ToolVet
Measured conclusion: Deep-tested. L2 outcome: tools_ok.
The vetted directory of paid APIs and MCP servers for AI agents.
| Author | app.toolvet |
|---|---|
| Access | remote |
| Publisher key required | No |
| Measured state | Deep-tested |
| L1 liveness | alive |
| L1 latency | 1935 ms |
| Last measured | 2026-10-26 |
Add to your agent
Copy this into your MCP client config:
{
"mcpServers": {
"ToolVet": {
"url": "https://toolvet.app/mcp",
"transport": "streamable-http"
}
}
}
Measured tools (8)
list_categoriesread-onlyFree. Categories in the directory with how many services each has.
Hints: read-only yes · destructive no · idempotent not declared · open-world no
get_serviceread-onlyFree. Basic facts about one listing by id: kind, URL, price, trust score and live status. Use get_service_report for history and security findings.
Parameters:
id(required) — string — Service id (slug)
Hints: read-only yes · destructive no · idempotent not declared · open-world no
scan_mcp_serverread-onlyFree. Connects to a remote MCP server (Streamable HTTP) the way an agent would, reads its tool definitions and instructions (up to a size limit) without calling any tool, and checks them for tool poisoning: hidden instructions, invisible characters, requests for credential files and more. Returns a grade A to F with findings, and says when part of the definitions was too large to check. Limited per IP.
Parameters:
url(required) — string — The remote MCP server URL, for example https://example.com/mcp
Hints: read-only yes · destructive no · idempotent not declared · open-world yes
get_service_statusread-onlyFree. Is a listed service up right now? Its state (up, degraded, down, or unknown when not checked yet), since when, the latest check, uptime over 24 hours, 7 and 30 days, and recent outages, from ToolVet's own checks.
Parameters:
id(required) — string — Service id (slug)
Hints: read-only yes · destructive no · idempotent not declared · open-world no
search_servicesread-onlySearch vetted, live-monitored x402 APIs and MCP servers. Returns listings ranked by relevance, trust score and usage, each with price, live status and how to call it; sponsored listings come in a separate list. For one pick for a task, use recommend_service. Costs $0.003 via x402. Each IP address gets 10 free searches a day.
Parameters:
query(required) — string — What the service should dokind— string — x402 for pay-per-call HTTP APIs, mcp for MCP serverslimit— integer — Number of results, 1 to 25 (default 10)network— string — CAIP-2 network your wallet pays on, e.g. eip155:8453max_price_usd— number — Maximum price per call in USD
Hints: read-only yes · destructive no · idempotent not declared · open-world no
recommend_serviceread-onlyGet the best 3 live, trustworthy services for a task, with reasons and call instructions. Use it when you have one concrete task; use search_services to compare more options. Costs $0.01 via x402.
Parameters:
task(required) — string — The task in plain languagekind— string — x402 for pay-per-call HTTP APIs, mcp for MCP serversnetwork— string — CAIP-2 network your wallet pays on, e.g. eip155:8453max_price_usd— number — Maximum price per call in USD
Hints: read-only yes · destructive no · idempotent not declared · open-world no
get_service_reportread-onlyFull vetting report for one service (uptime, latency, price history, security findings). Takes an id from search or recommend results. Costs $0.002 via x402.
Parameters:
id(required) — string — Service id (slug) from search results
Hints: read-only yes · destructive no · idempotent not declared · open-world no
preflight_checkread-onlyLive-check an x402 URL before paying it: valid challenge, real price, token, pay-to match. Sends one unpaid request to the URL and compares the answer with our records; the verdict is ok, caution or avoid. Costs $0.005 via x402.
Parameters:
url(required) — string — The x402 endpoint you are about to paymethod— string — HTTP method of the paid call (default: the listing's method when the URL is listed, else GET)
Hints: read-only yes · destructive no · idempotent not declared · open-world yes
Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.