Security runtimes

Security runtimes for AI agents and MCP systems

Start a bounded runtime against your agent, MCP server, or tool-using workflow. Get reproducible findings, signed evidence, and an audit-ready report.

tachyonic — runtime
$ curl -fsSL https://tachyonic.sh/install | bash
$ tachyonic login
$ tachyonic runtime start --target https://your-agent.example.com
$ tachyonic runtime watch <runtime_id>
01 Why now

AI risk moved from prompts to actions.

Modern agents read untrusted context, choose tools, call APIs, use delegated credentials, and act across systems. Existing AppSec tools were built for code, packages, and web endpoints — they do not fully exercise the trust boundaries created when an agent turns instructions into actions.

Tachyonic was built for that surface: agents, MCP servers, tool calls, runtime policy, and evidence that survives review.

02 What you get

From target to signed evidence.

[ 01 ]

Bounded runtime execution

Every runtime starts with explicit target, region, policy, and budget. Duration, tokens, and spend are capped before the run starts. Network egress is deny-default. Credentialed, destructive, and exploit-class actions can pause for approval.

[ 02 ]

Attack coverage for agentic systems

Tests prompt injection, tool abuse, MCP trust-boundary failures, permission escalation, sensitive data disclosure, multi-turn manipulation, and implementation flaws. The scanner covers 210 attack patterns; the full library expands to 237.

[ 03 ]

Signed evidence, not just a PDF

Each runtime emits an artifact bundle: findings, payloads, request and response captures, lifecycle events, logs, runtime policy, and report output — portable across review, remediation, customer assurance, and audit.

[ 04 ]

CLI, API, and dashboard workflows

Run from the terminal, wire into CI, or manage runtimes from the platform. The same runtime surface supports local testing, hosted runtimes, approval review, artifacts, and reports.

03 How it works

Three commands from target to evidence.

01

Start

tachyonic runtime start --target https://your-agent.example.com --region aws-us-east-1

Starts a bounded runtime in the selected region. Policy, budget, and target are explicit. Returns a runtime ID.

02

Watch

tachyonic runtime watch <runtime_id>

Follows the runtime until it reaches a terminal state. Shows status transitions and exits cleanly for CI or scripted workflows.

03

Collect

tachyonic runtime artifacts <runtime_id>

Lists the evidence bundle: findings, report output, request and response captures, logs, and artifact URLs.

04 Runtime controls

The runtime holds the boundary.

Region-pinned execution

Runtimes execute in selected US or EU regions.

Default-deny egress

Network access follows the runtime allowlist.

Approval gates

Credentialed, destructive, and exploit-class actions pause before execution.

Budget enforcement

Runtime duration, tokens, and spend are bounded.

Artifact-backed logs

Runtime logs are captured as evidence artifacts.

Signed evidence

Runtime output is packaged and signed for review and audit trails.

05 For the systems you ship

What Tachyonic tests.

AI coding agents

Before they touch repositories, secrets, or build systems.

MCP servers

Before tools, schemas, and transport boundaries reach production.

Browser and support agents

Before untrusted pages, tickets, emails, or documents become instructions.

Voice agents

Before calls, transcripts, and delegated actions reach production systems.

RAG and tool-enabled apps

Before retrieval, function calls, and actions cross trust boundaries.

Internal agentic workflows

Anything that turns natural language into infrastructure action.

06 Research proof

Backed by published research.

Tachyonic research has produced confirmed vulnerabilities, a source-code-level MCP SDK audit, GitHub security advisories, and public case studies.

8
Published assessments
44+
Confirmed vulnerabilities
6
Targets across studies
237
Attack patterns in library
07 Standards

Mapped to frameworks your team already uses.

Evidence packages support SOC 2, ISO 42001, EU AI Act readiness, customer assurance, and internal review. The product does not replace compliance work — it gives teams reproducible security evidence.

OWASP LLM Top 10 mapped
OWASP Agentic & ASI mapped
MITRE ATLAS mapped
08 Pricing

Start free. Pay by runtime.

Every runtime is priced by scope. Subscribe for a monthly allowance and team features, buy runtimes up front, or pay as you go.

Baseline
$5
Core patterns
Standard
$20
210 patterns
Advanced
$60
Multi-turn + consensus
Comprehensive
$100
Full library + multimodal

Priced by scan scope. EU regions +15%. Start free, then pay as you go or subscribe.

Free
$0
Monthly runtime allowance
Local scanner and CLI reports
Public attack taxonomy coverage
Default region
Get started
Popular
Pro
$99/mo
Allowance, then pay as you go
US and EU regions
Private reports and artifacts
30-day evidence retention
Start Pro
Team
$299/mo
Larger allowance, discounted overage
Shared findings, reports, approvals
90-day retention
5 seats
Choose Team
Enterprise
Custom
Committed volume and pricing
SSO, RBAC, and audit controls
365-day evidence retention
Assessment and remediation review
Contact sales

See full pricing →

Start your first runtime.

From install to signed evidence in three commands.

$ curl -fsSL https://tachyonic.sh/install | bash
$ tachyonic runtime start --target https://your-agent.example.com --region aws-us-east-1