Skip to main content
Glama
nik-kale

pangram-editorial

by nik-kale
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

Pangram MCP Editorial Tools

An MCP (Model Context Protocol) server that integrates Pangram's AI attribution APIs into professional writing workflows.

Designed for editorial review, transparency, and quality assurance when AI-assisted tools are used in journalism, research, and enterprise content creation.

Use Cases

  • Newsrooms & Publishers — Audit AI attribution before publication

  • Academic Writers — Verify transparency requirements for submissions

  • Enterprise Content Teams — QA workflows for AI-assisted documentation

  • Legal & Compliance — Attribution audits for authored materials

Related MCP server: PureRank MCP Server

Features

Tool

Purpose

pangram_attribution_audit

Detailed attribution and segment analysis for transparency audits

pangram_quick_snapshot

Quick attribution snapshot for editorial review

Quick Start

1. Install

git clone https://github.com/nicholasgriffintn/pangram-mcp-editorial-tools.git
cd pangram-mcp-editorial-tools
npm install
npm run build

2. Get Your Pangram API Key

  1. Go to pangram.com

  2. Log in to your dashboard

  3. Click API in the header

  4. Copy your API key

3. Configure Claude Desktop

Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

{
  "mcpServers": {
    "pangram-editorial": {
      "command": "node",
      "args": ["/absolute/path/to/pangram-mcp-editorial-tools/dist/index.js"],
      "env": {
        "PANGRAM_API_KEY": "your-api-key-here"
      }
    }
  }
}

4. Restart Claude Desktop

The Pangram editorial tools will now be available in all your conversations.

Usage Examples

Once connected, use naturally in Claude:

"Run an attribution audit on this article before I submit it"

"Quick transparency check on this draft"

"Analyze the authorship segments in my report"

Tools Reference

pangram_attribution_audit

Comprehensive attribution analysis providing:

  • Overall authorship assessment

  • Segment-by-segment attribution breakdown

  • Confidence metrics per section

  • Transparency report suitable for editorial review

Parameters:

  • text (required): Content to analyze (minimum 50 words)

  • response_format (optional): "markdown" (default) or "json"

pangram_quick_snapshot

Fast attribution check for iterative editorial workflows:

  • Summary authorship indicator

  • Attribution percentage

  • Quick review status

Parameters:

  • text (required): Content to analyze (minimum 50 words)

Requirements

  • Node.js 18+

  • Pangram API key (pangram.com)

  • Claude Desktop or any MCP-compatible client

API Note

Pangram's API is priced separately from their web dashboard subscription. See pangram.com/solutions/api for details.

Development

npm install
npm run build
npm run dev  # watch mode

About

This project addresses the growing need for attribution transparency in professional writing workflows. As AI-assisted authorship becomes standard practice in journalism, research, and enterprise content, tools that provide clear attribution analysis support responsible disclosure and editorial integrity.

License

MIT

Contributing

Contributions welcome. Please ensure any additions maintain the project's focus on editorial transparency and professional quality assurance.

Available Tools

2 tools
pangram_attribution_auditAttribution AuditB
Read-onlyIdempotent

Analyze text for AI attribution using Pangram's attribution analysis API.

This tool provides transparency analysis for AI-assisted content, supporting editorial review and quality assurance workflows. It identifies authorship patterns and provides segment-level attribution breakdowns.

Analysis includes:

  • Overall authorship assessment

  • Average and maximum AI attribution scores

  • Breakdown of authorship patterns by segment

  • Segment-by-segment attribution analysis with confidence levels

Args:

  • text (string): The content to analyze. Must be at least 50 words for accurate analysis.

  • response_format ('markdown' | 'json'): Output format (default: 'markdown')

Returns:

  • Markdown: Formatted transparency report with authorship assessment and segment analysis

  • JSON: Structured data with all attribution metrics

Use cases:

  • Editorial review before publication

  • Transparency audits for AI-assisted content

  • Quality assurance for professional writing workflows

  • Attribution documentation for compliance requirements

Requires: PANGRAM_API_KEY environment variable to be set

ParametersJSON Schema
NameRequiredDescriptionDefault
textYesThe text content to analyze for AI detection. Minimum 50 words required.
response_formatNoOutput format: 'markdown' for human-readable or 'json' for structured datamarkdown

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare the tool as read-only, idempotent, and non-destructive. The description adds context about requiring an API key, minimum text length, and analysis details, but does not disclose potential limitations or error handling, which would enhance transparency.

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

Conciseness3/5

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

The description is structured with bullet points and sections, but is somewhat verbose and could be more concise. Some information is redundant with the schema, and the description could be trimmed without losing clarity.

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

Completeness4/5

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

Given the tool has two parameters, no output schema, and annotations, the description covers purpose, parameters, output formats, and use cases adequately. It mentions required environment variable and minimum text length. Could be improved by noting error conditions or rate limits, but overall complete.

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

Parameters3/5

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

Schema coverage is 100%, with both parameters described in the schema. The description reiterates this information and adds a default for response_format, but does not provide meaningful additional semantics beyond what the schema already offers.

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

Purpose4/5

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

The description clearly states the tool analyzes text for AI attribution using Pangram's API, listing specific outputs and use cases. However, it does not differentiate from the sibling tool 'pangram_quick_snapshot', missing the opportunity to clarify unique purpose.

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

Usage Guidelines3/5

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

The description provides several use cases (editorial review, transparency audits, QA, compliance) but does not specify when not to use this tool or suggest alternatives. Given the sibling tool, explicit guidelines for selection would be beneficial.

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

pangram_quick_snapshotQuick Attribution SnapshotA
Read-onlyIdempotent

Get a quick attribution snapshot for editorial review.

Returns essential metrics for fast iteration during the writing and editing process. Use this for rapid checks when detailed segment analysis isn't needed.

Args:

  • text (string): The content to analyze. Must be at least 50 words.

Returns: A brief summary with:

  • Authorship indicator

  • Attribution percentage

  • Review status

Example: "Quick snapshot for this paragraph" → "✅ PRIMARY AUTHOR - 12.3% AI attribution"

ParametersJSON Schema
NameRequiredDescriptionDefault
textYesThe text content to analyze. Minimum 50 words required.

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already indicate read-only and idempotent. Description adds that it's a snapshot, returns specific metrics, and has word count requirement. No contradictions.

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?

Description is brief, well-structured with args, returns, and example. No superfluous content.

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

Completeness4/5

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

Tool is simple but description covers purpose, usage context, parameter requirement, and return structure with example. Lacks explicit error handling or edge cases, but adequate for this tool.

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

Parameters3/5

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

Schema description covers the parameter; description repeats the 50-word requirement but adds no new semantic information beyond the schema. Baseline 3 due to high schema coverage.

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?

Explicitly states 'get a quick attribution snapshot for editorial review' and contrasts with sibling tool by noting it's for rapid checks not detailed analysis. Distinguishable.

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

Usage Guidelines5/5

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

Recommends using for rapid checks when detailed segment analysis isn't needed, and states text must be at least 50 words.

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. 2 tool updatesv1.0.0
    • First observedpangram_attribution_audit
    • First observedpangram_quick_snapshot
Deploy Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.8/5.0

Scored across 2 tools

Disambiguation5/5

Both tools analyze AI attribution but serve different purposes: one provides a comprehensive audit with segment-level breakdowns, the other gives a quick summary. Their descriptions clearly distinguish them, so no ambiguity.

Naming Consistency4/5

Both tools use the 'pangram_' prefix and snake_case, but one uses 'attribution_audit' (noun_noun) and the other 'quick_snapshot' (adjective_noun). This is a minor inconsistency; otherwise, naming is predictable.

Tool Count3/5

The server has only 2 tools, which feels thin for a domain that could benefit from additional tools like batch analysis or report generation. However, the two levels of detail (quick and comprehensive) are well-scoped for its purpose.

Completeness4/5

For the narrow domain of AI attribution analysis, the tools cover quick and detailed analysis. There are no obvious missing operations, as it's a pure analysis service. Minor gap: no batch or comparison feature.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • PureRank MCP Server

    vadimsv1
    A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI agents to score drafts for AI-content-spam risk before publishing and scan entire sites, providing a pre-publish QA gate with pass/warn/fail verdicts.
    8
    MIT

  • content-qa-mcp

    Alvi-808
    A
    license
    A
    quality
    C
    maintenance
    Enables editorial content QA over the Model Context Protocol with four local tools that analyze readability, AI-sounding language, SEO on-page factors, and produce full reports where every finding includes an actionable fix.
    4
    1
    MIT