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Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.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)
Real Google results and search volume
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 7, 2026
The registry name was verified with the GitHub account CTF-Max, 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 16 days 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.
Real Google results and search volume for your AI agent (Codex or Claude Code), through your own DataForSEO account, with a daily spend cap. Built by Find Untapped Growth.
Built-in web search gives an agent a handful of results from its own index. This plugin gives it what Google actually shows for a phrase in a place: positions, People Also Ask, the local pack, which sites an AI Overview cites, the featured snippet, and every spot a given domain holds. It also gives Google Ads monthly search volume.
| Tool | What it does | Cost to you (DataForSEO list price, read 2026-10-09) |
|---|---|---|
google_serp | Live Google organic results for one keyword + location + device | $0.002 per 10 results (depth 10 = $0.002); search operators like site: cost 5× |
google_search_volume | Monthly volume, CPC, competition, 12-month trend for 1–100 keywords (1000 with allow_large_batch) | $0.09 per call, any number of keywords |
serp_estimate | Cost reserve for a call and whether today's cap allows it | free |
serp_spend | Spend today / this month, the cap, the last 10 calls, whether credentials are set | free |
Prices: SERP · depth billing · Google Ads volume. The plugin records the cost each response reports, so your ledger reflects what DataForSEO charged, not our estimate.
/plugin install untapped-serp --marketplace CTF-Max/untapped-plugins (or, from a terminal: claude plugin marketplace add CTF-Max/untapped-plugins, then claude plugin install untapped-serp@untapped-plugins).codex plugin marketplace add CTF-Max/untapped-plugins, then codex plugin add untapped-serp@untapped-plugins.python. Standard library only: nothing to pip install./plugin → untapped-serp → configure). They are kept in your computer's secure credential store, not in a settings file.powershell setx DATAFORSEO_LOGIN "you@example.com" setx DATAFORSEO_PASSWORD "your-api-password" (macOS/Linux: export them in your shell profile.)| Setting (Claude Code) / variable | Default | Meaning |
|---|---|---|
Daily spend cap / UNTAPPED_SERP_DAILY_CAP_USD | 1.00 | Paid calls stop once charged + in-flight spend for the UTC day would pass this |
UNTAPPED_SERP_SANDBOX | off | 1 = use DataForSEO's free sandbox (dummy data, labelled sandbox: true) |
UNTAPPED_SERP_HOME | ~/.untapped-plugins/serp (Windows: C:\Users\ \.untapped-plugins\serp) | Where the cache + spend ledger live |
max_age_hours: 0 forces fresh.api.dataforseo.com (or sandbox.dataforseo.com) are ever called; proxies and redirects are refused so your credentials can't be sent anywhere else.dry_run: true or serp_estimate shows the cost without calling.null (no data) for small local phrases; null is never zero.target: "not in top N" means not found in the results fetched, not "not indexed".python -m unittest discover -s untapped-serp/tests # offline, 21 tests
python tools/sync_shared.py --check # shared MCP lib copies are current python tools/serp_smoke.py # free sandbox round trip