aat-mcp
PulseGate's liveness check found it on 29 Sep 2026; it is registered on PyPI and has been in the index since 29 Sep 2026. How this is checked
aat-mcp is an Apache-2.0 Python package that records AI agent tool calls as signed, hash-chained audit trails. Its MCP middleware and offline verification support developers building auditable and tamper-evident agent systems.
Inferred · not functionally tested
Overview
6 featuresPurpose: Preventing AI agent tool-call evidence from being altered or difficult to verify.
Inferred · not functionally tested
Audience: AI infrastructure and security developers
Inferred · not functionally tested
Functions: monitoring
Inferred · not functionally tested
Interfaces: API: indicated (inferred, not tested) · MCP: indicated (inferred, not tested) · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)
Recorded constraints: pricing: open_source · license: Apache-2.0 · platforms: CLI · deployment: cli, self_hosted, api_only
Constraint provenance is unknown; confirm requirements with the publisher.
Record sources: pypi.org. These links do not verify the individual claims.
aat-mcp is an AI security & guardrails project. Inferred · not functionally tested: It focuses on preventing AI agent tool-call evidence from being altered or difficult to verify. Inferred · not functionally tested: aat-mcp is an open-source project aimed at AI infrastructure and security developers. Basis unknown · not verified: aat-mcp is open source under the Apache-2.0 license. Basis unknown · not verified: aat-mcp is available on the command line and API, and it can be self-hosted.
aat-mcp first shipped in 2026. Inferred · not functionally tested: Among its 6 catalogued features are signed audit trails, hash chaining, and tamper evidence. Inferred · not functionally tested: Catalogued interfaces include an MCP server.
Summary written by a language model from the project’s public pages.
Tasks: Inferred · not functionally tested
- Signed audit trails
- Hash chaining
- Tamper evidence
- Offline verification
- MCP middleware
- Tool-call recording
Topics: Inferred · not functionally tested
Built with & integrations
Trust & compliance
Indexing history
1What PulseGate has recorded for this listing
Frequently asked questions about aat-mcp
- What does aat-mcp do?
- Inferred · not functionally tested: Aat-mcp focuses on preventing AI agent tool-call evidence from being altered or difficult to verify. It is catalogued under AI security & guardrails on PulseGate.
- Who should use aat-mcp?
- Inferred · not functionally tested: aat-mcp is an open-source project built for AI infrastructure and security developers.
- Is aat-mcp free?
- Basis unknown · not verified: Yes — aat-mcp is open source under the Apache-2.0 license and free to use.
- What platforms does aat-mcp run on?
- Basis unknown · not verified: aat-mcp runs on the command line and API. It can also be self-hosted.
- Is aat-mcp still active?
- PulseGate's liveness check found it on 29 Sep 2026.
- What projects are similar to aat-mcp?
- Similar projects tracked by PulseGate include shieldclaw-mcp, receipts-mcp, and mcp-alchemy.shieldclaw-mcpreceipts-mcpmcp-alchemy
- When did aat-mcp launch?
- aat-mcp first shipped in 2026.
- Is aat-mcp open source?
- Basis unknown · not verified: Yes — aat-mcp is open source under the Apache-2.0 license.
Similar projects
Closest matches by what these projects do