# io.github.lesofi/handinloop-mcp-server (npm · handinloop-mcp-server)

Human-in-the-loop document extraction: submit a doc, get validated fields and an audit trail.

- Trust score: 62/100 (medium)
- Change this week: +44
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `handinloop-mcp-server`: 62/100 (this document), [markdown](https://verifymcp.io/servers/lesofi-handinloop-mcp-server/handinloop-mcp-server.md), [page](https://verifymcp.io/servers/lesofi-handinloop-mcp-server/handinloop-mcp-server)

## Channel facts

- Registry: `npm`
- Package: `handinloop-mcp-server`
- Version: `0.4.0`
- 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**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (95 of 99), 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 (95 of 99), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 19/100
  - Repository check failed: the declared repository URL returned HTTP 404.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 22 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 68/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1223 tokens (~203/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 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 lesofi-handinloop-mcp-server -- npx -y handinloop-mcp-server
```

### Codex

```bash
codex mcp add lesofi-handinloop-mcp-server -- npx -y handinloop-mcp-server
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add lesofi-handinloop-mcp-server --command npx --arg -y --arg handinloop-mcp-server
```

### Hermes

```yaml
mcp_servers:
  lesofi-handinloop-mcp-server:
    command: "npx"
    args: ["-y", "handinloop-mcp-server"]
```

### Other

```json
{
  "mcpServers": {
    "lesofi-handinloop-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "handinloop-mcp-server"
      ]
    }
  }
}
```

## 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 62, +46)

- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [functional improvement] Stability: unverified → 0.23
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] License: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Schema quality: unverified → excellent
- [functional] Licence: MIT

### 2026-08-02 (score 16, +3)

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

### 2026-07-31 (score 13, −5)

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

### 2026-07-30 (score 18, −19)

- [functional regression] Tool coverage: 100 → unverified

### 2026-07-28 (score 37, +19)

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

### 2026-07-27 (score 18)

First indexed and scored.

## MCP tools (6)

### `handinloop_list_task_types` (~77 tokens)

List HandInLoop Task Types

List the document extraction task types the HandInLoop human-in-the-loop platform supports.

Call this first to discover valid 'task_type' values for handinloop_submit_extraction_job, and to see which fields each task type returns.

Returns: { task_types: [{ id, name, description, output_fields[] }] }

### `handinloop_propose_fields` (~217 tokens)

Propose Extraction Fields

Ask HandInLoop to propose the fields worth extracting from a document — the "what should I extract?" assist.

Given a document (and an optional goal), the model suggests a field set you can then pass as 'fields' to handinloop_submit_extraction_job for a custom, human-verified extraction. Synchronous: returns immediately, no job, no human review.

Args:
  \- document_url OR document_base64: the document (PDF/image). Exactly one required.
  \- file_name (optional)
  \- goal (optional): focus, e.g. "accounts payable"

Returns: { fields: [{ name, description }] }

Input parameters:

- `document_base64` (string): Base64-encoded document content (alternative to document_url)
- `document_url` (string): Publicly fetchable URL of the document (PDF or image)
- `file_name` (string): Original filename, e.g. 'do-123.pdf'
- `goal` (string): Optional focus, e.g. 'accounts payable'

### `handinloop_save_task_type` (~236 tokens)

Save a Reusable Task Type

Save a named custom field set as a reusable task type (#103 Phase B).

Once saved, submit against it by passing its returned id as 'task_type' to handinloop_submit_extraction_job — no need to re-send the fields each time. Saved types also appear in handinloop_list_task_types. Saving an existing id updates it.

Args:
  \- fields: [{ name, description? }] — the field set (required, at least one).
  \- name (optional): human name; the id is derived from it if 'id' is omitted.
  \- id (optional): stable handle (lowercase letter then letters/digits/underscores). Must not collide with a built-in.
  \- description (optional).

Returns the saved TaskType { id, name, description, output_fields }.

Input parameters:

- `description` (string): Optional description of the type
- `fields` (array, required): The field set to save (at least one)
- `id` (string): Stable handle; derived from name if omitted
- `name` (string): Human name, e.g. 'Delivery Order'

### `handinloop_submit_extraction_job` (~384 tokens)

Submit Extraction Job

Submit a document to HandInLoop for extraction with human-in-the-loop validation.

AI extracts the document first; low-confidence fields are routed to a trained human reviewer. The result is validated data with per-field confidence and a complete audit trail.

ASYNC: returns immediately with a job_id and status 'queued'. Human turnaround is minutes to hours in production — poll handinloop_get_job_status (respect estimated_seconds_remaining), then call handinloop_get_job_result once status is 'completed'. Ideal for scheduled/recurring workflows.

Args:
  \- task_type: one of the ids from handinloop_list_task_types (e.g. "invoice"), OR
  \- fields: for CUSTOM extraction, describe the fields to extract yourself — [{ name, description? }]. Works on ANY document, not just the built-in task types. Provide task_type OR fields.
  \- document_url OR document_base64: the document (PDF/image). Exactly one required.
  \- file_name (optional): original filename for routing and audit
  \- instructions (optional): note for the human reviewer

Returns: { job_id, task_type, status, submitted_at, estimated_seconds_remaining }

Input parameters:

- `document_base64` (string): Base64-encoded document content (alternative to document_url)
- `document_url` (string): Publicly fetchable URL of the document (PDF or image)
- `fields` (array): Custom extraction: define the fields to extract instead of a built-in task_type. Provide task_type OR fields.
- `file_name` (string): Original filename, e.g. 'inv-04187.pdf'
- `instructions` (string): Free-form note passed to the human reviewer
- `task_type` (string): Built-in task type id from handinloop_list_task_types, e.g. 'invoice'. Provide this OR fields.

### `handinloop_get_job_status` (~142 tokens)

Get Job Status

Check the status of a previously submitted extraction job.

Statuses: 'queued' (waiting for a worker) -> 'in_review' (human processing) -> 'completed' (result ready) | 'rejected' (invalid document).

Use estimated_seconds_remaining to pick a sensible polling interval; for scheduled routines, checking on the next run is usually enough.

Args:
  \- job_id: id returned by handinloop_submit_extraction_job

Returns: { job_id, task_type, status, submitted_at, finished_at?, estimated_seconds_remaining? }

Input parameters:

- `job_id` (string, required): Job id returned by handinloop_submit_extraction_job

### `handinloop_get_job_result` (~167 tokens)

Get Job Result

Fetch the validated extraction result for a completed job.

Only call once handinloop_get_job_status reports status 'completed' (calling earlier returns an error with the remaining time).

Returns: {
  job_id, task_type, status,
  fields: [{ name, value, confidence (0..1), human_verified }],
  line_items?: [...],            // for invoice-like documents
  audit_trail: [{ at, actor: system|ai|human, action }]
}

Fields with human_verified=true were reviewed or corrected by a trained human — treat confidence 1.0 as authoritative. The audit_trail documents every step for compliance purposes; preserve it when storing results.

Input parameters:

- `job_id` (string, required): Job id returned by handinloop_submit_extraction_job

## Diagnostics

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

## Score history

- 2026-08-03: 62
- 2026-08-02: 16
- 2026-08-01: 13
- 2026-07-31: 13
- 2026-07-30: 18
- 2026-07-28: 37
- 2026-07-27: 18

## Links

- npm package: https://www.npmjs.com/package/handinloop-mcp-server
- Socket report: https://socket.dev/npm/package/handinloop-mcp-server
- Changelog RSS feed: https://verifymcp.io/servers/lesofi-handinloop-mcp-server/handinloop-mcp-server/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/lesofi-handinloop-mcp-server/handinloop-mcp-server/changelog.json
- HTML version of this page: https://verifymcp.io/servers/lesofi-handinloop-mcp-server/handinloop-mcp-server