1. Conduid
  2. Developer Tools
  3. Scraps
MCP server · Developer Tools

Scraps

by · github.com/boykush/scraps

The Wiki-link doc compiler for the LLM era.

Unclaimed MIT markdownpersonal-knowledge-managementmcpknowledge-managementstatic-site-generatormcp-serverclidevtoolsrust
InstallView source
72Good

Scored 6 hours ago · breakdown

About Scraps

Scraps is an MCP server published by boykush in the Developer Tools category: the Wiki-link doc compiler for the LLM era.

The repository has 45 stars and 6 forks, with the last commit 15 hours ago. Recent commit activity is the strongest signal that reported issues will get attention.

Install

From source
git clone https://github.com/boykush/scraps

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about Scraps

Powered by Claude · Grounded in docs

I know everything about Scraps. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

Static checks derived from the repository 6 hours ago. Heuristics on the source, not an audit.

  • ✓README presentThe repository ships documentation.
  • ✓License declaredUsable under a stated license.
  • ✓Tests presentA test suite exists in the repository.
  • ✓Dependencies pinnedA lockfile pins dependency versions.
  • ✓No dynamic code executionSource scan found no eval, dynamic Function, or shell execution.
  • !Scoped permissionsDoesn't declare a permission scope. Assume it can do anything its process can.

Releases

v3.4.0v3.4.0 · 15 Oct 2026Before upgrading a published site No change is marked breaking, but two affect a deployed site: Page URLs change. Pages are written at their name as written instead of a slug (#823). Every scrap, tag and type page whose name is not…
v3.3.0v3.3.0 · 12 Oct 2026What's Changed ✨ Features feat: add `scraps check` to run the build without writing the site (#810) `scraps check` runs the same pipeline as `scraps build` (config, load, render) and exits non-zero where a build would, but writes no site.…
v3.2.0v3.2.0 · 10 Oct 2026What's Changed ✨ Features feat(plugins): add the pkm plugin with a plugin eval suite (#792) A new `pkm` plugin brings personal knowledge management skills for a Scraps wiki to Claude Code. `/learn` explains a source on the pages the wiki…
v3.1.0v3.1.0 · 3 Oct 2026What's Changed ✨ Features feat(mcp): export a trace span per MCP request over OTLP (#775) `scraps mcp serve` exports one OpenTelemetry span per MCP request once `OTEL_EXPORTER_OTLP_ENDPOINT` or `OTEL_EXPORTER_OTLP_TRACES_ENDPOINT` is set,…
v3.0.1v3.0.1 · 25 Sep 2026What's Changed 📚 Documentation docs: drop the design snapshots under design/v1 and design/v2 (#736) 🔧 Maintenance chore!: retire the scraps-migration plugin and move repo skills to apm (#742) The `scraps-migration` plugin has left both…

README

Scraps treats documentation like a programming language. Wiki-linked markdown becomes a typed source, compiling into a static site for readers and into JSON any agent can shell into — turning Karpathy's LLM Wiki pattern into a typed, queryable artifact. CLI primary with companion AI skills, fitting any editor and any LLM agent.

Quick start

# Install
brew install boykush/tap/scraps    # or: cargo install scraps

# Compile a wiki
mkdir my-wiki && cd my-wiki
scraps init
scraps build

# Query the same source from a shell or AI agent
scraps search "release checklist" --json
scraps links "Configuration" --json
scraps lint

See the Getting Started tutorial for the full flow.

How it works

graph LR
  Source[Markdown sources] --> IR[Scraps IR — typed graph]
  IR --> HTML[Static HTML]
  IR --> JSON[CLI JSON]

Scraps reads [[wiki-link]], #[[tag]], ![[embed]], [[Page#heading]], and ctx_path as typed primitives. The same source compiles to an HTML site for human readers and to JSON for scripts and AI agents. The IR is kept under .scraps/ next to .scraps.toml, so every command reads the wiki through it and an unchanged source is never parsed twice.

AI integration

CLI + JSON is the primary path — any shell-capable agent can query Scraps without an MCP client implementation. Bundled plugins provide agent-facing workflows:

  • llm-wiki — Karpathy-style Ingest / Query / Lint skills for Claude Code and Codex, plus Claude Code agents for purpose-driven lint and the default Scraps LLM Wiki schema
  • pkm — Personal knowledge management skills for Claude Code: learn a source and record only what you understood, or digest an article into a short linked page
  • mcp-server — MCP server for MCP-compatible clients, shared across repositories via scraps mcp serve --http

See the AI integration guide for the trade-offs.

Documentation

Screenshots

Search, pagination, and Wiki-link navigation, themed with Nord.

Each scrap page draws its neighbourhood: backlinks on the left, links on the right, arrows pointing at the referenced scrap.

Contributing

Bugs, feature requests, and PRs are welcome. See CONTRIBUTING.md, the issue templates, and the Code of Conduct.

License

MIT

README fetched from the repository 6 hours ago. The original is authoritative.

Questions

About Scraps

How do I install Scraps?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is Scraps safe to use with an AI agent?

Its trust score is 72 out of 100 (good). It passes 5 of the 6 static security checks run so far; the failures are listed above. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Scraps still maintained?

Yes — the latest release is v3.4.0 (15 Oct 2026), and the last commit was 15 hours ago. The repository has 45 stars and 9 open issues.