Skip to content
Back to the index

agent-trust-plane

PyPIInfrastructure

PulseGate's liveness check found it on 22 Sep 2026; it is registered on GitHub and PyPI and has been in the index since 22 Sep 2026. How this is checked

agent-trust-plane is an MIT-licensed Python package for enforcing authorization boundaries around AI agent tool calls. It evaluates tool-call arguments against delegated authority, creates single-use grants, supports replay, and turns denied calls into CI regression tests.

Inferred · not functionally tested

Open SourceMITCLISelf-hostedAPI
Visit PyPI

Overview

6 features

Purpose: Preventing unauthorized AI agent tool calls and detecting security regressions in delegated permissions.

Inferred · not functionally tested

Audience: AI security engineers and developers building MCP-enabled agents

Inferred · not functionally tested

Functions: agents, 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: MIT · platforms: CLI · deployment: cli, self_hosted, api_only

Constraint provenance is unknown; confirm requirements with the publisher.

Record sources: pypi.org · github.com. These links do not verify the individual claims.

agent-trust-plane is an AI & LLM security project. Inferred · not functionally tested: It focuses on preventing unauthorized AI agent tool calls and detecting security regressions in delegated permissions. Inferred · not functionally tested: It is built as an open-source project for AI security engineers and developers building MCP-enabled agents. Basis unknown · not verified: agent-trust-plane is open source under the MIT license. Basis unknown · not verified: agent-trust-plane is available on the command line and API, and it can be self-hosted.

It is developed by TimelessVisions, and it first shipped in 2026. The project is developed in the open on GitHub with 35 commits in the last 90 days. Inferred · not functionally tested: Among its 6 catalogued features are argument authorization, delegated authority, and single-use grants. Inferred · not functionally tested: Catalogued interfaces include an MCP server. agent-trust-plane is currently in beta.

Summary written by a language model from the project’s public pages.

Tasks: Inferred · not functionally tested

  • Argument authorization
  • Delegated authority
  • Single-use grants
  • Decision replay
  • Denial pinning
  • CI regression tests

Topics: Inferred · not functionally tested

Tags
agent-authorizationmcp-securitysecurity-regression-testingdelegated-permissions
AI capabilities
Structured

JSON profile · Text profile · Access guide

Built with & integrations

Framework
FastAPI
Written with
Claude Code
Connectors
MCP
Runs on
CLISelf-hostedAPI-only
Written with — evidence
Claude Code
commit 0d0d14d1f071 · since Sep 2026

Trust & compliance

License
MIT
Public signals
HTTPSOpen SourceGitHubActive maintenance

Indexing history

1

What PulseGate has recorded for this listing

  1. Indexed22 Sep · 16:24 UTC
    agent-trust-plane seen via PyPI Bulk Enumerator
    Source: PyPI Bulk Enumerator · Open

Frequently asked questions about agent-trust-plane

What is agent-trust-plane?
Inferred · not functionally tested: Agent-trust-plane focuses on preventing unauthorized AI agent tool calls and detecting security regressions in delegated permissions. It is catalogued under AI & LLM security on PulseGate.
Who is agent-trust-plane for?
Inferred · not functionally tested: agent-trust-plane is an open-source project built for AI security engineers and developers building MCP-enabled agents.
Does agent-trust-plane have a free plan?
Basis unknown · not verified: Yes — agent-trust-plane is open source under the MIT license and free to use.
What platforms does agent-trust-plane run on?
Basis unknown · not verified: agent-trust-plane runs on the command line and API. It can also be self-hosted.
Is agent-trust-plane still maintained?
PulseGate's liveness check found it on 22 Sep 2026. Its GitHub repository shows 35 commits in the last 90 days.
What projects are similar to agent-trust-plane?
Similar projects tracked by PulseGate include agentplane, agent-assurance, and agentidem.agentplaneagent-assuranceagentidem
Who makes agent-trust-plane?
agent-trust-plane is developed by TimelessVisions.
How long has agent-trust-plane been around?
agent-trust-plane first shipped in 2026.

Similar projects

Closest matches by what these projects do