# io.github.agenson-horrowitz/agent-output-guard (npm · @agenson-horrowitz/agent-output-guard-mcp)

Validate and verify data from other agents before acting on it. Zero LLM costs.

- Trust score: 68/100 (medium)
- Change this week: +22
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `@agenson-horrowitz/agent-output-guard-mcp`: 68/100 (this document), [markdown](https://verifymcp.io/servers/agenson-horrowitz-agent-output-guard/agenson-horrowitz-agent-output-guard-mcp.md), [page](https://verifymcp.io/servers/agenson-horrowitz-agent-output-guard/agenson-horrowitz-agent-output-guard-mcp)

## Channel facts

- Registry: `npm`
- Package: `@agenson-horrowitz/agent-output-guard-mcp`
- Version: `1.0.8`
- 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**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (96 of 100), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (96 of 100), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 122 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 70/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 521 tokens (~104/item across 5 items; 5 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**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add agenson-horrowitz-agent-output-guard -- npx -y @agenson-horrowitz/agent-output-guard-mcp
```

### Codex

```bash
codex mcp add agenson-horrowitz-agent-output-guard -- npx -y @agenson-horrowitz/agent-output-guard-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "agenson-horrowitz-agent-output-guard": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@agenson-horrowitz/agent-output-guard-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add agenson-horrowitz-agent-output-guard --command npx --arg -y --arg @agenson-horrowitz/agent-output-guard-mcp
```

### Hermes

```yaml
mcp_servers:
  agenson-horrowitz-agent-output-guard:
    command: "npx"
    args: ["-y", "@agenson-horrowitz/agent-output-guard-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "agenson-horrowitz-agent-output-guard": {
      "command": "npx",
      "args": [
        "-y",
        "@agenson-horrowitz/agent-output-guard-mcp"
      ]
    }
  }
}
```

## 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.

### 2026-08-02 (score 68, +32)

- [security regression] Provenance: unverified → fail
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → pass
- [functional improvement] License: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Stability: unverified → 0.23
- [functional improvement] Schema quality: unverified → good
- [functional] Licence: MIT

### 2026-08-01 (score 36, +8)

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

### 2026-07-31 (score 28, +4)

- [security regression] Malware scan: pass → unverified
- [functional improvement] Tool coverage: unverified → 100

### 2026-07-30 (score 24, −22)

- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified

### 2026-07-27 (score 46)

First indexed and scored.

## MCP tools (5)

### `verify_json_schema` (~100 tokens)

Validate JSON data from another agent against expected schema. Essential for preventing malformed data propagation in multi-agent workflows. Returns validation status, errors, and confidence score.

Input parameters:

- `data` (required): JSON data received from another agent
- `schema` (object, required): Expected JSON schema for validation
- `source_agent` (string): Identifier of the agent that provided this data (for audit trail)
- `strict_validation` (boolean): Enable strict validation mode (fails on additional properties)

### `detect_hallucination_markers` (~104 tokens)

Scan agent output for common hallucination patterns, uncertainty markers, and fabrication indicators. Critical for multi-agent reliability. Returns detailed analysis and confidence score.

Input parameters:

- `content_type` (string): Type of content being analyzed for context-aware detection
- `sensitivity_level` (string): Detection sensitivity (high = more conservative)
- `source_agent` (string): Identifier of the agent that generated this text
- `text` (string, required): Text output from another agent to analyze

### `validate_data_freshness` (~119 tokens)

Check if data from another agent is recent and valid based on timestamps, staleness indicators, and expected update frequencies. Prevents acting on outdated information.

Input parameters:

- `data` (required): Data object to check for freshness
- `expected_update_frequency` (string): How often this data should be updated
- `max_age_hours` (number): Maximum acceptable age in hours
- `source_agent` (string): Agent that provided this data
- `timestamp_field` (string): Field name containing timestamp (e.g., "created_at", "updated_at")

### `cross_reference_check` (~87 tokens)

Compare data from multiple agents for consistency and detect discrepancies. Essential for multi-agent coordination. Returns consistency score and detailed comparison.

Input parameters:

- `comparison_fields` (array): Specific fields to compare across datasets
- `primary_data` (required): Primary data object to verify
- `reference_data` (array, required): Array of reference data from other agents
- `tolerance_level` (string): How strict to be with differences

### `output_consistency_score` (~111 tokens)

Calculate overall consistency score for agent output including internal logic, format consistency, and reliability indicators. Returns comprehensive reliability assessment.

Input parameters:

- `context` (string): Context or prompt that generated this output
- `expected_format` (object): Expected structure/format of the output
- `historical_outputs` (array): Previous outputs from same agent for pattern analysis
- `output` (required): Complete output from an agent (text, data, or structured response)
- `source_agent` (string): Agent identifier for tracking reliability over time

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/agenson-horrowitz-agent-output-guard/agenson-horrowitz-agent-output-guard-mcp#diagnostics

## Score history

- 2026-08-03: 68
- 2026-08-02: 68
- 2026-08-01: 36
- 2026-07-31: 28
- 2026-07-30: 24
- 2026-07-28: 46
- 2026-07-27: 46

## Links

- npm package: https://www.npmjs.com/package/@agenson-horrowitz/agent-output-guard-mcp
- Socket report: https://socket.dev/npm/package/@agenson-horrowitz/agent-output-guard-mcp
- Repository: https://github.com/agenson-tools/agent-output-guard-mcp
- Changelog RSS feed: https://verifymcp.io/servers/agenson-horrowitz-agent-output-guard/agenson-horrowitz-agent-output-guard-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/agenson-horrowitz-agent-output-guard/agenson-horrowitz-agent-output-guard-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/agenson-horrowitz-agent-output-guard/agenson-horrowitz-agent-output-guard-mcp