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Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.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 and compare AI tools for work from a curated, read-only directory.
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://findaiforwork.com/mcpRun this in your terminal
claude mcp add --transport http findaiforwork https://findaiforwork.com/mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"findaiforwork": {
"url": "https://findaiforwork.com/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": {
"findaiforwork": {
"type": "http",
"url": "https://findaiforwork.com/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://findaiforwork.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.
Tool names and descriptions exactly as the server reported them on Nov 7, 2026. The maker wrote them, not us; we show them as plain text.
search_toolsSearch published AI software listings by free text, category slug or pricing model. Returns a total plus compact summaries.
get_toolReturn the full public listing for one tool by slug, including its Markdown copy and related tools.
list_categoriesList every active category with its slug, description and the number of published tools in it.
compare_toolsCompare two to five published tools side by side. Unknown slugs are reported in missing instead of being guessed.
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 8, 2026
The registry name was verified with the GitHub account brand-lc, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Responded in 623 ms (HTTP 200)
No sign-in needed
Read 4 tool descriptions and found no hidden instructions to the AI
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 3 of 3 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 in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed –, and the latest version (1.0.1) reached the registry 10 days 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.
[findaiforwork.com](https://findaiforwork.com) · Find AI tools built for better work.
FindAIforWork is an independent directory of AI software for productive work. Every listing is reviewed before it goes live, organized by the job it helps you do, and written to explain what the product actually does rather than what it claims. The directory is intentionally focused on useful AI software for research, writing, analysis, design, and operations — not a general software catalog.
Curated software for research, writing, analysis, design, and operations.
Eleven focused categories, each organized around a kind of work:
Submit a product at findaiforwork.com/submit. There are three one-time listing plans and no subscriptions:
| Plan | Price | What you get |
|---|---|---|
| Free | $0 | A dofollow listing on the detail page in exchange for a verified FindAIforWork backlink on your product homepage. Published after human review. |
| Basic | $9.90 one-time | A dofollow listing without a homepage backlink. Published once payment is confirmed. |
| Pro | $29.90 one-time | Everything in Basic, plus a Featured badge and section, a featured homepage placement with first-screen priority for 30 days, and a rotating Sponsored sidebar slot while the plan is active. |
The site publishes agent guides and Markdown versions of its public pages:
/tools/{slug}.md and an alternatives page.The reviewed catalog is also available to AI assistants over the Model Context Protocol. The server is public and read-only: no account, no API key, and nothing is written.
| Endpoint | https://findaiforwork.com/mcp |
| Transport | Streamable HTTP, stateless (POST with JSON-RPC; GET returns 405) |
| Authentication | None |
| Registry name | io.github.brand-lc/findaiforwork |
| Tool | What it does | Inputs |
|---|---|---|
search_tools | Search published listings by text, category or pricing model | query?, category?, pricing? (FREE, FREEMIUM, PAID, OPEN_SOURCE, CONTACT_SALES), sort? (latest, trending, az), limit? (1-25, default 10) |
get_tool | One full public listing: Markdown description, secondary categories and five related tools | slug |
list_categories | Every active category with its slug, description and listing count | none |
compare_tools | Two to five listings side by side; unknown slugs come back in missing | slugs (2-5) |
Every result includes the canonical page URL and the product's official website, so an assistant can cite both. query is a plain substring match on name, tagline, description and maker, so short keywords work best. A listing with an active paid Pro plan carries featured: true; the flag never changes the order of results.
Claude Code:
claude mcp add --transport http findaiforwork https://findaiforwork.com/mcp
Cursor (.cursor/mcp.json):
{ "mcpServers": { "findaiforwork": { "url": "https://findaiforwork.com/mcp" } } }
VS Code (.vscode/mcp.json):
{ "servers": { "findaiforwork": { "type": "http", "url": "https://findaiforwork.com/mcp" } } }
Any other client that supports remote MCP servers: add https://findaiforwork.com/mcp as a custom (remote) server. Clients that only speak stdio can use a bridge such as npx -y mcp-remote https://findaiforwork.com/mcp.
search_tools returns at most 25 results per call. The server itself keeps no sessions and never reads cookies. Requests are rate limited per IP address, in memory.
Questions: support@findaiforwork.com
Read more about the directory at findaiforwork.com/about and the editorial approach at findaiforwork.com/methodology.
Questions about a listing, an order, or a review decision: support@findaiforwork.com.