AgentSeal provides a tamper-proof audit logging system for AI agents using SHA-256 hash chains, allowing you to cryptographically prove what actions your agents took.
record_action: Log agent actions (e.g., sending emails, writing files, API calls) to an immutable audit trail, capturing agent ID, action type, parameters, reasoning, and authorization info. Each entry is chained cryptographically.
query_actions: Retrieve previously recorded actions, with optional filtering by agent ID or action type, and a configurable result limit.
verify_chain: Cryptographically verify the integrity of the hash chain — for a specific agent or all entries — to detect any tampering or unauthorized modifications.
MCP server for AgentSeal. 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 your claude_desktop_config.json:
{
"mcpServers": {
"agentseal": {
"command": "npx",
"args": ["-y", "agentseal-mcp"],
"env": {
"AGENTSEAL_API_KEY": "as_sk_your_key_here"
}
}
}
}Restart Claude Desktop after saving.
Same configuration — add the server with your API key.
Variable | Required | Description |
| Yes | Your API key from agentseal.io |
| No | Custom API base URL (defaults to production) |
Related MCP server: Agent Audit Trail MCP Server
record_actionRecord an agent action to the audit trail. Call this after significant actions to create a cryptographically chained record of what happened and why.
Parameter | Type | Required | Description |
| string | Yes | Identifier for the agent (e.g. |
| string | Yes | What kind of action (e.g. |
| object | No | Details of the action |
| string | No | Why the agent decided to take this action |
| string | No | Who or what approved the action |
Returns a sequence number and SHA-256 hash confirming the entry was chained.
query_actionsLook up previously recorded actions from the audit trail. Use this to check what actions have been taken or recall past decisions.
Parameter | Type | Required | Description |
| string | No | Filter by agent |
| string | No | Filter by action type |
| number | No | Max entries to return (default 20) |
verify_chainVerify 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.
Parameter | Type | Required | Description |
| string | No | Verify chain for a specific agent. If omitted, verifies all entries. |
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_chain catches it instantly.
Sign up at agentseal.io. Free to use.
For direct integration without MCP: pip install agentseal-sdk. See agentseal-sdk.
MIT
Look up previously recorded actions from the audit trail. Use this to check what actions have been taken, verify history, or recall past decisions.
Inputs: agent_id, action_type, limit.
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.
Inputs: agent_id (required), action_type (required), action_params, reasoning, +1 more.
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.
Inputs: agent_id.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 3 tools
Each tool has a clearly distinct purpose: record_action records, query_actions retrieves, verify_chain checks integrity. No overlap or ambiguity.
All tool names follow a consistent verb_noun pattern (query_actions, record_action, verify_chain), making them predictable and easy to understand.
Three tools is an ideal scope for an audit trail server, covering the essential operations of recording, querying, and verifying without unnecessary bloat.
The tool surface fully covers the core lifecycle of an audit trail: recording actions, looking up history, and verifying chain integrity. No obvious gaps given the domain's immutability requirements.
Signed, publicly logged records of what your AI agent did, with proofs anyone can check offline.
Bitcoin-anchored, tamper-evident audit log for AI agents — record, disclose and verify actions.
Issue & verify signed (ed25519), hash-chained, timestamped provenance receipts for agent actions.
Immutable event logging and audit trail for agent transactions
