MCP.Market

Seven Dpt MCP server

by pierreb4·io.github.pierreb4/seven-dpt-mcp·v0.1.5

Feynman's twelve-problems method as an MCP server: dormant problems + an evoke loop for new tricks.

A92/100grade A
What users say
No reviews yet
Be the first
Safety scan
A92/100

full report

Adoption
Growing

0 stars34 downloads/wk

Reviews

Write one

Nobody has reviewed Seven Dpt yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Seven Dpt tools (8, 2 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • add_problem

    Add a long-running problem to your global Feynman set — the ~dozen you keep dormant in mind across every project. Keep the active set small; that constraint is the method.

  • capture_spark

    Persist a candidate solution plus a concrete next step against a problem — the output of a successful evocation. This is the memory that lets long-running issues progress across sessions.

  • evoke

    The core loop. Give it a trick, result, idea, or observation you just encountered. Returns your open problems plus a scaffold that walks you through evocation -> transcendence -> approach. Call this whenever you learn something that might generalize.

  • get_problem

    Show one problem plus every spark (idea + next step + outcome) captured against it — the long-running memory that makes a stuck issue accumulate progress across sessions.

  • list_problems

    Show your global set of long-running problems. Defaults to open ones only.

  • update_problemwrite action

    Edit a problem or move it out of the active set — the retire/solve/merge loop that keeps the set near twelve. When closing (status solved/retired), write a resolution saying WHY plus, for a retirement, the explicit RE-OPEN trigger: a retired problem is parked with a wake condition, not deleted. A merge is a retirement whose resolution names the absorbing problem. Reopen later by setting status bac

  • update_sparkwrite action

    Record what happened when you acted on a spark — an outcome note, a new status (tried / worked / failed), and ideally the cost (effort spent) and value (graded payoff). LOG FAILURES TOO: 'most bets fail' is the premise of problem #2, so failed and zero-value outcomes are exactly the signal a spend-policy is learned from — recording only wins makes the history unusable. This outcome history is what

  • wake_status

    Evaluate every parked problem/spark's wakeCondition right now: ripeness, progress, and current/target echoes per atom. Read-only. The ambient digest shows the compact version at session start; this is the full view for curation passes.

Public scan report

scanner v0.1.9 · 2026-09-24 · same rubric, same numbers if you re-run it

no findings
  • Code scan3 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 1 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Seven Dpt compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
92/100
higher than 95% of 48,255 servers
Tools
8
the typical server has 7
Tools that change things
25%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
34
more than 23% of 12,191 servers with a package

What its tools let an agent do: 5 read · 1 create · 2 change

Install Seven Dpt in Claude Code, Cursor or VS Code

Runs npx -y seven-dpt-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add seven-dpt-mcp -- npx -y seven-dpt-mcp
Add to Cursor

What the publisher says

From the Seven Dpt repository's README, as published. We do not edit it. Read it on GitHub

seven-dpt-mcp

A tiny, local MCP server that gives Claude (in any project) a persistent set of long-running problems and a loop for cracking them — Feynman's twelve favorite problems method, driven by the tripartite model of inspiration.

every time you meet a new trick, test it against all of them.

  • Feynman's method (via Gian-Carlo Rota): keep ~a dozen problems dormant in mind;

a stimulus evokes a possibility, you transcend the problem's current framing, then you're motivated to act on it.

  • Inspiration = evocation + transcendence + approach motivation (Thrash & Elliot):

The server holds state and scaffolding; the connected model does the thinking — no LLM runs inside the server, no API key.

Tools

Storage: ~/.local/share/seven-dpt/store.json (override with SEVENDPTDB). One store, shared by every project = one brain.

Wake conditions (0.1.4)

Retiring a problem parks it with a re-open trigger — but a trigger written in prose is a wait owned by "someone will remember." A wakeCondition makes it computable: a small predicate (all/any over atoms like sparkCount, a date gate, fileMatches / fileLines / fileCount on a path, or an explicit manual note) attached when you retire/solve a problem (updateproblem), park a spark (updatespark), or capture one born gated (capture_spark). The ambient digest evaluates every condition at session start and surfaces what's ripe (with an act/re-park pointer), what's ripening (with current/target progress), and — loudly — any condition whose source became unreadable: a wake source that vanished must scream, not sit at 0% forever. Everything echoes its aim (prior-ledger.jsonl 12/20), so a wrong path or unit is visible when you arm it, not months later. No auto-reopen: ripeness is surfaced, you decide. --wake prints the full ledger from the CLI.

Claim typing (0.1.5)

A parked spark with a wake condition can revive — but nothing says when it may die, so an unfalsifiable hope can ride the digest forever. 0.1.5 gives every spark an optional claim-typing trio, all write-once on the same anti-hindsight model as prior:

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Seven Dpt: common questions

Is Seven Dpt MCP server safe?
Yes, by our scan: it is graded A (92/100). Read the Seven Dpt safety report
How do I install Seven Dpt?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Seven Dpt need an API key?
No secret keys are declared. It reads 1 setting from the environment.
Is Seven Dpt maintained?
The last commit was 42 days ago (2026-09-23). The latest release is v0.1.5.
How does Seven Dpt compare with other MCP servers?
safety score 92/100 (higher than 95% of 48,255 servers); tools 8 (the typical server has 7); tools that change things 25% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.