ClientProof is answering right now. Last checked 9 min ago.
Read-only tools for agency testimonial walls: list clients, testimonials, and embed widgets.
Today is the operative word: we check ClientProof every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 9 min ago.
claude mcp add clientproof --transport http https://useclientproof.com/api/mcp
{
"mcpServers": {
"clientproof": {
"url": "https://useclientproof.com/api/mcp"
}
}
}
[mcp_servers.clientproof]
url = "https://useclientproof.com/api/mcp"
{
"mcpServers": {
"clientproof": {
"url": "https://useclientproof.com/api/mcp"
}
}
}
{
"mcpServers": {
"clientproof": {
"url": "https://useclientproof.com/api/mcp"
}
}
}
This endpoint answered with an authorization challenge. The server is running, and it signs you in through your browser: there is no API key to paste.
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://useclientproof.com/api/mcp | streamable-http | sign-in | 294 ms | 9 min ago |
Read-only evidence for the tools agents run: MCP server records, coverage and policy.
Read-only VMware vCenter/ESXi monitoring, 32 MCP tools; vSphere calls allowlist-gated in tests.
Read-only tools to inspect your agent setup: list MCP servers, flag unpinned ones, test a policy.
Self-healing CI tests and proof of work for AI agents
Local multi-channel message emulator for E2E testing, with MCP tools for LLM agents.
Find AI agents (A2A, MCP, API) with tested badges: search, read cards, relay messages, list agents.
Kineti: spend cap, undo, and test proof for AI coding agents
Approval layer for AI agent payments: budgets, rules, human approval. Sandbox, test credentials.
Answers built from our own checks of this server.