AgentSeal

Web · Windows · Mac · Linux · API

Freedom report

Three barsScore 6.6

Free tierA free tier is on its own pricing page
Open codeNo open-source code on record
Runs widely4 of 6 device platforms
DocumentedPlans, terms and facts published

AgentSeal is ranked #1 of 27 in AI red teaming tools on Freedom251. It runs on API, Linux, macOS, Web, Windows. There is a free plan.

AgentSeal plans and pricing

All plans

Free Free 30 basic probes · MCP registry · Guard · Watch agentseal.org · 30 Sept 2026

Pro Not published 311 probes · runtime MCP scanning with OAuth · PDF export · dashboard agentseal.org · 30 Sept 2026

Compared on AI red teaming tools

Free plan: Yes
Attack categories: prompt extraction; instruction injection; data exfiltration; MCP tool poisoning; RAG poisoning; multimodal attacks; behavioral genome testing
Target systems: system prompts; AI agents; HTTP endpoints; MCP servers; RAG pipelines; multimodal AI systems
Automation level: continuous
Deployment: hybrid
Continuous monitoring: Yes
Report exports: JSON; SARIF 2.1.0; JUnit XML; PDF; GitHub Actions step summary

Best AgentSeal alternatives

See all 12

Two bars OpenSecureAI Scanner Free tier No. 2$49/mo6.6 Two bars Promptfoo Free tier No. 3Free6.6 Two bars RedAmon Free tier No. 4Free6.6 One bar Confident AI Free tier No. 5$200/mo6.4 One bar Darkhunt AI Security Free tier No. 6Free6.4 One bar Giskard Free tier No. 7Free6.4

The record

Purpose: AgentSeal is an open-source security scanner and toolkit for testing AI agent prompts, auditing MCP servers, and detecting agent vulnerabilities.
Prompt testing: Its scan command runs adversarial probes against system prompts to detect extraction and injection vulnerabilities.
Machine protection: Guard scans agent configurations and skill files on a machine, while Watch monitors those files and MCP configs for changes.
MCP scanning: Scan-MCP runs MCP servers in a sandbox and tests tool behavior with adversarial payloads; OAuth is supported for authenticated remote servers.
LLM providers: The site lists Ollama, OpenAI, Anthropic Claude, OpenRouter, Google Gemini, DeepSeek, Groq, Together AI, LM Studio, llama.cpp, vLLM, and compatible OpenAI chat API endpoints.
Privacy: The site says prompts go directly from the CLI to the user's LLM provider, and dashboard-synced prompts and model configurations are encrypted at rest with Fernet (AES-256).
Offline use: The CLI can run fully offline with a local Ollama model, with zero network calls and zero telemetry, according to the site.
CI integrations: AgentSeal supports SARIF 2.1.0, JUnit XML, GitHub Actions summaries, and policy-as-code rules for gating pull requests.
Security registry: The MCP registry page says each server passes through a seven-stage security pipeline before it is listed, including sandboxing and probing.
Scan coverage: The FAQ describes 311 probes across extraction, injection, MCP tool poisoning, RAG poisoning, and multimodal attacks.
Installation: The CLI is installable with pip, and the site also provides an npm wrapper for Node projects and CI pipelines.
Requirements: The installation page requires Python 3.10 or higher for the CLI, and says the npm wrapper shells out to the Python CLI.
Dashboard: The dashboard provides scan results, prompt management, security monitoring, and GitHub integration settings.
Support: The contact page says the team typically responds within 24 hours and provides an email address for urgent matters.
Price from: Free

Where it ranks on Freedom251

Best AI Red Teaming Tools in 2026#1 of 27

Is AgentSeal yours?

Claim it for free: prove the domain, then correct facts, plans and screenshots. An editor reviews every change.

Claim it free Promote AgentSeal

Sources

agentseal.org· checked 30 Sept 2026
agentseal.org/docs· checked 30 Sept 2026
agentseal.org/docs/installation· checked 30 Sept 2026
agentseal.org/docs/dashboard· checked 30 Sept 2026
agentseal.org/contact· checked 30 Sept 2026