Agentdataboundary MCP is listed as active in the registry but did not answer our last check. It exposes 4 tools. Last commit 19 May 2026.
Permission boundary receipts for ChatGPT agents.
Over the last week it answered 0.0% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 8 min ago.
claude mcp add agentdataboundary-mcp --transport http https://agentdataboundary.clauxel.com/mcp
{
"mcpServers": {
"agentdataboundary-mcp": {
"url": "https://agentdataboundary.clauxel.com/mcp"
}
}
}
[mcp_servers.agentdataboundary-mcp]
url = "https://agentdataboundary.clauxel.com/mcp"
{
"mcpServers": {
"agentdataboundary-mcp": {
"url": "https://agentdataboundary.clauxel.com/mcp"
}
}
}
{
"mcpServers": {
"agentdataboundary-mcp": {
"url": "https://agentdataboundary.clauxel.com/mcp"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
export_remediation_plan
flag_sensitive_fields
map_permissions
summarize_boundary
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://agentdataboundary.clauxel.com/mcp | streamable-http | answering | 12 ms | 8 min ago |
Decision-assurance for AI agents: an auditable action boundary + receipt before it acts.
Signed, hash-chained provenance receipts for AI agent actions.
A trusted local encrypted execution boundary for AI agents.
Persistent memory for AI agents across Claude, ChatGPT and any MCP client.
ERC-7303 token-controlled roles for AI agents: grant, check, and revoke permissions on-chain
Outbound US/CA fax for agents: quote PDF, pay via MPP, get delivery receipt.
Identity and auth for AI agents: credentials, tokens, delegations, and permission checks.
Credential isolation for AI agents. Inject secrets at the network boundary.
Answers built from our own checks of this server.