Skip to main content
Glama
review-gate-mcp

review-gate-mcp

by ravnlab

review-gate-mcp

An MCP server that asks a human when it isn't sure.

Most extraction demos guess. This one implements the pattern that makes automation safe to run on documents that matter: fields extracted with high confidence flow through; anything uncertain is held in a review queue for a person to resolve - never silently guessed into your systems.

document ──▶ extract_with_gate ──▶ confident fields ──▶ your system
                     │
                     └──▶ uncertain fields ──▶ review_queue ──▶ a human ──▶ resolve_review

Tools

tool

what it does

extract_with_gate

extract invoice_number, total_amount, date, email, vendor_name from text; confidence below 0.85 goes to the queue instead of the output

review_queue

list items waiting for a human decision

resolve_review

a human supplies the verified value, closing the loop

Related MCP server: PDF Reader MCP Server

Run it

npm install
npm test          # end-to-end over real MCP stdio: extract -> hold -> human resolve

Add to Claude Code / Claude Desktop / Cursor (any MCP client):

{
  "mcpServers": {
    "review-gate": { "command": "node", "args": ["/path/to/review-gate-mcp/server.js"] }
  }
}

Then ask your agent to extract fields from a pasted document and watch what it does with the smudged one.

The point

The extractors here are deliberately transparent heuristics - swap in a model-backed extractor and the gate stays identical. The pattern is the product: a system that escalates its hard cases beats one that guesses them. This is the standard RavnLab builds automation to; the evaluation side of the same idea lives in ravnlab-eval-harness.

MIT. Built by RavnLab.

Available Tools

3 tools
extract_with_gateA

Extract fields from a document. High-confidence values return immediately; uncertain values are held in a human-review queue instead of guessed. Fields: invoice_number, total_amount, date, email, vendor_name.

Inputs: text (required), fields (required).

resolve_reviewB

A human supplies the correct value for a held item, closing the loop.

Inputs: value (required), review_id (required).

review_queueA

List extraction items currently waiting for a human decision.

Inputs: no named parameters.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.9/5.0

    Scored across 3 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: extraction, resolving held items, and listing the queue. No overlap or ambiguity between the three.

    Naming Consistency4/5

    All tool names use snake_case and follow a verb-focused pattern (extract_with_gate, resolve_review, review_queue). The 'with_gate' modifier is slightly unconventional but consistent within the set.

    Tool Count4/5

    Three tools is appropriate for the narrow domain of document extraction with human review. The count feels minimal but sufficient for the core workflow.

    Completeness4/5

    The toolset covers the primary extraction workflow (extract, review queue, resolve). Minor gaps like skipping or rejecting items are absent but not critical for the stated purpose.

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      An MCP server that provides comprehensive PDF processing capabilities including text extraction, image extraction, table detection, annotation extraction, metadata retrieval, page rendering, and document structure analysis.
      -
    • A
      license
      Not graded
      quality
      D
      maintenance
      A document intelligence MCP server that extracts text and structured fields from business documents, routes low-confidence extractions to a human review queue, and enables searching across processed documents.
      MIT