# io.github.louissarvin/proctor (npm · proctor-mcp)

Human oversight for AI agents: block a tool call on a verified human, with on-chain proof.

- Trust score: 73/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-25

## Components

- npm · `proctor-mcp`: 73/100 (this document), [markdown](https://verifymcp.io/servers/louissarvin-proctor/proctor-mcp.md), [page](https://verifymcp.io/servers/louissarvin-proctor/proctor-mcp)

## Channel facts

- Registry: `npm`
- Package: `proctor-mcp`
- Version: `1.0.0`
- 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 2026-09-25.

- **Supply Chain Security**: 89/100
  - No malware found by supply-chain analysis.
  - CVE check failed: a known high-severity CVE affects @grpc/grpc-js 1.12.6, reached via @x402/hedera > @hiero-ledger/sdk > @grpc/grpc-js. A fixed version is available.
  - No install/post-install scripts declared.
  - 34 of 105 dependencies flagged as unhealthy (1 deprecated).
- **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 14 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 77/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 180 tokens (~180/item across 1 items; 1 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 50/100
  - Stability observed for 15 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.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 1 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 2 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the io.github.louissarvin/proctor MCP server?

io.github.louissarvin/proctor runs locally as an npm package, launched with npx -y proctor-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add louissarvin-proctor -- npx -y proctor-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "louissarvin-proctor": {
      "command": "npx",
      "args": [
        "-y",
        "proctor-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "louissarvin-proctor": {
      "command": "npx",
      "args": [
        "-y",
        "proctor-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add louissarvin-proctor -- npx -y proctor-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "louissarvin-proctor": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "proctor-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add louissarvin-proctor --command npx --arg -y --arg proctor-mcp
```

### Hermes

```yaml
mcp_servers:
  louissarvin-proctor:
    command: "npx"
    args: ["-y", "proctor-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "louissarvin-proctor": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "proctor-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add louissarvin-proctor -t stdio -c npx -a -y proctor-mcp
```

### Other

```json
{
  "mcpServers": {
    "louissarvin-proctor": {
      "command": "npx",
      "args": [
        "-y",
        "proctor-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.

### 2026-09-25 (score 73, 0)

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

### 2026-09-24 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-22 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-20 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-18 (score 70, +4)

- [functional improvement] Stability: unverified → 0.27

### 2026-09-15 (score 66, +5)

- [security improvement] Source repository: unverified → pass

### 2026-09-14 (score 61, −5)

- [security regression] Provenance: pass → unverified

### 2026-09-11 (score 66, +15)

- [security improvement] Malware scan: unverified → pass

## MCP tools (1)

### `request_human_approval` (~149 tokens)

Request human approval

Block until a verified human who is NOT the operator of this agent approves or refuses a high-risk action. Fails closed: no answer before the deadline is a refusal. Returns a tamper-evident citation on a Hedera topic with no admin key, so the decision can be proven to a third party later. Use before any irreversible or high-value action.

Input parameters:

- `action` (string, required): What the agent is about to do, in plain language.
- `amount` (string): Amount, as a decimal string. Drives the policy threshold.
- `counterparty` (string): Who receives the value.
- `ttlSeconds` (number): Deadline. Default 300, max 900.

Output parameters:

- `approved` (boolean)
- `decisionHash` (string)
- `escalated` (boolean): False when policy allowed it without a human.
- `evidence` (string): Where the record can be verified.
- `outcome` (string): APPROVE, REFUSE or EXPIRE.

## Diagnostics

Captured diagnostic sections: Provenance, Vulnerabilities, Dependencies. The full working is on the page: https://verifymcp.io/servers/louissarvin-proctor/proctor-mcp#diagnostics

## Score history

- 2026-09-25: 73
- 2026-09-24: 73
- 2026-09-23: 72
- 2026-09-22: 72
- 2026-09-21: 71
- 2026-09-20: 71
- 2026-09-19: 70
- 2026-09-18: 70
- 2026-09-17: 66
- 2026-09-16: 66
- 2026-09-15: 66
- 2026-09-14: 61
- 2026-09-13: 66
- 2026-09-12: 66
- 2026-09-11: 66
- 2026-09-10: 51

## Common questions

### What is the io.github.louissarvin/proctor MCP server?

io.github.louissarvin/proctor is an MCP server listed in the public MCP registry as io.github.louissarvin/proctor. Human oversight for AI agents: block a tool call on a verified human, with on-chain proof. This page covers its npm package (proctor-mcp).

### Is the io.github.louissarvin/proctor MCP server safe to use?

io.github.louissarvin/proctor scores 73 out of 100 on VerifyMCP. We recorded 9 known advisories against it as of 25 September 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the io.github.louissarvin/proctor MCP server expose?

io.github.louissarvin/proctor exposes 1 tool: request_human_approval. Their descriptions and schemas cost roughly 149 tokens of context every time the server is loaded.

### Is the io.github.louissarvin/proctor MCP server still maintained?

io.github.louissarvin/proctor is still listed as active in the MCP registry. We last reached this channel on 25 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the io.github.louissarvin/proctor MCP server under?

io.github.louissarvin/proctor declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/proctor-mcp
- Socket report: https://socket.dev/npm/package/proctor-mcp
- Repository: https://github.com/louissarvin/proctor
- Changelog RSS feed: https://verifymcp.io/servers/louissarvin-proctor/proctor-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/louissarvin-proctor/proctor-mcp.json
- HTML version of this page: https://verifymcp.io/servers/louissarvin-proctor/proctor-mcp