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Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.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)
Search, read, and ask the Nyuchi docs (docs.nyuchi.com); send feedback or raise issues.
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.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Works in Claude on the web, desktop and mobile:
https://docs.nyuchi.com/mcpOpen Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"nyuchi-docs": {
"command": "npx",
"args": [
"-y",
"nyuchi-docs-mcp"
]
}
}
}Run this in your terminal
claude mcp add --transport http nyuchi-docs https://docs.nyuchi.com/mcpclaude mcp add nyuchi-docs -- npx -y nyuchi-docs-mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"nyuchi-docs": {
"url": "https://docs.nyuchi.com/mcp"
}
}
}Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"nyuchi-docs": {
"command": "npx",
"args": [
"-y",
"nyuchi-docs-mcp"
]
}
}
}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.
Paste into .vscode/mcp.json in your project
{
"servers": {
"nyuchi-docs": {
"type": "http",
"url": "https://docs.nyuchi.com/mcp"
}
}
}Paste into .vscode/mcp.json in your project
{
"servers": {
"nyuchi-docs": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"nyuchi-docs-mcp"
]
}
}
}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.
ChatGPT connects only to servers on the internet:
https://docs.nyuchi.com/mcpMenu names can differ slightly by plan and over time.
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.
We have not read this server’s tool list yet; we check endpoints in rotation.
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 nyuchi, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Not checked yet; we check endpoints in rotation
Not checked yet; we check endpoints in rotation
Not checked yet; we read the tool list when we check the endpoint
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.
Either way works: install it on your computer or connect to the cloud version.
The GitHub repo last changed –, and the latest version (0.1.0) reached the registry 4 months ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
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.
Nyuchi engineering documentation — how things are done at Nyuchi, and how
to use the Mzizi tools from a Nyuchi project.
Live: docs.nyuchi.com | Product docs: docs.bundu.org | MCP: docs.nyuchi.com/mcp
A pnpm workspace of six packages.
| Package | Path | What it does |
|---|---|---|
site | site/ | The Astro + Starlight docs site itself. Ships as a Cloudflare Worker with Static Assets. |
@nyuchi/nyuchi-docs-search | nyuchi-docs-search/ | cmdk-style search modal + Ask-AI tab for Starlight sites. Not yet published to npm. |
shamwari-docs-ai | shamwari-docs-ai/ | Cloudflare Worker — the Ask-AI chat proxy (SSE). |
nyuchi-docs-mcp-worker | nyuchi-docs-mcp-worker/ | Cloudflare Worker nyuchi-docs-mcp — the docs MCP server at docs.nyuchi.com/mcp. |
@nyuchi/nyuchi-docs-mcp | nyuchi-docs-mcp/ | The stdio bridge to that hosted endpoint, for clients that cannot speak Streamable HTTP. |
@nyuchi/nyuchi-docs-skills | nyuchi-docs-skills/ | The public agent skill for docs.nyuchi.com. The repo's authoring skills are internal and deliberately not shipped. |
bundu-labs/bundu-docs covers the Bundu Foundation's outward-facing projects — the Mzizi product, the Ubuntu doctrine, and the Bundu brand system. It is an internal-visibility repository, so that link resolves only for org members. It consumes @nyuchi/nyuchi-docs-search and points at the nyuchi-docs-mcp worker.
@nyuchi/nyuchi-docs-searchis not on npm —registry.npmjs.org
returns
{"error":"Not found"}for it (checked 2026-09-12). Until it is
published,
bundu-docscannot install it from the registry.
site/src/content/docs/)/v1 gateway, WorkOS authentication, console-managed API keys, security, and the product namespaces.accounts.mukoko.com (the AuthKit issuer), SSO, JWTs.platform.nyuchi.com.mzizi-mcp, mzizi-cli, mzizi-skills, the DNA double-helix architecture, registry health, and the A2A design.pnpm install
pnpm dev # site only pnpm -r build # all packages pnpm -r test # all packages
Site dev server: http://localhost:4321. Content lives in site/src/content/docs/; the sidebar is configured in site/astro.config.mjs.
The search modal opens with ⌘K / Ctrl+K. The Ask AI tab streams answers from shamwari-docs-ai (Cloudflare Worker) with retrieval-grounded citations. To enable it locally, copy site/.env.example to site/.env:
cp site/.env.example site/.env
Both workers in this repo deploy via Cloudflare Workers Builds — the Cloudflare GitHub App is connected to nyuchi/nyuchi-docs with one trigger per worker (root directory points at the worker package). No GitHub Actions deploy workflow, no CLOUDFLARE_API_TOKEN repo secret.
site/, ships as a Cloudflare Worker with Workers Static Assets. Live at https://nyuchi-docs.nyuchi.workers.dev, and the cutover is done: docs.nyuchi.com now serves this Worker. Both hosts return the same Astro 7.2.9 / Starlight 0.41.10 page (checked 2026-09-12); there is no Mintlify-on-Vercel deployment behind the apex any more.shamwari-docs-ai/, thin proxy in front of Cloudflare AI Search. Live at https://shamwari-docs-ai.nyuchi.workers.dev, which serves exactly two routes: GET /health and POST /chat. Its root returns 404, correctly. See shamwari-docs-ai/README.md for the per-corpus AI Search instance setup (managed via REST API).nyuchi-docs-mcp-worker/, the docs MCP server. Live at https://nyuchi-docs-mcp.nyuchi.workers.dev and routed from docs.nyuchi.com/mcp*. Needs its own Workers Builds trigger (root directory nyuchi-docs-mcp-worker/).docs.nyuchi.com serves these outside the docs tree. Most are static files in site/public/; security.txt is generated per request by the site worker.
| Path | Served from | What it is |
|---|---|---|
/robots.txt | site/public/robots.txt | Crawl policy + sitemap pointer. Everything here is meant to be indexed. |
/llms.txt | site/public/llms.txt | Machine-readable site index for LLMs. |
/AUTH.md | site/public/AUTH.md | Agent-facing WorkOS auth reference, synced from nyuchi/api-gateway. |
/.well-known/mcp/server-card.json | site/public/.well-known/mcp/ | MCP server card for the nyuchi-docs-mcp worker at /mcp. |
/.well-known/security.txt | site/src/worker/security-txt.ts | RFC 9116 disclosure contact — generated per request, not a static file. |
security.txt is dynamic because RFC 9116 makes Expires mandatory and caps it under one year, so a checked-in file silently becomes non-compliant as it ages. site/wrangler.toml sets run_worker_first = true, so every request already passes through site/src/worker/gate.ts; it answers this path before the gate check and before the asset router, deriving Expires from the request time (180 days out). Same approach as mukoko-dev/mukoko-events (formerly nhimbe) and mukoko-dev/kweli.
The search package (nyuchi-docs-search) is consumed by both nyuchi-docs (this repo, via workspace:*) and bundu-docs (separate repo, via the npm registry). Keeping it in the same workspace as the docs site means local changes to the search UI are picked up instantly during pnpm dev, while the published package is a single pnpm publish away.
| Command | Description |
|---|---|
pnpm dev | The docs site on :4321 |
pnpm build | Build the site |
pnpm build:all | Build every workspace package |
pnpm test | Every package's tests |
pnpm lint | Every package's linter |
pnpm check | Every package's type/content check |
pnpm skills:validate | Validate the shipped agent skills |
pnpm deploy:worker | Deploy shamwari-docs-ai |
pnpm deploy:mcp | Deploy nyuchi-docs-mcp-worker |
pnpm ingest | Re-ingest the corpus into Cloudflare AI Search |
Never run
prettier --writeon an.mdxfile. Prettier 3.9.x rewrites
{/* … */}to{/_ … _/}and produces invalid MDX..mdis safe.
/v1 gateway these docs describeReleases follow the org versioning policy (nyuchi/.github#80). The branch decides the bump, and there are no version labels:
staging-version.yml.version in nyuchi-docs-mcp/package.json to it. CI refuses any other version and names the right one.bump: major.Versions released before 2026-10-04 are not renumbered.
This repository is public but carries no LICENSE file, so no licence is granted over it as a whole: all rights reserved. © Nyuchi Africa (PVT) Ltd. The @nyuchi/nyuchi-docs-search package declares MIT in its own package.json; if that is the intent for the package, the repository needs a LICENSE to back it.