Skip to main content
Glama
Sign In
armavita-originality-ai-mcp

armavita-originality-ai-mcp

by EfrainTorres
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

armavita-originality-ai-mcp

armavita-originality-ai-mcp is a local-first MCP server for Originality.ai scanning workflows. It is built for local MCP clients (Claude Code, Cursor, Codex) and supports:

  • AI detection, plagiarism, readability, grammar, fact-checking, and SEO scans

  • stdio MCP transport only

  • Python >=3.11

  • mcp==1.26.0

  • License: AGPL-3.0-only

Current contract version: 2.0.0.

Install

Package install (enables the armavita-originality-ai-mcp CLI):

pip install -e .

Local launcher install (recommended for repo development):

python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt

Related MCP server: originality-mcp

Run

bash ./run.sh

Alternative entrypoints:

python run.py
armavita-originality-ai-mcp

Required Environment Variable

  • ORIGINALITY_API_KEY: Originality.ai API key used for all API requests.

Quick MCP Client Config

Canonical server key and path:

{
  "mcpServers": {
    "armavita-originality-ai": {
      "command": "bash",
      "args": ["/absolute/path/to/armavita-originality-ai-mcp/run.sh"],
      "env": {
        "ORIGINALITY_API_KEY": "your_api_key_here"
      }
    }
  }
}

Tool Coverage

  • Scanning: scan_ai, scan_full, scan_plagiarism, scan_readability, scan_seo, scan_url

  • Retrieval and account: get_scan_results, credit_balance

Security

  • Never commit real ORIGINALITY_API_KEY values.

  • Keep credentials in client/server env config, not in source files.

Development

Quick syntax check:

python -m py_compile run.py armavita_originality_ai_mcp/server.py armavita_originality_ai_mcp/client.py armavita_originality_ai_mcp/handlers/scan_handlers.py armavita_originality_ai_mcp/tools/scan_tools.py

Docs

Scope

  • This repository is an OSS local MCP server.

  • Transport mode is local stdio only.

License

GNU Affero General Public License v3.0 (AGPLv3). See LICENSE.

Available Tools

8 tools
credit_balanceA

Check your Originality.ai credit balance. Returns remaining credits available for scanning. Use before batch operations to verify you have enough credits.

Inputs: no named parameters.

get_scan_resultsA

Retrieve previously stored scan results by scan ID. Use this to fetch full results for scans that were stored (storeScan=true), or to check on scans that may have been processing when originally submitted.

Inputs: scan_id (required).

scan_aiA

Detect AI-generated content using Originality.ai. Returns an overall AI vs. Original percentage and a sentence-by-sentence breakdown with confidence scores. Use this after writing content to check AI detection scores before publishing. Costs ~1 credit per 100 words.

Inputs: content (required), title.

scan_fullA

Run a comprehensive content audit: AI detection + plagiarism + readability + grammar/spelling + fact-checking. Returns all scores in one call. Plagiarism checks can take up to 60 seconds. Use for pre-publish content audits. Costs credits for each enabled check.

Inputs: content (required), title, check_facts, excluded_urls.

scan_plagiarismA

Check content for plagiarism only — no AI detection, readability, or grammar. Returns an overall plagiarism percentage and matched sources with URLs. Plagiarism checks can take up to 60 seconds. Use to verify content originality before publishing. Cheaper than scan_full since only plagiarism credits are used.

Inputs: content (required), title, excluded_urls.

scan_readabilityA

Analyze content readability and grammar only — no AI detection or plagiarism. Returns Flesch Reading Ease, grade level, sentence difficulty breakdown, and grammar/spelling errors with corrections. Fast and cheap. Use to check if content meets the 8th-9th grade reading level target.

Inputs: content (required), title.

scan_seoB

Run SEO content optimization analysis for a target keyword. Returns keyword seed recommendations with min/max/current density targets. Combine with AI detection and readability for a full content quality check. Currently supports United States only.

Inputs: content (required), keyword (required), title, device, +3 more.

scan_urlA

Scan a published URL for AI content, plagiarism, readability, and grammar. Originality.ai fetches and extracts the page content automatically. Use to audit competitor content or verify published articles.

Inputs: url (required), title, check_ai, check_plagiarism, +4 more.

Tool Schema Changelog

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

Loading tool schema changelog…

    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

    A4/5.0

    Scored across 8 tools

    Disambiguation4/5

    Most tools have distinct purposes, such as credit_balance for account checks, get_scan_results for retrieval, and various scan_* tools for different content analyses (AI, plagiarism, readability, SEO, URL). However, scan_full overlaps with other scans by combining multiple checks, which could cause confusion when an agent needs a specific analysis like plagiarism alone versus the comprehensive option.

    Naming Consistency5/5

    All tool names follow a consistent snake_case pattern with clear verb_noun structures, such as credit_balance, get_scan_results, and scan_ai. The naming is predictable and readable, making it easy for agents to understand the action and target at a glance.

    Tool Count5/5

    With 8 tools, the server is well-scoped for content analysis and auditing, covering essential operations like balance checks, result retrieval, and various scanning types. Each tool serves a clear purpose without being overly broad or thin, fitting the domain effectively.

    Completeness4/5

    The tool set provides comprehensive coverage for content auditing, including AI detection, plagiarism, readability, SEO, and URL scanning, plus account management with credit_balance and result retrieval. A minor gap is the lack of a tool for managing scans (e.g., deleting or listing stored results), but agents can work around this with the existing tools.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Resources

    Related MCP Connectors

    Related MCP Servers