Markdown · Editable
MCP security checklist
Review identity, tool permissions, supply chain and audit coverage before connecting a server.
Download Markdown: MCP security checklist Read the MCP security guide
Resources
Resources
The guides, documentation and trust material behind governing AI agents and MCP servers.
Start with a free security resource
Download a checklist or run a local example. No email or signup required.
Review identity, tool permissions, supply chain and audit coverage with an editable worksheet for your team.
Reproduce token and scope failures locally with synthetic inputs and 21 self-checks. Requires Node.js 18 or later; this is a teaching fixture, not a production MCP server.
Put the guidance to work
Editable templates for your next security review, vendor evaluation or incident drill. Download them and make them your own.
CSV · Editable
AI-agent procurement scorecard
Compare vendors against your requirements, record evidence and make critical gaps visible.
Download CSV: AI-agent procurement scorecard Read the procurement guideMarkdown · Editable
AI incident-response worksheet
Capture the timeline, contain affected agents and agree on evidence and recovery criteria.
Download Markdown: AI incident-response worksheet Read the incident-readiness guideNode.js · Editable
MCP authorization lab
Reproduce token and scope failures locally with synthetic inputs and 21 self-checks. Requires Node.js 18+.
Download Node.js: MCP authorization lab Read the troubleshooting guideMarkdown · Editable
Agent Skill review worksheet
Record reviewed files, requested access, enforced permissions, and allowed and denied runtime tests.
Download Markdown: Agent Skill review worksheet Read the Skills review guideNode.js · Editable
Signed audit verification lab
Run nine synthetic cases to see signature failures, broken chains, and tail-truncation limits. Tested with Node.js 26.10.0.
Download Node.js: Signed audit verification lab Read the audit verification exampleBrowse
Guides
- Agent identityThe non-human identity lifecycle: scoped credentials, rotation, revocation.
- MCP security: server governance guideBringing MCP servers under governance: authentication, tool scoping, limits.
- Runtime policyHow a call is evaluated, and what passed, redacted and blocked mean.
Developer resources
- DocumentationQuickstarts, concepts and setup for agents, clients and runtimes.
- SDKsInstall the runtime in the language your agent already runs in.
- FrameworksWhat to wire up for LangGraph, CrewAI, OpenAI Agents and the rest.
- ExamplesCredential-free client configurations and connector source.
Security & trust
- Trust CenterWhat we do and do not attest to, hosting, controls and legal documents.
- ArchitectureControl plane, runtime plane and evidence plane, and how data flows.
- Audit verificationCheck an exported audit bundle offline, without us.
- Compliance mappingsHow the controls line up with SOC 2, the EU AI Act, ISO 42001 and more.
Tools
- Tools & templatesEditable security checklists, procurement scorecards and incident worksheets.
- Maturity assessmentScore your AI governance and get a prioritized next-steps list.
- Cost calculatorEstimate agent fleet spend and runaway-cost exposure.
Secure your first production agent.
Create your workspace, connect one agent, and inspect the decisions it produces.