---
title: "eczid-agent-trust"
description: "See what the AI agents in a workspace can reach: agent manifests, instructions, declared tools, MCP servers, permission policy and public proof references. Inspection only. Free."
canonical: https://agentpluginsdirectory.com/plugins/eczid-agent-trust
last-updated: 2026-10-21
---

# eczid-agent-trust
See what the AI agents in a workspace can reach: agent manifests, instructions, declared tools, MCP servers, permission policy and public proof references. Inspection only. Free.
- Slug: eczid-agent-trust
- Publisher: EcoCitizenz Ltd
- Repository: https://github.com/Ecocitizenz/eczid-agent-plugins
- Manifest: plugins/eczid-agent-trust/plugin.json
- Version: 0.1.1
- License: MIT
- Category (editorial): security
- Skills: 1 (agent-trust-review)
- MCP servers: 1 (ecz-id-verifier)
- Stars: 0
- Repository created: 2026-09-03
- Repository last pushed: 2026-09-03
- Publisher type: User
- Listing: https://agentpluginsdirectory.com/plugins/eczid-agent-trust
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What eczid-agent-trust does, in the publisher's words

See what the AI agents in a workspace can reach: agent manifests, instructions, declared tools, MCP servers, permission policy and public proof references. Inspection only. Free.

No account, no sign-in, no licence key, no trial and no paywall. Every capability described below works in full as soon as you install it, in whatever host you run it in, for free.

This plugin is open source under the MIT licence (the ECZ-ID Verifier npm package it launches carries its own licence): https://github.com/Ecocitizenz/eczid-agent-plugins

- Skill agent-trust-review runs a portable, filename-and-path-only evidence review (scripts/review.mjs) and reports EVIDENCE OBSERVED / NOT OBSERVED, a deterministic Review Priority (LOW / NORMAL / ELEVATED / HIGH) with the reasons, why each class matters and what to review next, plus at most three contextual next actions.

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/Ecocitizenz/eczid-agent-plugins/HEAD/plugins/eczid-agent-trust/README.md

## Skills

- agent-trust-review: What can this agent reach, who authorised it, and what has public proof? Runs a local, filename-and-path-only evidence review and reports EVIDENCE OBSERVED / NOT OBSERVED, a deterministic Review Priority with reasons, why each class matters and what to review next. Use when asked about Agent Trust…

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.

## MCP servers

- ecz-id-verifier: transport: stdio; command: npx -y @ecocitizenz/ecz-id-mcp-verifier@0.9.0 ecz-id-mcp-server

Read from the plugin's own mcp.json. Environment variable names only, never values.