{
  "markdown": "# agentseal-mcp\n\n[![agentseal-mcp MCP server](https://glama.ai/mcp/servers/JoeyBrar/agentseal-mcp/badges/card.svg)](https://glama.ai/mcp/servers/JoeyBrar/agentseal-mcp)\n\nMCP server for [AgentSeal](https://agentseal.io). Tamper-proof audit logs for AI agents, using SHA-256 hash chains.\n\nEvery 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.\n\n## Setup\n\n### Claude Desktop\n\nAdd to your `claude_desktop_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"agentseal\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"agentseal-mcp\"],\n      \"env\": {\n        \"AGENTSEAL_API_KEY\": \"as_sk_your_key_here\"\n      }\n    }\n  }\n}\n```\n\nRestart Claude Desktop after saving.\n\n### Cursor / Other MCP hosts\n\nSame configuration — add the server with your API key.\n\n### Environment variables\n\n| Variable | Required | Description |\n|---|---|---|\n| `AGENTSEAL_API_KEY` | Yes | Your API key from [agentseal.io](https://agentseal.io) |\n| `AGENTSEAL_URL` | No | Custom API base URL (defaults to production) |\n\n## Tools\n\n### `record_action`\n\nRecord an agent action to the audit trail. Call this after significant actions to create a cryptographically chained record of what happened and why.\n\n| Parameter | Type | Required | Description |\n|---|---|---|---|\n| `agent_id` | string | Yes | Identifier for the agent (e.g. `research-bot`) |\n| `action_type` | string | Yes | What kind of action (e.g. `email:send`, `file:write`, `api:call`) |\n| `action_params` | object | No | Details of the action |\n| `reasoning` | string | No | Why the agent decided to take this action |\n| `authorized_by` | string | No | Who or what approved the action |\n\nReturns a sequence number and SHA-256 hash confirming the entry was chained.\n\n### `query_actions`\n\nLook up previously recorded actions from the audit trail. Use this to check what actions have been taken or recall past decisions.\n\n| Parameter | Type | Required | Description |\n|---|---|---|---|\n| `agent_id` | string | No | Filter by agent |\n| `action_type` | string | No | Filter by action type |\n| `limit` | number | No | Max entries to return (default 20) |\n\n### `verify_chain`\n\nVerify 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.\n\n| Parameter | Type | Required | Description |\n|---|---|---|---|\n| `agent_id` | string | No | Verify chain for a specific agent. If omitted, verifies all entries. |\n\nReturns the number of entries verified and whether the chain is intact.\n\n## How it works\n\nEach 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.\n\n## Get an API key\n\nSign up at [agentseal.io](https://agentseal.io). Free to use.\n\n## Python SDK\n\nFor direct integration without MCP: `pip install agentseal-sdk`. See [agentseal-sdk](https://github.com/JoeyBrar/agentseal-sdk).\n\n## License\n\nMIT\n",
  "bytes": 3042,
  "sha": "838092a5d12a5fc280b0e88f52c39011d434f109c4217e97cf757efc25d9949d",
  "repo_slug": "joeybrar/agentseal-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_joeybrar_agentseal_89a6c323/readme"
}