Agent Trust
PulseGate's liveness check found it on 17 Sep 2026; it has been in the index since 17 Sep 2026. How this is checked
Agent Trust is an open profile and reference implementation for establishing autonomous agent identity, attenuated delegation, proof of possession, attestations, and tamper-evident provenance. It targets developers building interoperable authorization and trust systems using standards such as JWS, OAuth/OIDC, SPIFFE/WIMSE, MCP, and A2A.
Inferred · not functionally tested
Overview
6 featuresPurpose: Proving what autonomous AI agents are authorized to do and preserving trustworthy delegation and provenance.
Inferred · not functionally tested
Audience: developers building autonomous AI agents and identity systems
Inferred · not functionally tested
Functions: Unknown
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: Open Source · platforms: CLI, WEB · deployment: browser, cli, self_hosted, api_only
Constraint provenance is unknown; confirm requirements with the publisher.
Record sources: github.com. These links do not verify the individual claims.
Agent Trust is an Auth & identity project. Inferred · not functionally tested: It focuses on proving what autonomous AI agents are authorized to do and preserving trustworthy delegation and provenance. Inferred · not functionally tested: It is built as an open-source project for developers building autonomous AI agents and identity systems. Basis unknown · not verified: Agent Trust is open source under the Open Source license. Basis unknown · not verified: It ships for the web, the command line, and API, and it can be self-hosted.
It is developed by MNKIAgentOS. Inferred · not functionally tested: Among its 6 catalogued features are agent identity, delegation attenuation, and proof of possession. 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
- Agent identity
- Delegation attenuation
- Proof of possession
- Attestations
- Provenance tracking
- JWS support
Topics: Inferred · not functionally tested
Built with & integrations
- multiple
- bLangChain in the HTML
Trust & compliance
Indexing history
1What PulseGate has recorded for this listing
- Indexed17 Sep · 23:05 UTCio.github.MNKIAgentOS/mnki-mcp seen via MCP Registry (official)Source: MCP Registry (official) · Open
Frequently asked questions about Agent Trust
- What does Agent Trust do?
- Inferred · not functionally tested: Agent Trust focuses on proving what autonomous AI agents are authorized to do and preserving trustworthy delegation and provenance. It is catalogued under Auth & identity on PulseGate.
- Who should use Agent Trust?
- Inferred · not functionally tested: Agent Trust is an open-source project built for developers building autonomous AI agents and identity systems.
- Does Agent Trust have a free plan?
- Basis unknown · not verified: Yes — Agent Trust is open source under the Open Source license and free to use.
- What platforms does Agent Trust run on?
- Basis unknown · not verified: Agent Trust runs on the web, the command line, and API. It can also be self-hosted.
- Is Agent Trust still active?
- PulseGate's liveness check found it on 17 Sep 2026.
- What are alternatives to Agent Trust?
- Similar projects tracked by PulseGate include AgentTrust ID, Agentra™, and agent-trust-plane.AgentTrust IDAgentra™agent-trust-plane
- Who develops Agent Trust?
- Agent Trust is developed by MNKIAgentOS.
- Is Agent Trust open source?
- Basis unknown · not verified: Yes — Agent Trust is open source under the Open Source license.
Similar projects
Closest matches by what these projects do