Agentseal

io.github.JoeyBrarPublished by GitHub account JoeyBrarv0.2.1Updated Oct 24, 2026

Verifiable action logs for AI agents. Every action is recorded in a SHA-256 hash chain.

VerifiedSTDIODesktop onlyDeveloper ToolsSecurity & Monitoring

Overview

AI-generated overview

AgentSeal is a local MCP server that lets an AI assistant record its actions in a SHA-256 hash-chained audit trail, query past entries, and verify the chain's

What you can do
Record agent actions to a tamper-evident audit trail, with action type, parameters, reasoning and who authorized it, returning a sequence number and hash. Look up previously recorded actions, filtered by agent or action type, to recall what was done or why. Verify the integrity of the hash chain for one agent or all entries and report where it breaks.
When to use it
Useful when you need to prove to clients or auditors that an agent did what it claims, and want a verifiable, tamper-evident log of significant actions such as sending email, writing files or calling APIs.
Requirements
Runs as a local process via npx from the npm package agentseal-mcp, configured in an MCP host such as Claude Desktop or Cursor. Requires an AgentSeal API key supplied in the AGENTSEAL_API_KEY environment variable; an optional AGENTSEAL_URL sets a custom API base URL. Network access to the AgentSeal service is needed.
Before you install
Requires the secret AGENTSEAL_API_KEY, which is stored in the host configuration file. Recorded actions, including parameters and reasoning, are sent to the AgentSeal service, so avoid logging sensitive data. The server writes audit entries to a remote trail; the README says signup is free but does not describe limits or later pricing.

Installation

In SourceWeft

  1. Open Agentseal in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

agentseal-mcp

[agentseal-mcp MCP server]

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:

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

VariableRequiredDescription
AGENTSEAL_API_KEYYesYour API key from agentseal.io
AGENTSEAL_URLNoCustom 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.

ParameterTypeRequiredDescription
agent_idstringYesIdentifier for the agent (e.g. research-bot)
action_typestringYesWhat kind of action (e.g. email:send, file:write, api:call)
action_paramsobjectNoDetails of the action
reasoningstringNoWhy the agent decided to take this action
authorized_bystringNoWho 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.

ParameterTypeRequiredDescription
agent_idstringNoFilter by agent
action_typestringNoFilter by action type
limitnumberNoMax 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.

ParameterTypeRequiredDescription
agent_idstringNoVerify 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

Source: README.md at commit e888572

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.2.1LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts