PRODUCT PROFILE · RANK 5 OF 8
Lasso Security review: Claude Code hooks and an open-source MCP gateway
SHORT ANSWER
Lasso Security inspects every Claude Code tool call before it runs through the agent's lifecycle hooks and routes MCP traffic through an open-source gateway that can block, alert or sanitize. It needs several components, and its only published price is an annual commit listed on AWS Marketplace. It scores 6.40 and ranks 5 of 8.
By The Agent Desk · Agentic Endpoint Compare · Published 2026-10-11
Desk research from public vendor pages, press releases and standards pages read on 27 September and 11 October 2026. Editorial assessment; we did not run the products.
Rank 5 of 8 among broader AI security platforms on our published weights
Claude Code hooks and an open-source MCP gateway
What does Lasso control?
Inspects every Claude Code tool call before it runs through the agent's lifecycle hooks and routes MCP traffic through an open-source gateway that can block, alert or sanitize.
How does Lasso reach devices?
Browser extension, proxy integrations, the MCP gateway and Claude Code hooks through the enterprise management platform; works with stacks such as Palo Alto Networks or CrowdStrike.
Source: Lasso Security: AI usage control · Read 27 Sep 2026
Which verdicts can Lasso return?
- Block or denyDocumented
- Ask a personNot described
- Alert or warnDocumented
- Mask or modifyDocumented
- Simulate firstNot described
- Remove or scale backNot described
"MCP actions block, alert or sanitize; masks sensitive data before prompts reach third-party models."
Source: Lasso Security: MCP security · Read 27 Sep 2026
Source: Lasso Security: AI usage control · Read 27 Sep 2026
How does Lasso score on each criterion?
| Criterion | Weight | Score | Why |
|---|---|---|---|
| Stop before it runs | 25% | 8 / 10 | Inspects every Claude Code tool call before it is executed through the agent's lifecycle hooks, and gates MCP traffic through its gateway. Source: Lasso Security: AI coding assistants · Read 27 Sep 2026 |
| Verdict range | 15% | 5 / 10 | Documents 3 of six verdict types: Block or deny, Alert or warn and Mask or modify. "MCP actions block, alert or sanitize; masks sensitive data before prompts reach third-party models." Source: Lasso Security: MCP security · Read 27 Sep 2026 Source: Lasso Security: AI usage control · Read 27 Sep 2026 |
| Capability rules | 15% | 6 / 10 | Controls which users and teams can connect to which MCP servers, with role-based permissions and DLP; broader capability rules are not itemized. Source: Lasso Security: MCP security · Read 27 Sep 2026 |
| Actor trail | 10% | 5 / 10 Tied lowest | Keeps a history of inputs, policy decisions and enforcement actions; agent versus person attribution is not described. Source: Lasso Security: AI usage control · Read 27 Sep 2026 |
| Rollout path | 10% | 6 / 10 | Browser extension, proxy, gateway and Claude Code hooks: several components to run. Source: Lasso Security: AI usage control · Read 27 Sep 2026 |
| Cloud and workspace reach | 10% | 6 / 10 | Runtime enforcement at the proxy, API or AI gateway layer reaches AI apps beyond the laptop; agents in cloud workspaces are not described. Source: Lasso Security homepage · Read 27 Sep 2026 |
| Named agent coverage | 5% | 5 / 10 | Names 3 of the six agents we track: Claude Code, Cursor and Windsurf. Source: Lasso Security: AI coding assistants · Read 27 Sep 2026 Source: Lasso Security: MCP security · Read 27 Sep 2026 |
| Public proof | 10% | 8 / 10 Tied highest | Lists Lasso for Employees at $20,000 per 12 months on AWS Marketplace (marketplace list price), and its newsroom describes a $30 million round led by ClearSky in September 2026. Source: AWS Marketplace: Lasso for Employees · Read 11 Oct 2026 |
Which agents does Lasso name?
- Claude CodeNamed
- CursorNamed
- GitHub CopilotNot named
- OpenAI CodexNot named
- WindsurfNamed
- Claude DesktopNot named
Lasso names 3 of the six agents we track.
Source: Lasso Security: AI coding assistants · Read 27 Sep 2026
Source: Lasso Security: MCP security · Read 27 Sep 2026
- Lasso Security discovers MCP servers across Claude, Cursor and Windsurf and integrates with Claude Code hooks.
What does it cost?
Marketplace list price AWS Marketplace list price: $20,000 per 12 months (Lasso for Employees, GenAI Chatbots annual commit).
Marketplace list price for one listing. Other listings, such as Lasso for Secured Gateway for LLMs, were not priced on the pages we read; lasso.security publishes no pricing.
Source: AWS Marketplace: Lasso for Employees · Read 11 Oct 2026
Where is Lasso strongest, and where does it fall short?
Strongest
- Public proof: 8 / 10 (Tied highest)
- Concrete pre-execution inspection for Claude Code tool calls.
- An open-source MCP gateway with block, alert and sanitize actions.
Falls short
- Stop before it runs: 8 / 10; highest Bay 9 / 10
- Verdict range: 5 / 10; highest Bay and Onyx Security 7 / 10
- Capability rules: 6 / 10; highest Bay 9 / 10
- Actor trail: 5 / 10; highest Bay 8 / 10
- Rollout path: 6 / 10; highest Bay 9 / 10
- Cloud and workspace reach: 6 / 10; highest Onyx Security, Zenity and Noma Security 9 / 10
- Named agent coverage: 5 / 10; highest Zenity 7 / 10
- Several components to run: extension, proxy, gateway and hooks.
- Agent versus person attribution is not described on the pages we read.
Key facts
| Fact | Detail and source |
|---|---|
| Coding assistants | Connects directly to Claude Code's lifecycle hooks via the enterprise management platform and inspects every tool call before it is executed. Source: Lasso Security: AI coding assistants · Read 27 Sep 2026 |
| MCP gateway | Open-source MCP gateway; discovers MCP servers across Claude, Cursor and Windsurf; actions block, alert or sanitize. Source: Lasso Security: MCP security · Read 27 Sep 2026 |
| Usage control | Browser extension and proxy integrations; masks sensitive data before prompts reach third-party models; keeps audit-ready records. Source: Lasso Security: AI usage control · Read 27 Sep 2026 |
| Platform | Discovery and AI-BOM, AI-SPM, automated red teaming, runtime enforcement at the proxy, API or AI gateway layer, and AIDR. Source: Lasso Security homepage · Read 27 Sep 2026 |
| Research | Introduced LEAP, a guardrail classification architecture that runs on CPUs, on 9 September 2026; performance figures are vendor-stated. Source: Lasso Security blog: LEAP (9 September 2026) · Read 27 Sep 2026 |
| AWS Marketplace | Lasso for Employees is listed with a GenAI Chatbots annual commit of $20,000 per 12 months (marketplace list price). Source: AWS Marketplace: Lasso for Employees · Read 11 Oct 2026 |
| Funding | Lasso's newsroom describes a $30 million round led by ClearSky with participation from Entrée Capital, announced in September 2026 alongside LEAP. Source: Lasso Security newsroom · Read 11 Oct 2026 |
How does Lasso compare head to head?
| Pair | Result |
|---|---|
| Bay matched with Lasso Security | Bay 7.20, Lasso Security 6.40 |
| Lasso Security matched with Neo | Lasso Security 6.40, Neo 6.85 |
| Lasso Security matched with Onyx Security | Lasso Security 6.40, Onyx Security 6.85 |
| Lasso Security matched with Zenity | Lasso Security 6.40, Zenity 6.75 |
| Lasso Security matched with Noma Security | Lasso Security 6.40, Noma Security 6.55 |
| CrowdStrike Falcon Guardian matched with Lasso Security | CrowdStrike Falcon Guardian 6.25, Lasso Security 6.40 |
| Harmonic Security matched with Lasso Security | Harmonic Security 5.90, Lasso Security 6.40 |
| Ent matched with Lasso Security | Ent 5.80, Lasso Security 6.40 |
| Koi (Palo Alto Networks) matched with Lasso Security | Koi (Palo Alto Networks) 5.75, Lasso Security 6.40 |
| Lasso Security matched with Prompt Security (SentinelOne) | Lasso Security 6.40, Prompt Security (SentinelOne) 5.45 |
| Glow Security matched with Lasso Security | Glow Security 5.40, Lasso Security 6.40 |
| Bloom Security matched with Lasso Security | Bloom Security 4.65, Lasso Security 6.40 |
Frequently asked questions
Can Lasso Security stop an agent action before it runs?
Inspects every Claude Code tool call before it is executed through the agent's lifecycle hooks, and gates MCP traffic through its gateway. We score this 8 out of 10.
Which verdicts does Lasso Security document?
Lasso Security documents 3 of six verdict types: Block or deny, Alert or warn and Mask or modify. "MCP actions block, alert or sanitize; masks sensitive data before prompts reach third-party models."
How much does Lasso Security cost?
AWS Marketplace list price: $20,000 per 12 months (Lasso for Employees, GenAI Chatbots annual commit). Marketplace list price for one listing. Other listings, such as Lasso for Secured Gateway for LLMs, were not priced on the pages we read; lasso.security publishes no pricing.