# Aspex

- [Know what your agents can do. Know what they actually did.](https://aspex.mintlify.app/introduction.md): Aspex is a local security debugger for AI agents. It reads the MCP configs and client logs already on your machine and reasons about them together: offline, deterministic, one binary.
- [Quickstart](https://aspex.mintlify.app/quickstart.md): Install, see what your agents did, scan what they could do. About a minute.
- [Common workflows](https://aspex.mintlify.app/guides/common-workflows.md): Task first, command second. What you want to do, and where to start.
- [Install](https://aspex.mintlify.app/install.md): One Go binary for macOS, Linux and Windows. The download is the only network call Aspex ever makes.
- [How Aspex reasons](https://aspex.mintlify.app/concepts/how-aspex-reasons.md): Every conclusion is a deterministic function of local data. This page names the model and the code paths, so you can reproduce any finding.
- [Capabilities and attack paths](https://aspex.mintlify.app/concepts/capabilities-and-attack-paths.md): What a server can do, with evidence, and what two of them can do together.
- [Observed vs inferred](https://aspex.mintlify.app/concepts/observed-vs-inferred.md): How aspex trace labels what it can show, what it infers, and what it cannot know.
- [Score and blast radius](https://aspex.mintlify.app/concepts/score-and-blast-radius.md): What the 0–100 score measures, why an attack path caps it, and what the blast radius factors are.
- [aspex (front door)](https://aspex.mintlify.app/tools/launcher.md): Run aspex with no arguments: see what your agents did this month, then pick a tool.
- [aspex scan](https://aspex.mintlify.app/tools/scan.md): Every configured server, its live tool list, the attack paths they compose, and the blast radius. Offline; nothing is sent anywhere.
- [scan subcommands](https://aspex.mintlify.app/tools/scan-subcommands.md): hooks, inspect, inventory, attack-paths, shadow, phantom, fix env, cron, install-hook and the rest of aspex scan.
- [aspex trace](https://aspex.mintlify.app/tools/trace.md): What did your agents actually do? A full audit trail from the logs your AI clients already write. No proxy, no config change.
- [aspex explain](https://aspex.mintlify.app/tools/explain.md): Ask a security question about your agent environment and get a deterministic answer computed from the capability graph. No LLM.
- [aspex simulate](https://aspex.mintlify.app/tools/simulate.md): Counterfactual security analysis: what would happen to your attack surface if you changed something. Nothing is modified.
- [lock, verify, diff](https://aspex.mintlify.app/tools/change-detection.md): Change security for agent environments: a lockfile of what your agents can do, drift explained in security terms, and a security-impact diff between git revisions.
- [aspex explore](https://aspex.mintlify.app/tools/explore.md): A local, loopback-only session explorer: timeline, provenance, kill chains, capability graph, and findings that separate observed from inferred.
- [aspex tighten](https://aspex.mintlify.app/tools/tighten.md): Least-privilege recommendations from what is configured versus what your agents actually used.
- [aspex bom](https://aspex.mintlify.app/tools/bom.md): Agent Security Bill of Materials: a portable, versioned description of what constitutes an agent environment.
- [aspex mcp](https://aspex.mintlify.app/tools/mcp.md): Let your agent ask Aspex before it changes its own configuration: a read-only MCP server.
- [aspex doctor](https://aspex.mintlify.app/tools/doctor.md): Fast health check for your AI agent setup
- [aspex-attack](https://aspex.mintlify.app/tools/attack.md): Red-team a live MCP server with adversarial inputs. Advanced, opt-in, only against servers you own.
- [Daily Workflow](https://aspex.mintlify.app/guides/daily-workflow.md): Practical security habits for AI agent users
- [CI integration](https://aspex.mintlify.app/guides/ci-integration.md): Fail the build when a config change introduces a risky MCP server. GitHub Actions, SARIF, baselines, and the pre-commit hook.
- [Policy, baselines and prioritization](https://aspex.mintlify.app/guides/policy.md): Make aspex scan enforce your team's rules, adopt it on an estate with existing findings, and fix the risky servers that are actually in use first.
- [VS Code and Cursor](https://aspex.mintlify.app/guides/vscode.md): aspex scan findings as editor diagnostics, plus the SARIF viewer and pre-commit hook routes that work today.
- [Rules](https://aspex.mintlify.app/reference/rules.md): 225+ rules across three families. Every finding maps to OWASP LLM Top 10 2025, MITRE ATLAS and CWE, and carries a severity.
- [Supported Clients](https://aspex.mintlify.app/reference/clients.md): MCP clients supported by Aspex tools
- [Agent Security Corpus](https://aspex.mintlify.app/reference/corpus.md): A public, tool-agnostic benchmark of agent security scenarios, and Aspex's detection contract.
- [Privacy](https://aspex.mintlify.app/privacy.md): Aspex is fully offline and never sends your data anywhere