Mandat adds authorization and audit layer for AI agent tool calls
Start here
Mandat released an open-source (Apache-2.0) authorization, delegation and audit layer for AI agent actions, starting with MCP. Each tool call is checked against a policy on its arguments — for example, allowing refunds up to €50, requiring human approval for €50–500 and denying anything above €500. Agents receive short-lived, single-task tokens that carry the human-to-agent-to-sub-agent chain, and every call leaves a tamper-evident audit record exportable to a SIEM. The release also includes a scanner for authentication and supply-chain mistakes in MCP servers and client configurations. It installs via npm or pip, with TypeScript and Python libraries for the official MCP SDK; the CLI requires Node 20 or later, and the Python library requires Python 3.10 or later.
Generated from reports · updated 1 h ago
Report timeline
Follow the reports to see the event from different sides.
- Hacker News · AIMandat launches authorization, delegation and audit layer for AI agent tool calls, MCP first
Mandat is an open-source (Apache-2.0) tool that adds authorization, delegation and audit to AI agent actions, starting with MCP. Each tool call is checked against a policy on its arguments, such as allowing refunds up to €50, requiring human approval for €50–500 and denying anything above €500, while agents receive short-lived single-task tokens carrying the human to agent to sub-agent chain and every call leaves a tamper-evident audit record exportable to a SIEM. It also ships a scanner for authentication and supply-chain mistakes in MCP servers and client configs, and installs via npm or pip with TypeScript and Python libraries for the official MCP SDK.
Heat for this event
Not enough continuous observations yet to draw a trend.