Every agent action is recorded in a SHA-256 hash chain. With this, you can actually prove to clients that your agent did what it said it did. Record, query, verify, and export agent activity.
Overview
Features
- One-command setup —
npx agentseal-mcpwith your API key - Verify on demand — Check chain integrity with a single call
- Multi-agent — Track multiple agents under one org
- Export — JSON or CSV of the full trail
- Python SDK —
pip install agentseal-sdkfor direct - SHA-256 hash chain — Each entry's hash includes the previous one. Change anything and the chain breaks.integration
- EU AI Act ready — Built for high-risk AI compliance requirements
Tools
- record_action — Record an agent action with reasoning
- query_actions — Look up past actions by agent or type
- verify_chain — Check that the hash chain is intact and no records were modified
Get started
Sign up at agentseal.io for an API key. Free to use.
Server Config
{
"mcpServers": {
"agentseal": {
"command": "npx",
"args": [
"-y",
"agentseal-mcp"
],
"env": {
"AGENTSEAL_API_KEY": "as_sk_your_key_here"
}
}
}
}