Skip to main content
Glama
avatrix1

StructureAI MCP Server

by avatrix1
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

StructureAI MCP Server

Extract structured JSON from unstructured text. Works with any MCP-compatible client (Claude Desktop, Cursor, etc).

Supported Schemas

  • receipt — items, totals, dates, merchant info

  • invoice — line items, amounts, due dates, parties

  • email — sender, recipients, subject, body, dates

  • resume — name, experience, education, skills

  • contact — name, email, phone, address, social

  • custom — define your own fields

Related MCP server: Resume Parser MCP

Install

npm install -g @avatrix/structureai-mcp

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "structureai": {
      "command": "structureai-mcp"
    }
  }
}

From source

git clone https://github.com/avatrix1/structureai-mcp.git
cd structureai-mcp
npm install && npm run build
node dist/index.js

Usage

The server exposes one tool: extract_structured_data

Parameters:

  • text (required) — The unstructured text to extract from

  • schema (required) — One of: receipt, invoice, email, resume, contact, custom

  • custom_fields (optional) — Array of field names when using "custom" schema

  • api_key (optional) — Your API key for higher limits

Pricing

License

MIT

Available Tools

1 tool
extract_structured_dataA

Extract structured JSON from unstructured text. Supports schemas: receipt, invoice, email, resume, contact, custom. Free tier: 10 requests. Get an API key at https://api-service-wine.vercel.app for 500 more requests ($2).

ParametersJSON Schema
NameRequiredDescriptionDefault
textYesThe unstructured text to extract data from
schemaYesThe type of data to extract
api_keyNoYour API key. Get one at https://api-service-wine.vercel.app ($2 for 500 requests)
custom_fieldsNoCustom field names when schema is 'custom'

TDQS

A4.1/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It indicates extraction is safe (read-only implied) and mentions free tier limitations. However, it lacks details on error handling, rate limits beyond the free tier, and behavior for unsupported or malformed input.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise: two sentences front-loading the core purpose and then providing essential supplementary info. Every sentence is useful with no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has no output schema, so the description should ideally describe the returned JSON structure. It only states 'structured JSON' vaguely. The description is adequate for basic use but leaves out output format details and error scenarios.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so parameters are already documented. The description adds value by explaining the api_key parameter's purpose and how to obtain one, and it clarifies the supported schemas beyond the enum values.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool extracts structured JSON from unstructured text and lists supported schemas (receipt, invoice, email, resume, contact, custom). It directly defines the verb, resource, and scope without ambiguity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides context on limitations (free tier of 10 requests) and how to obtain an API key for more requests. While there are no sibling tools to distinguish, this guidance helps the agent understand usage constraints.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

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

  1. 1 tool updatev1.0.0
    • First observedextract_structured_data
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.2/5.0

Scored across 1 tool

Disambiguation5/5

Only one tool exists, so there is no possibility of confusion between tools. The single tool has a clear, distinct purpose.

Naming Consistency5/5

The tool name 'extract_structured_data' follows a clear verb_noun pattern (snake_case) and is descriptive. With a single tool, consistency is trivially perfect.

Tool Count4/5

One tool is minimal but appropriate for a focused server that handles multiple extraction schemas through a single interface. It is slightly under the typical well-scoped range but still reasonable.

Completeness4/5

The tool covers the core functionality of extracting structured data from text for several common schemas. Minor gaps like a status or usage check are not critical, and the tool is complete for its stated purpose.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • Resume Parser MCP

    Acidlambunk
    F
    license
    Not graded
    quality
    D
    maintenance
    Enables parsing of raw resume text into structured JSON format with organized sections for skills, experience, education, and projects. Uses Google's Gemini AI model to extract and categorize resume information from unstructured text input.
    -

  • Invoice Parser MCP

    knportal
    A
    license
    Not graded
    quality
    D
    maintenance
    Enables AI agents to extract structured JSON from invoices and receipts in PDF and image formats using Claude Vision. Supports full document parsing, line item extraction, validation, and batch CSV export with API key or cryptocurrency payment options.
    MIT

  • SchemaFetch MCP Server

    Fourier18
    F
    license
    Not graded
    quality
    B
    maintenance
    Enables AI agents to extract structured JSON data from web pages using presets or custom JSON schemas, with confidence scores and source snippets, paid per call via USDC on Base.
    -

Appeared in Searches