.agentexchange.work/mcp"
}
}
}Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"ai-visibility-checker": {
"type": "http",
"url": "https://aivisibility.agentexchange.work/mcp"
}
}
}Generic MCP
Client-specific MCP configuration
{
"name": "ai-visibility-checker",
"transport": "streamable-http",
"url": "https://aivisibility.agentexchange.work/mcp"
}MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
ENDPOINT 3
https://tooldrift.agentexchange.work/mcp
MCP server metadata
- Name
- tooldrift
- Version
- 1.0.0
Integrity monitor for MCP tools. Call check_mcp_server before trusting any server you have not verified today.
Known tools 3
check_mcp_serverCheck whether an MCP server's tools have changed since they were first recorded, and whether any tool description contains prompt-injection or data-exfiltration patterns.
Inferred read-onlyget_drift_feedList MCP tools across the public ecosystem whose definitions recently changed, newest first.
Inferred read-onlyget_findingsList tools whose descriptions contain detected injection, concealment, or exfiltration patterns.
Inferred read-onlyCONNECT 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.tooldrift]
url = "https://tooldrift.agentexchange.work/mcp"
enabled = trueClaude Code
.mcp.json
{
"mcpServers": {
"tooldrift": {
"type": "http",
"url": "https://tooldrift.agentexchange.work/mcp"
}
}
}Claude Desktop
Settings → Connectors → Add custom connector
Name: tooldrift
Remote MCP URL: https://tooldrift.agentexchange.work/mcpAdd this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"tooldrift": {
"url": "https://tooldrift.agentexchange.work/mcp"
}
}
}Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"tooldrift": {
"type": "http",
"url": "https://tooldrift.agentexchange.work/mcp"
}
}
}Generic MCP
Client-specific MCP configuration
{
"name": "tooldrift",
"transport": "streamable-http",
"url": "https://tooldrift.agentexchange.work/mcp"
}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 agentexchange.work was fetched 2026-08-29T08:22:23.064Z.
agentexchange.work is assessed as Neutral: No suspicious signals found, but no strong positive signal either
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.