agentmods.dev

seven-dpt-mcp

seven-dpt-mcp is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from pierreb4/seven-dpt-mcp. Its token cost is not measured, scanned A, original, Apache-2.0.

An MCP server based on Feynman's twelve-problems method, a way to learn by breaking ideas into questions and working through them. It stores dormant problems and supports an evoke loop for generating new approaches.

In plain words
What is it for?
Use it to manage the method's problem list and evoke new tricks during problem-solving. It runs locally and needs the `SEVEN_DPT_DB` environment variable.
Why use it?
It gives an agent a structured place to retain problems and revisit them when looking for useful ideas or techniques.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

Written for no agent in particular: it speaks MCP, so any client can run it.

not rated 0repo 3d ago A scan tokens not measured original Apache-2.0

Good fit Use it to manage the method's problem list and evoke new tricks during problem-solving. It runs locally and needs the SEVEN_DPT_DB environment variable.

Compare 6 mcp servers from other repositories ↓
Install with agentmods
npx agentmods add mcp/pierreb4/seven-dpt-mcp/seven-dpt-mcp
View source ↗ pierreb4/seven-dpt-mcp
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/pierreb4/seven-dpt-mcp

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for seven-dpt-mcp

README.md
[![agentmods](https://agentmods.dev/badge/mcp/pierreb4/seven-dpt-mcp/seven-dpt-mcp/github.svg)](https://agentmods.dev/mcp/pierreb4/seven-dpt-mcp/seven-dpt-mcp)
Your own site
<a href="https://agentmods.dev/mcp/pierreb4/seven-dpt-mcp/seven-dpt-mcp"><img src="https://agentmods.dev/badge/mcp/pierreb4/seven-dpt-mcp/seven-dpt-mcp/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for seven-dpt-mcp

Your own site · 80×15
<a href="https://agentmods.dev/mcp/pierreb4/seven-dpt-mcp/seven-dpt-mcp"><img src="https://agentmods.dev/badge/mcp/pierreb4/seven-dpt-mcp/seven-dpt-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

seven-dpt-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

server.json · 12 lines

What it actually says

{
  "seven-dpt-mcp": {
    "command": "npx",
    "args": [
      "-y",
      "seven-dpt-mcp"
    ],
    "env": {
      "SEVEN_DPT_DB": ""
    }
  }
}
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 12 lines scan A dc125c1ec8c2

Subscribe to this mod's changes

seven-dpt-mcp is an MCP server published in the GitHub repository pierreb4/seven-dpt-mcp (0 stars, last pushed 3d ago), licensed Apache-2.0. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Learning and teaching
Related

Other mcp servers, from other repositories

flashcards

Read and write open-source flashcards through split read/write MCP tools. Remote server at mcp.flashcards-open-source-app.com.

kirill-markin/flashcards-open-source-app · not measured

canvas-student-mcp

MCP server for Canvas LMS that works even when your school disables API tokens — session-cookie auth, read-only by design. 30 tools for Claude and any MCP client. Runs locally from the canvas-student-mcp npm package.

xmike04/canvas-student-mcp · not measured

korean-special-education-curriculum-mcp

MCP server "korean-special-education-curriculum-mcp" as configured in sonbyobyo/korean-special-education-curriculum-mcp. Runs locally from the korean-special-education-curriculum-mcp npm package.

sonbyobyo/korean-special-education-curriculum-mcp · not measured

sefaria

Sefaria MCP — the free digital library of Jewish texts. Remote server at gateway.pipeworx.io.

pipeworx-io/mcp-sefaria · not measured

college-roi-mcp

U.S. college ROI data: 30-yr NPV for 500 colleges, lifetime ROI for 134 majors. Keyless. Runs locally from the college-roi-mcp npm package.

thomasthinks/college-roi-mcp · not measured

context7

Context7's hosted MCP server: up-to-date library documentation and code examples on demand. Remote server at mcp.context7.com.

trianglegrrl/promptonomicon · not measured