AgentSeal
About
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.
Details
- Author
- JoeyBrar
- Downloads
- 225
- Categories
- Developer Tools, Security, Finance, Other, AI
Jump to
- One-command setup (npx agentseal-mcp) with API key
- On-demand chain integrity verification
- Multi-agent tracking under one organization
- Export full trail as JSON or CSV
- Python SDK for direct integration (agentseal-sdk)
- SHA-256 hash chain — tamper-evident records
- EU AI Act ready for high-risk AI compliance
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
AgentSealCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Set up in one command: npx agentseal-mcp with your API key. Use the server’s three tools — record_action, query_actions, and verify_chain — to record, look up, and verify agent actions. A Python SDK (pip install agentseal-sdk) is also available for direct integration.
record_action
Record an agent action to the AgentSeal audit hash trail. Call this after every significant action (sending emails, modifying files, running queries, making API calls) to create a cryptographically sealed record of what happened and why.
query_actions
Look up previously recorded actions from the audit trail. Use this to check what actions have been taken, verify history, or recall past decisions.
verify_chain
Verify the integrity of the audit trail hash chain. Each entry's SHA-256 hash includes the previous entry's hash — if any record was modified, the chain breaks and this will report where.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"agentseal": {
"agentseal": {
"command": "npx",
"args": [
"-y",
"agentseal-mcp"
],
"env": {
"AGENTSEAL_API_KEY": "as_sk_your_key_here"
}
}
}
}
}McpServers
{
"agentseal": {
"command": "npx",
"args": [
"-y",
"agentseal-mcp"
],
"env": {
"AGENTSEAL_API_KEY": "as_sk_your_key_here"
}
}
}MCP server forAgentSeal. Tamper-proof audit logs for AI agents, using SHA-256 hash chains.
Every agent action is recorded in a hash chain. With this, you can actually prove to your clients that your agent did what it said it did.
Add to yourclaude_desktop_config.json:
{ "mcpServers": { "agentseal": { "command": "npx", "args": ["-y", "agentseal-mcp"], "env": { "AGENTSEAL_API_KEY": "as_sk_your_key_here" } } } }
Same configuration — add the server with your API key.
Record an agent action to the audit trail. Call this after significant actions to create a cryptographically chained record of what happened and why.
Returns a sequence number and SHA-256 hash confirming the entry was chained.
Look up previously recorded actions from the audit trail. Use this to check what actions have been taken or recall past decisions.
Verify the integrity of the hash chain. Each entry's SHA-256 hash includes the previous entry's hash — if any record was modified, the chain breaks and this reports where.
Returns the number of entries verified and whether the chain is intact.
Each recorded action is hashed with SHA-256. That hash includes the previous entry's hash, forming a chain. Modify any record and every hash after it changes —verify_chaincatches it instantly.
For direct integration without MCP:pip install agentseal-sdk. Seeagentseal-sdk.
This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.
TIBET provenance tracking for AI decisions. Cryptographic audit trails with ERIN/ERAAN/EROMHEEN/ERACHTER intent logging for compliance and transparency.
Cross-reference DORA and NIS2 requirements — gap analysis, mapping, and compliance overlap detection for financial services
Unmodified government company registry data — 27 national registries, live. Cross-border UBO / beneficial owner chain walker for KYC, AML, due diligence. 27 tools + 10 MCP prompt workflows.
PCI DSS v4.0 payment security compliance — SAQ selection, control validation, scope reduction by MEOK AI Labs
Boost security in your dev lifecycle via SAST, SCA, Secrets & IaC scanning with Cycode.
Cloud security insights, guardrail guidance, and compliance checking via Dawnguard.
Require a named human's offline-verifiable approval before an AI agent takes an irreversible action — payment release, record change, deploy. Two-person rule, Ed25519 Trust Receipts, IETF-drafted, Apache-2.0.
Turns the Agent into a vLEI/KERI protocol expert
Six-gate governance for AI agents: PROCEED/PAUSE/HALT decisions with hash-chained audit trails.
Paid remote MCP for agent data-access boundary reviews, permission scope evidence, sensitive data notes, and governance receipts.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
