Mandat releases AI Agent authorization and audit tool
Understand this story
Mandat has released a set of authorization, delegation, and audit tools for AI agent operations, with priority support for MCP. It enforces policies by parameter on every tool call: for refunds, for example, amounts up to €50 are allowed, €50 to €500 are escalated to human handling, and amounts over €500 are rejected; it also issues short-lived single-task tokens, records the human→agent→sub-agent chain, and leaves a tamper-proof audit record for each call that can be exported to a SIEM. The tool is released under the Apache-2.0 license. The command-line tool is installed globally via npm and requires Node ≥ 20; the Python library for MCP servers built with the official mcp SDK is installed via pip and requires Python ≥ 3.10; running the full demo from a cloned repository requires Node ≥ 23.6 and no installation.
AI overview based on source reports · Updated 23 hr ago
Coverage timeline
Follow the coverage to explore different perspectives.
- Hacker News AIMandat – Authorization, delegation and audit for AI agent actions
Mandat is an MCP-first tool that checks a policy on every AI agent tool call (e.g., refunds ≤ €50 allowed, €50–500 require a human, > €500 denied), issues short-lived single-task tokens carrying the human → agent → sub-agent chain, and records each call in a tamper-evident audit log exportable to a SIEM. It also ships a scanner for authentication and supply-chain mistakes in MCP servers and client configs, and is installable via npm or pip with an Apache-2.0 license.
Activity for this story
- Current comparable activity
- 5
- Peak comparable activity
- 10Nov 13 23:00
- Change in the past 24 hours
- –
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.