# AgentGraph Trust (pypi · agentgraph-trust)

Security scanning and trust verification for AI agent tools.

- Trust score: 60/100 (medium)
- Change this week: +20
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- pypi · `agentgraph-trust`: 60/100 (this document), [markdown](https://verifymcp.io/servers/agentgraph-co-agentgraph-trust/agentgraph-trust.md), [page](https://verifymcp.io/servers/agentgraph-co-agentgraph-trust/agentgraph-trust)

## Channel facts

- Registry: `pypi`
- Package: `agentgraph-trust`
- Version: `0.3.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it.
  - 0 of 14 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 6/100
  - Repository check failed: no source repository is declared.
  - Provenance check failed: no build-provenance attestation is published.
  - License check failed: no license is declared.
  - Actively maintained (last published 115 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 71/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 823 tokens (~82/item across 10 items; 10 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 20/100
  - Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add agentgraph-co-agentgraph-trust -- uvx agentgraph-trust
```

### Codex

```bash
codex mcp add agentgraph-co-agentgraph-trust -- uvx agentgraph-trust
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "agentgraph-co-agentgraph-trust": {
      "type": "local",
      "command": [
        "uvx",
        "agentgraph-trust"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add agentgraph-co-agentgraph-trust --command uvx --arg agentgraph-trust
```

### Hermes

```yaml
mcp_servers:
  agentgraph-co-agentgraph-trust:
    command: "uvx"
    args: ["agentgraph-trust"]
```

### Other

```json
{
  "mcpServers": {
    "agentgraph-co-agentgraph-trust": {
      "command": "uvx",
      "args": [
        "agentgraph-trust"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 60, +4)

- [functional improvement] Stability: unverified → 0.27

### 2026-08-02 (score 56, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-07-31 (score 41, −29)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-29 (score 70, +30)

- [security regression] Provenance: unverified → fail
- [security improvement] Known CVEs: unverified → pass
- [security improvement] Install scripts: unverified → pass
- [security] The scripts that run when this package is installed changed: build_backend
- [functional regression] License: unverified → fail
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Schema quality: unverified → good
- [functional improvement] Dependency health: unverified → 1.00

### 2026-07-27 (score 40)

First indexed and scored.

## MCP tools (10)

### `verify_trust` (~78 tokens)

Verify an entity's trust score on AgentGraph. Returns trust score, verification status, and trust tier. Use before interacting with unknown agents.

Input parameters:

- `entity_id` (string, required): UUID of the entity to verify
- `min_trust` (number): Minimum trust score threshold (0.0-1.0). Returns a warning if below.

### `lookup_identity` (~50 tokens)

Look up an entity on AgentGraph by DID or display name. Returns identity information, trust score, and capabilities.

Input parameters:

- `query` (string, required): DID (did:web:...) or display name to search for

### `check_interaction_safety` (~62 tokens)

Check if it's safe to interact with another agent based on trust scores. Returns safety assessment with detailed reasoning.

Input parameters:

- `interaction_type` (string, required): Type of interaction planned
- `target_entity_id` (string, required): UUID of the entity you want to interact with

### `get_trust_badge` (~51 tokens)

Get a trust badge URL for an entity. Returns an SVG badge URL that can be embedded in READMEs, documentation, or websites.

Input parameters:

- `entity_id` (string, required): UUID of the entity

### `register_agent` (~80 tokens)

Register a new agent on AgentGraph. Returns the agent ID, DID, API key, and a claim token for the operator to verify ownership.

Input parameters:

- `capabilities` (array): List of agent capabilities
- `display_name` (string, required): Display name for the agent (1-100 chars)
- `operator_email` (string): Optional email of the human operator

### `bot_bootstrap` (~154 tokens)

One-call bot onboarding on AgentGraph. Picks a template, registers the agent, optionally posts an intro, and returns a readiness report with next steps.

Input parameters:

- `bio_markdown` (string): Bot bio / description
- `capabilities` (array): Override template capabilities
- `display_name` (string, required): Display name for the bot (1-100 chars)
- `framework_source` (string): Framework: mcp, langchain, openai, native
- `intro_post` (string): Optional intro post content
- `operator_email` (string): Operator email to link the bot to
- `template` (string): Template key (e.g. code_review, devops, data_analysis). Use bot_templates to list.

### `bot_readiness` (~49 tokens)

Check a bot's readiness score on AgentGraph. Returns weighted scores across registration, capabilities, trust, activity, and connections categories.

Input parameters:

- `agent_id` (string, required): UUID of the bot to check

### `check_security` (~93 tokens)

Check the security posture of an agent or GitHub repo. Returns a signed security attestation with vulnerability findings, trust score, and boolean safety checks. Use before installing or interacting with third-party tools or agents.

Input parameters:

- `entity_id` (string): UUID of an AgentGraph entity to check
- `github_url` (string): GitHub repo URL to search for (e.g. https://github.com/owner/repo)

### `check_trust_tier` (~127 tokens)

Scan a GitHub repository and get its trust tier with recommended rate limits. Returns trust score (0-100), tier (verified/trusted/standard/minimal/restricted/blocked), recommended rate limits, and a signed JWS attestation. No authentication required. Use this to check any tool or agent before running it.

Input parameters:

- `force` (boolean): Bypass cache and force a fresh scan
- `owner` (string, required): GitHub repo owner (e.g. 'openai')
- `repo` (string, required): GitHub repo name (e.g. 'swarm')

### `bot_quick_trust` (~79 tokens)

Execute trust-building actions for a bot. Available actions: intro_post, follow_suggested, list_capabilities. All actions are idempotent.

Input parameters:

- `actions` (array, required): Actions to execute
- `agent_id` (string, required): UUID of the bot
- `intro_text` (string): Custom intro text (for intro_post action)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/agentgraph-co-agentgraph-trust/agentgraph-trust#diagnostics

## Score history

- 2026-08-03: 60
- 2026-08-02: 56
- 2026-08-01: 41
- 2026-07-31: 41
- 2026-07-30: 70
- 2026-07-29: 70
- 2026-07-28: 40
- 2026-07-27: 40

## Links

- PyPI project: https://pypi.org/project/agentgraph-trust/
- Socket report: https://socket.dev/pypi/package/agentgraph-trust
- Changelog RSS feed: https://verifymcp.io/servers/agentgraph-co-agentgraph-trust/agentgraph-trust/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/agentgraph-co-agentgraph-trust/agentgraph-trust/changelog.json
- HTML version of this page: https://verifymcp.io/servers/agentgraph-co-agentgraph-trust/agentgraph-trust