Skip to main content
Glama
copus-io

Copus MCP Server

Official
by copus-io
OverviewSchemaRelated ServersScoreDiscussions
JavaScript
Remote

Copus MCP Server

An MCP (Model Context Protocol) server that allows AI assistants to search and retrieve human-curated content recommendations from Copus.

What is Copus?

Copus is a human-curated content discovery platform — "The Internet Treasure Map". Unlike SEO-driven search results, Copus surfaces recommendations from real people who explain why content is valuable.

Each curation includes:

  • Curator's personal note — Why they recommend this

  • Curator credentials — Why they're qualified to recommend this

  • Original source URL — The actual content being recommended

  • AI-enhanced metadata — Key takeaways, target audience, problem solved

  • Engagement metrics — Views, saves, comments from the community

Related MCP server: o3-search MCP

What This MCP Server Enables

This server gives AI assistants access to Copus's curated content database. Instead of generic search results, your AI can find:

  • Tools and resources vetted by domain experts

  • Articles recommended by practitioners in the field

  • Hidden gems that real people found valuable enough to share

Compatible AI Platforms

This MCP server works with any AI platform that supports the Model Context Protocol:

  • Claude Desktop (Anthropic)

  • Claude Code (Anthropic)

  • Cursor (AI code editor)

  • Cline (VS Code extension)

  • Continue (VS Code/JetBrains extension)

  • Zed (Code editor)

  • Any other MCP-compatible AI platform

Installation

Quick Start (npx)

No installation required — run directly with npx:

npx copus-mcp-server

Global Installation

npm install -g copus-mcp-server

Then run:

copus-mcp-server

Local Installation

npm install copus-mcp-server

Configuration

Claude Desktop

Add to your Claude Desktop configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "copus": {
      "command": "npx",
      "args": ["copus-mcp-server"]
    }
  }
}

Or if installed globally:

{
  "mcpServers": {
    "copus": {
      "command": "copus-mcp-server"
    }
  }
}

Claude Code

Add to your Claude Code MCP settings:

{
  "mcpServers": {
    "copus": {
      "command": "npx",
      "args": ["copus-mcp-server"]
    }
  }
}

Cursor

Add to your Cursor MCP configuration (.cursor/mcp.json in your project or global settings):

{
  "mcpServers": {
    "copus": {
      "command": "npx",
      "args": ["copus-mcp-server"]
    }
  }
}

Cline (VS Code Extension)

Add to Cline's MCP settings in VS Code:

  1. Open VS Code Settings

  2. Search for "Cline MCP"

  3. Add the server configuration:

{
  "copus": {
    "command": "npx",
    "args": ["copus-mcp-server"]
  }
}

Continue (VS Code/JetBrains)

Add to your Continue configuration (~/.continue/config.json):

{
  "mcpServers": [
    {
      "name": "copus",
      "command": "npx",
      "args": ["copus-mcp-server"]
    }
  ]
}

Available Tools

search_curations

Search human-curated content recommendations on Copus.

Parameters:

  • query (string, required): Search keywords

  • limit (number, optional): Maximum results (default: 10, max: 50)

Returns: Array of curations with:

  • Title and description

  • Curator name and profile

  • Original source URL

  • Category and keywords

  • Engagement metrics (views, saves)

get_curation

Get detailed information about a specific curation.

Parameters:

  • id (string, required): Curation ID (UUID from search results)

Returns: Full curation details including:

  • Curator's personal recommendation note

  • Curator credentials

  • Key takeaways

  • Target audience

  • What problem this content solves

  • Full engagement metrics

Example Use Cases

Once configured, you can ask your AI assistant things like:

Learning Resources

"I want to learn Python, what resources should I check out?"

"Find me some recommended machine learning tutorials"

"What are the best resources for learning web development?"

Tools & Software

"What tools do designers recommend for wireframing?"

"Find me some AI tools that people actually use and recommend"

"What's a good free video editing software?"

Reading & Content

"Any good reads on creative writing?"

"Find me articles about productivity that people found valuable"

"What are some recommended newsletters about tech?"

Specific Topics

"Find watermark remover tools"

"What Linux tools do people recommend?"

"Show me personal growth content recommendations"

Example Response

When you search for "python tutorials", you might get:

{
  "query": "python tutorials",
  "totalResults": 5,
  "results": [
    {
      "id": "abc123...",
      "title": "Real Python - Python Tutorials",
      "description": "Comprehensive Python tutorials covering basics to advanced topics...",
      "originalSource": "https://realpython.com",
      "category": "Technology",
      "curator": "experienced_dev",
      "engagement": {
        "views": 150,
        "saves": 23
      }
    }
  ]
}

Why Use Copus Over Regular Search?

Regular Search

Copus Curations

SEO-optimized results

Human-selected recommendations

Algorithm-driven

Expert-vetted content

No context on quality

Curator explains why it's valuable

Anonymous sources

Known curator with credentials

Quantity-focused

Quality-focused

Development

Building from Source

git clone https://github.com/copus-io/copus-mcp-server.git
cd copus-mcp-server
npm install
npm run build

Running in Development

npm run dev

Testing

# Run the server
npm start

# In another terminal, test with MCP inspector or your AI platform

API Reference

This MCP server wraps the Copus public API:

  • Search API: https://copus.network/api/search?q={query}

  • Curation Details: https://copus.network/work/{id}?format=json

  • OpenAPI Spec: https://copus.network/.well-known/openapi.yaml

  • AI Plugin Manifest: https://copus.network/.well-known/ai-plugin.json

Links

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

  1. Fork the repository

  2. Create your feature branch (git checkout -b feature/amazing-feature)

  3. Commit your changes (git commit -m 'Add amazing feature')

  4. Push to the branch (git push origin feature/amazing-feature)

  5. Open a Pull Request

License

MIT License - see LICENSE for details.

Support

Built with love by the Copus team.

Available Tools

2 tools
get_curationA

Get detailed information about a specific Copus curation including:

  • The curator's personal recommendation note explaining why this content is valuable

  • Curator credentials (why they're qualified to recommend this)

  • Key takeaways and summary

  • Target audience

  • What problem this content solves

  • Original source URL

  • Engagement metrics (views, saves, comments)

Use this after search_curations to get full details about a specific result.

ParametersJSON Schema
NameRequiredDescriptionDefault
idYesCuration ID (UUID from search results)

TDQS

A3.9/5.0
Behavior3/5

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

Description implies read-only behavior but does not disclose auth needs, error handling, or rate limits. With no annotations, the description carries the burden and is adequate but not rich.

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

Conciseness4/5

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

Description is efficient, using a bulleted list within a sentence. Front-loaded and clear, though slightly verbose in listing fields.

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?

Despite no output schema, description enumerates return fields comprehensively. For a simple get tool with one param, it's complete enough for an agent to understand results.

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?

Single parameter 'id' with 100% schema coverage. Description adds minimal extra meaning beyond schema (e.g., origin from search results), so baseline 3 applies.

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?

Description clearly states it retrieves detailed info for a specific curation, listing included fields. Distinguishes from sibling search_curations by specifying post-search usage.

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?

Explicitly says 'Use this after search_curations to get full details about a specific result,' providing clear context. Does not list exclusions but is sufficient for a simple retrieval tool.

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

search_curationsA

Search human-curated content recommendations on Copus. Unlike regular search engines, these are recommendations from real people who explain why the content is valuable. Great for finding trusted tools, articles, and resources vetted by domain experts.

Examples:

  • "python learning resources" - Find recommended Python tutorials and courses

  • "wireframing tools" - Discover designer-recommended wireframing software

  • "creative writing" - Get curated articles and resources on writing

  • "AI tools" - Find AI tools recommended by practitioners

  • "productivity apps" - Discover productivity tools people actually use

ParametersJSON Schema
NameRequiredDescriptionDefault
limitNoMaximum number of results to return (default: 10, max: 50)
queryYesSearch keywords (e.g., 'python tutorials', 'design tools', 'AI resources')

TDQS

A4.2/5.0
Behavior3/5

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

With no annotations, the description covers the read-only search behavior and the nature of results (human-curated with explanations). However, it lacks details on pagination, rate limits, or what happens with empty queries.

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 concise, front-loaded with purpose, and uses a clear structure of definition, differentiation, and examples. Every sentence adds value.

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 no output schema and no annotations, the description provides sufficient context for a search tool. It covers purpose, usage guidance, and examples. Minor omissions like pagination limits completeness slightly.

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 baseline is 3. The description adds value through concrete query examples that illustrate usage, which goes beyond the schema's basic parameter descriptions.

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 searches human-curated content recommendations, differentiating it from regular search engines. It uses specific verbs and resources, and the distinction from sibling tool 'get_curation' is implicit.

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 clear context by contrasting with regular searches and giving multiple examples. However, it does not explicitly state when not to use the tool or mention the sibling as an alternative for single curations.

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. Dates show when Glama detected each change.

  1. 2 tool updatesv1.0.1
    • First observedget_curation
    • First observedsearch_curations
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4/5.0
Disambiguation5/5

The two tools have clearly distinct roles: search_curations finds content, get_curation retrieves details. There is no ambiguity between them.

Naming Consistency5/5

Both tool names follow the verb_noun pattern using snake_case: search_curations and get_curation. The pattern is consistent and predictable.

Tool Count3/5

With only 2 tools, the server is very lean. While it covers search and detail retrieval for curations, the minimal set may feel insufficient for more complex workflows, though it is appropriate for a simple read-only API.

Completeness3/5

The server covers the essential operations for browsing curations (search and get details), but lacks filtering, sorting, or any curation management tools. It fulfills its basic purpose but has notable gaps if more functionality is expected.

Maintenance

ActivityInactive
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/copus-io/copus-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server