Let AI agents seal their own work (MCP)

Agents act at machine speed: they write documents, make decisions, call tools, produce artifacts. The organisations deploying them are starting to ask the obvious governance question — can the agent prove what it did? With Sigill's Model Context Protocol (MCP) server, the answer is built in: any MCP-capable assistant or agent framework gets sealing and verification as native tools, no integration code required.

Connect it

Add Sigill to the agent's MCP configuration — for example in Claude Code:

claude mcp add --transport http sigill https://api.sigill.ai/mcp \
  --header "Authorization: Bearer YOUR_API_KEY"

That's the whole integration. The agent now has tools to timestamp hashes, seal documents, look up prior proofs, and verify artifacts — with your tenant's certificates and quotas, and the same privacy model as the API (hash-based tools transmit digests, not content).

What it looks like in practice

• "Seal the contract draft you just wrote" — the agent produces the PDF, seals it with the organisation certificate, and hands back a sealed artifact any PDF reader validates.
• "Timestamp every file you deliver" — the agent stamps each output's hash as it works, leaving .tsr tokens beside its deliverables.
• "Before using this document, verify it" — the agent checks a seal it received instead of trusting the bytes, and can explain the verification report it gets back.
• "What did we seal last week?" — the agent queries the operation history and reconciles it against its own logs.

The MCP announcement post walks through a full session, and sealing Claude Code sessions shows the pattern applied to coding agents specifically.

Agents at scale: pair MCP with the SDKs

MCP is right for interactive assistants and tool-using agents. For agent platforms — where your infrastructure runs many agents and you want evidence produced systematically rather than by the agent's choice — put the SDKs in the harness instead: seal every session log on rotation (JAdES for agent logs), timestamp every artifact at creation, and record AI evidence envelopes for individual model calls. The two approaches compose: the agent can seal deliberately via MCP while the platform seals everything as a matter of policy.

Why this matters now

Agent output is exactly the evidence class that disputes will be made of: decisions with money attached, generated documents sent to counterparties, autonomous changes to systems. Evidence captured at the moment of action — hashed, timestamped, sealed — is categorically stronger than logs assembled after the fact, because it is independently verifiable and tamper-evident from the second it exists. Giving the agent the sealing tools is the cheapest way to make that the default.