Agentseal

joeybrar/agentseal-mcp

This server creates tamper-proof audit trails for AI agents using SHA-256 hash chains. It exposes three tools: record_action logs agent decisions with optional reasoning and authorization metadata, query_actions retrieves past entries by agent or action type, and verify_chain confirms no records have been modified by checking hash continuity. Each action's hash incorporates the previous entry's hash, so any tampering breaks the chain immediately. Reach for this when you need cryptographic proof of what your agent did, whether for client accountability, compliance audits, or debugging why an agent made a particular decision. Requires an API key from agentseal.io and runs via npx for quick setup in Claude Desktop or Cursor.

GitHub stars

1

tools

3

auth

Secret needed

transport

STDIO

env var

1

last updated

Apr 18, 2026

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

{
  "mcpServers": {
    "agentseal": {
      "command": "npx",
      "args": ["-y", "agentseal-mcp"],
      "env": {
        "AGENTSEAL_API_KEY": "as_sk_your_key_here"
      }
    }
  }
}