Context7
Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.
Description from the maker (original English)
Knowledge graph CLI for managing features, ADRs, and test criteria as MCP-discoverable artifacts.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Download the maker’s .mcpb file
The link goes to the maker’s own file; we do not host or repackage it. Open the file and Claude Desktop installs it.
Run this in your terminal
Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 6, 2026
The registry name was verified with the GitHub account Hafeok, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (0.2.0) reached the registry 4 months ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need MCPB on your computer.
In the same category: Context7, Codebase Memory, Exa
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
A machine-checkable statement of what a product does, with an executable oracle for its behaviour, exported as one graph that someone else can sign. product-cli is being rewritten as one Native AOT .NET binary that authors that statement — the What of a product, in the sdlc: vocabulary — as a graph with shapes, never prose with diagrams. Anything that cannot be stated as a node, an edge or a shape is not yet specified, and the tool says so rather than accepting it.
The What is authored in conversation: an agent proposes, the author watches the graph, its findings and its open questions change live, and adopts or rejects each proposal, so every element traces to the person who adopted it. Behaviour is executable before any code exists — Deciders and Projectors are simulated against scenarios drawn from the flows, and the same scenarios later judge realised code through a wire protocol. The tool puts nothing in force and decides nothing about realisation: it produces a canonical document, and what that document is held against, and who accepts it, belong to Writ.
The product is defined in decision-driven-design: applications/sdlc/product-cli/product-definition.md. This repository holds the tool, its ADRs (docs/decisions/) and its tests. Agents start at AGENTS.md.
The Rust workspace is frozen at the tag rust-final (commit 70395df), where all of it stays readable under the MIT licence it was published with. No Rust release follows it. Its published releases, up to v0.7.0, keep working.
Apache-2.0 (LICENSE, NOTICE). Developed with AI assistance under human review.