About AgentSeal
AgentSeal is an MCP server that records AI agent actions in tamper-evident SHA-256 hash chains. It is for teams that need to query activity and verify the integrity of an audit trail.
Key features
- 01Record agent actions in an audit trail
- 02Chain records with SHA-256 hashes
- 03Query actions by agent or type
- 04Verify chain integrity
Use cases
- 01Keep an audit trail of significant agent actions
- 02Review actions taken by a specific agent
- 03Check whether audit records were modified
MCP support
The MCP server exposes tools to record, query and verify AgentSeal audit records. Clients authenticate with an AGENTSEAL_API_KEY.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y agentseal-mcpAGENTSEAL_API_KEYSecretYour AgentSeal API key from agentseal.ioLocal servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
3Saved tool list · updated 3w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| agent_id | string | Yes | Identifier for this agent (e.g. 'research-bot', 'finance-agent') |
| action_type | string | Yes | What type of action was taken (e.g. 'email:send', 'file:write', 'api:call', 'db:query') |
| action_params | object | No | Parameters of the action (e.g. {to: '[email protected]', subject: '...'}) |
| reasoning | string | No | Why you decided to take this action — your chain of thought |
| authorized_by | string | No | Who or what authorized this action (e.g. 'user:alice', 'policy:auto-approve') |
Details
From the project READMEagentseal-mcp
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.
Setup
Claude Desktop
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.
Cursor / Other MCP hosts
Same configuration — add the server with your API key.
Environment variables
| Variable | Required | Description |
|---|---|---|
AGENTSEAL_API_KEY | Yes | Your API key from agentseal.io |
AGENTSEAL_URL | No | Custom API base URL (defaults to production) |
Tools
record_action
Record 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 |
|---|---|---|---|
agent_id | string | Yes | Identifier for the agent (e.g. research-bot) |
action_type | string | Yes | What kind of action (e.g. email:send, file:write, api:call) |
action_params | object | No | Details of the action |
reasoning | string | No | Why the agent decided to take this action |
authorized_by | string | No | Who or what approved the action |
Returns a sequence number and SHA-256 hash confirming the entry was chained.
query_actions
Look 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 |
|---|---|---|---|
agent_id | string | No | Filter by agent |
action_type | string | No | Filter by action type |
limit | number | No | Max entries to return (default 20) |
verify_chain
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.
| Parameter | Type | Required | Description |
|---|---|---|---|
agent_id | 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.
How it works
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.
Get an API key
Sign up at agentseal.io. Free to use.
Python SDK
For direct integration without MCP: pip install agentseal-sdk. See agentseal-sdk.
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.