Integration · Developer tools
Connect Claude & ChatGPT to AxioRank
Ask your AI whether a tool call would be allowed, which calls were denied yesterday, or whether an external agent can be trusted, and get the answer from AxioRank. It can ask for a verdict (allow, deny or hold) on a tool call or MCP tool call, check approvals on hold, read audit logs and verifiable receipts, and look up servers in the public tool-definition transparency log.
Free plan, no credit card. Takes about a minute.
Try asking
“Would AxioRank allow a call to delete_customer with id 42?”
The AI sends the tool name and arguments to AxioRank and returns the verdict: allow, deny or hold.
“Which tool calls were denied in the last 24 hours?”
It lists audit log entries from the last 24 hours with decision deny.
“Has the call on hold with approval apr_123 been approved yet?”
It checks the status of the approval and tells you where it stands.
What your AI can do
Tool call checks
Ask for a verdict on a tool call or an MCP tool call before it runs, and check the status of calls held for approval.
Audit logs
List audit log entries by time range, decision or source, and get a verifiable receipt for any entry.
Trust and transparency
Preflight external agents and servers, list covered protocols, and read servers and tool-definition history from the public transparency log.
“Get me the receipt for audit log entry 9f81.”
It fetches a verifiable receipt for that audit log entry.
“Can we trust this agent before we connect it? Here is its URL.”
It runs a preflight on the agent or server and returns AxioRank's trust assessment.
“Has mcp.example.com changed its tool definitions?”
It reads the history of tool definitions that server has published in the transparency log.
9 tools for AxioRank
These tools are switched on when you connect. You can switch any of them off, or require your approval before it runs.
check_agent_trustVisible to othersPreflight an external agent or server before trusting it: pass its url (or a document) and optionally the protocol, and get a trust assessment.check_mcp_tool_callChanges dataAsk AxioRank for a verdict on a tool call to an MCP server. Pass the tool name and server, and optionally the arguments. The check is recorded in the audit log.check_tool_callChanges dataAsk AxioRank for a verdict (allow, deny or hold) on a tool call before an agent runs it. Pass the tool name and optionally its arguments, intent and model. The check is recorded in the audit log.get_approval_statusCheck the status of a tool call that was put on hold for approval, by approval_id.get_audit_receiptGet a verifiable receipt for one audit log entry by audit_log_id.get_server_tool_historyGet the history of tool definitions published by one server, by host name.list_audit_logList audit log entries of AI agent tool calls between from and to (ISO timestamps), optionally filtered by decision (allow, deny, hold) or source. Needs an API key with the logs:read scope.list_logged_serversList servers recorded in the public tool-definition transparency log.list_protocolsList the agent protocols AxioRank covers.
Set up in three steps
- 1
Pick the app
Create a free PipMCP account and choose AxioRank from the app list.
- 2
Paste your key
Paste your AxioRank API key (it starts with axr_live_). In the AxioRank dashboard go to Outbound > Agents > Create Agent and copy the key. It is shown only once. Reading audit logs needs a key with the logs:read scope.
- 3
Add the link to your AI
You get a personal MCP link. Add it to Claude, ChatGPT or Cursor:
- Click your name, then Settings › Connectors › Add custom connector.
- Paste your link as the Remote MCP server URL.
- Switch it on from the + menu in a chat.
Questions
What can the AI do in AxioRank?
The AI can ask AxioRank for a verdict on a tool call or MCP tool call, check approvals on hold, list audit logs, get audit receipts, list covered protocols, read servers and tool-definition history from the transparency log, and run a trust preflight on an external agent or server.
Does the AI see my AxioRank credentials?
No. Your AxioRank API key is encrypted at rest and never shown to the AI. After you save it, it is not shown again, not even to you. The AI only sees the results of the tools it calls.
Can I control what the AI is allowed to do?
Yes. You choose which tools are switched on, so you can start with audit logs and lookups only. Checking an external agent sends its URL or document to AxioRank and can require your approval before it runs. Every tool call is logged in PipMCP.
Does it work with ChatGPT?
Yes. In ChatGPT go to Settings › Apps & Connectors › Advanced and turn on Developer mode, then add your PipMCP link. Developer mode needs a paid ChatGPT plan: Plus, Pro, Business or Enterprise. The same link also works in Claude (Settings › Connectors › Add custom connector), Cursor and other MCP clients.
What does it cost?
PipMCP has a free plan with no credit card required. Paid plans bill per completed task. You also need your own AxioRank account.
Why does the AI get an error when it reads audit logs?
Audit-log reads need an AxioRank API key with the logs:read scope. If your key does not have it, create a key that does in the AxioRank dashboard and paste it into PipMCP instead. The other tools work without that scope.
Let your AI work in AxioRank today.
Start free. Your key stays encrypted, and you decide what the AI may do.
Connect AxioRank freePipMCP is not affiliated with AxioRank. Product names are trademarks of their owners.