$ loading_
Enforce runtime tool-call policies and security scans for AI agents.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "Toolguard" yet — see the docs or source repo.
Configure Toolguard for my AI agent to allow only read_file and web_search, deny shell_exec and external network write actions, and provide an example policy.
A sample policy with clear allow and deny rules to restrict the agent’s tool permissions.
Use Toolguard to run a security scan on the current repository, detect risky markers like TODO, FIXME, and XXX, and summarize findings by file, line number, and severity.
A structured scan report listing matched risk markers, their locations, and priorities.
When the AI agent attempts to call an unauthorized tool, use Toolguard to block the request, record the violation reason, and return an example auditable event log format.
An explanation of the blocking flow plus an audit log example including timestamp, tool name, and reason.
Intercept and block MCP tool calls with YAML policies for safer AI agents.
Enforce permissions, approvals, sanitization, and audit for AI agent MCP calls.
Manage notes securely with policy controls, approvals, and prompt injection detection.
Audit MCP servers and AI packages for security and supply chain risks.
Add security scanning, risk gating, and safe execution to MCP tool calls.
Securely expose OpenAPI endpoints as MCP tools with auth, limits, and auditing.