Koskamo

Hypnotic Patterns MCP

An MCP server that allows AI assistants to teach Python programming using the Hypnotic Patterns educational content. It provides tools to list patterns, access learning paths, retrieve lessons with exercises and quizzes, get code scripts, check answers, and explain concepts, facilitating a guided learning experience without running user code.

Visit doner.cloud

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Hypnotic Patterns MCP logo, by doner.cloudVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-07Operated by doner.cloud
MCP endpoint (Streamable HTTP)
https://hypnoticpatterns.doner.cloud/mcp
Vendor documentation

What its tools do

6 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Read-only (6)

6 of 6 have a description · 6 of 6 declare behavior hints · 6 of 6 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Passed Official MCP Registry namespace is tied to doner.cloud ·
  • Passed Endpoint is on the registry namespace domain ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Teach Python lessons based on math animations
  • Check quiz answers and provide hints
  • Retrieve code scripts and Colab notebooks
  • Explain programming concepts like recursion

Source and maintenance

Vendor evidenceRegistry 1.0.0
mcp-registry: cloud.doner/hypnotic-patterns@1.0.0Project website

Protocol and capabilities

Server
hypnotic-patterns 1.0.0
MCP protocol negotiated in check
2025-11-25
Tools
6 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
1 advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": false
  },
  "prompts": {
    "listChanged": false
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

Hypnotic Patterns teaches Python with glowing math animations: each lesson builds one pattern (the golden angle of a sunflower, the Galton board, the chaos game, Turing patterns, three-body orbits…) in a short numpy and matplotlib script, line by line. Good when someone wants to learn or teach Python, numpy or matplotlib through a small visual project, or asks about the math of one of these patterns. learning_path gives the course in order, get_lesson a lesson step by step (exercises and quiz without their answers), get_code the script, check_answer checks a quiz answer or gives an exercise’s hint and reference answer, explain_concept finds an idea in the lessons. Every answer links the lesson and its video; English or Polish (lang "pl"), the patterns and lessons also in Spanish, Portuguese, French and German. The prompt "tutor" teaches one lesson the way the site does: a question first, then a hint, the code last.

Tools

6 advertised

list_patterns — List the patterns
Advertised by the server during the last successful anonymous check.
Advertised read-only

The patterns of the channel: each one simple rule (the golden angle, the Galton board, Turing patterns…), its category, whether it has a Python lesson and at what level, with links to its page and newest video.

list_patterns input schema
{
  "type": "object",
  "properties": {
    "lang": {
      "enum": [
        "en",
        "pl",
        "es",
        "pt",
        "fr",
        "de",
        "ja",
        "ko"
      ],
      "type": "string",
      "description": "The language of the answer: en (the default), pl; es, pt, fr, de, ja and ko for patterns and lessons (the course stays in English there)"
    }
  },
  "additionalProperties": false
}
list_patterns annotations
{
  "readOnlyHint": true,
  "openWorldHint": false
}
learning_path — The Python course, in order
Advertised by the server during the last successful anonymous check.
Advertised read-only

The free Python course in its order: each lesson builds one pattern in a short numpy/matplotlib script, from arrays and loops (Beginner) to randomness and recursion (Intermediate) to simulations and grids (Advanced). Each lesson with what it teaches and its link. Optionally only one level.

learning_path input schema
{
  "type": "object",
  "properties": {
    "lang": {
      "enum": [
        "en",
        "pl",
        "es",
        "pt",
        "fr",
        "de",
        "ja",
        "ko"
      ],
      "type": "string",
      "description": "The language of the answer: en (the default), pl; es, pt, fr, de, ja and ko for patterns and lessons (the course stays in English there)"
    },
    "level": {
      "enum": [
        "Beginner",
        "Intermediate",
        "Advanced"
      ],
      "type": "string",
      "description": "Only the lessons of this level"
    }
  },
  "additionalProperties": false
}
learning_path annotations
{
  "readOnlyHint": true,
  "openWorldHint": false
}
get_lesson — A lesson, step by step
Advertised by the server during the last successful anonymous check.
Advertised read-only

One lesson of the course: the question the pattern asks, why it works at three depths, the formula, its script line by line with explanations, exercises with hints, a quiz and flashcards. Exercise answers and quiz keys are left out on purpose: use check_answer once the learner has tried.

get_lesson input schema
{
  "type": "object",
  "required": [
    "pattern"
  ],
  "properties": {
    "lang": {
      "enum": [
        "en",
        "pl",
        "es",
        "pt",
        "fr",
        "de",
        "ja",
        "ko"
      ],
      "type": "string",
      "description": "The language of the answer: en (the default), pl; es, pt, fr, de, ja and ko for patterns and lessons (the course stays in English there)"
    },
    "pattern": {
      "enum": [
        "golden-angle",
        "galton-board",
        "times-table",
        "chaos-game",
        "pendulum-wave",
        "turing-patterns",
        "sorting-race",
        "three-body-orbits",
        "spinning-ring"
      ],
      "type": "string",
      "description": "The pattern (its slug), as list_patterns gives it"
    }
  },
  "additionalProperties": false
}
get_lesson annotations
{
  "readOnlyHint": true,
  "openWorldHint": false
}
get_code — The Python script of a pattern
Advertised by the server during the last successful anonymous check.
Advertised read-only

The whole Python script of a pattern (numpy and matplotlib, under 80 lines), as the lesson and the site show it and as the site’s tests run it, with how to run it, what to change to see something new, and a Google Colab notebook to run it in a browser.

get_code input schema
{
  "type": "object",
  "required": [
    "pattern"
  ],
  "properties": {
    "lang": {
      "enum": [
        "en",
        "pl",
        "es",
        "pt",
        "fr",
        "de",
        "ja",
        "ko"
      ],
      "type": "string",
      "description": "The language of the answer: en (the default), pl; es, pt, fr, de, ja and ko for patterns and lessons (the course stays in English there)"
    },
    "pattern": {
      "enum": [
        "golden-angle",
        "galton-board",
        "times-table",
        "chaos-game",
        "pendulum-wave",
        "turing-patterns",
        "sorting-race",
        "three-body-orbits",
        "spinning-ring"
      ],
      "type": "string",
      "description": "The pattern (its slug), as list_patterns gives it"
    }
  },
  "additionalProperties": false
}
get_code annotations
{
  "readOnlyHint": true,
  "openWorldHint": false
}
check_answer — Check an answer
Advertised by the server during the last successful anonymous check.
Advertised read-only

For a quiz question of a lesson: says whether the answer is right, which option is, and why. For an exercise: gives its hint and its reference answer to compare the learner’s attempt with (this server does not grade free text and never runs code); offer the hint first and the reference only after a try.

check_answer input schema
{
  "type": "object",
  "required": [
    "pattern",
    "kind",
    "number"
  ],
  "properties": {
    "kind": {
      "enum": [
        "quiz",
        "exercise"
      ],
      "type": "string",
      "description": "A quiz question or an exercise"
    },
    "lang": {
      "enum": [
        "en",
        "pl",
        "es",
        "pt",
        "fr",
        "de",
        "ja",
        "ko"
      ],
      "type": "string",
      "description": "The language of the answer: en (the default), pl; es, pt, fr, de, ja and ko for patterns and lessons (the course stays in English there)"
    },
    "answer": {
      "type": "string",
      "maxLength": 2000,
      "description": "The learner’s answer: for the quiz the option’s text or its number (1 to 3); for an exercise optional"
    },
    "number": {
      "type": "integer",
      "minimum": 1,
      "description": "Its number in the lesson, from 1"
    },
    "pattern": {
      "enum": [
        "golden-angle",
        "galton-board",
        "times-table",
        "chaos-game",
        "pendulum-wave",
        "turing-patterns",
        "sorting-race",
        "three-body-orbits",
        "spinning-ring"
      ],
      "type": "string",
      "description": "The pattern (its slug), as list_patterns gives it"
    }
  },
  "additionalProperties": false
}
check_answer annotations
{
  "readOnlyHint": true,
  "openWorldHint": false
}
explain_concept — Explain a concept from the lessons
Advertised by the server during the last successful anonymous check.
Advertised read-only

Finds a Python or math idea in the lessons (e.g. "np.roll", "recursion", "golden ratio", "binomial", "leapfrog", "attractor") and gives what the lessons say about it, with the lesson and video that show it.

explain_concept input schema
{
  "type": "object",
  "required": [
    "concept"
  ],
  "properties": {
    "lang": {
      "enum": [
        "en",
        "pl",
        "es",
        "pt",
        "fr",
        "de",
        "ja",
        "ko"
      ],
      "type": "string",
      "description": "The language of the answer: en (the default), pl; es, pt, fr, de, ja and ko for patterns and lessons (the course stays in English there)"
    },
    "concept": {
      "type": "string",
      "maxLength": 120,
      "minLength": 2,
      "description": "The idea to look up"
    }
  },
  "additionalProperties": false
}
explain_concept annotations
{
  "readOnlyHint": true,
  "openWorldHint": false
}

Prompts

1 advertised

tutor — Teach a lesson

Advertised by the server during the last successful anonymous check.

Teach one lesson of the course as the site does: a question to guess first, then the script step by step, hints before answers, the code at the end.

pattern
The pattern to teach (golden-angle if none)
level
The learner: beginner, intermediate or advanced

Resources

Not advertised

No resource definitions available.

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
954 ms
95th percentile latency
954 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 954 ms · metadata changed · 6 tool(s), 1 prompt(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http hypnotic-patterns-mcp https://hypnoticpatterns.doner.cloud/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add hypnotic-patterns-mcp --url https://hypnoticpatterns.doner.cloud/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable hypnotic-patterns-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "hypnotic-patterns-mcp": {
      "url": "https://hypnoticpatterns.doner.cloud/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "hypnotic-patterns-mcp": {
      "type": "streamableHttp",
      "url": "https://hypnoticpatterns.doner.cloud/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start hypnotic-patterns-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "hypnotic-patterns-mcp": {
      "type": "http",
      "url": "https://hypnoticpatterns.doner.cloud/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http hypnotic-patterns-mcp https://hypnoticpatterns.doner.cloud/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://hypnoticpatterns.doner.cloud/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "hypnotic-patterns-mcp": {
      "serverUrl": "https://hypnoticpatterns.doner.cloud/mcp"
    }
  }
}

Let your agent find its tools

Find servers like Hypnotic Patterns MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 8,787

Do you run Hypnotic Patterns MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing