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Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.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-time Google search (AI Overview, answer box, People also ask) and Google Maps places.
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.
X-API-KeyValues marked secret are keys to your account. Never share them or paste them into a chat.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
This address needs a key in a request header, which the add-connector menu cannot set. Use Claude Code, Cursor or VS Code instead.
Run this in your terminal
claude mcp add --transport http google-search https://api.serpgrab.com/mcp --header 'X-API-Key: your-value'Fill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"google-search": {
"url": "https://api.serpgrab.com/mcp",
"headers": {
"X-API-Key": "your-value"
}
}
}
}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": {
"google-search": {
"type": "http",
"url": "https://api.serpgrab.com/mcp",
"headers": {
"X-API-Key": "your-value"
}
}
}
}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 address needs a key in a request header, which the add-connector menu cannot set. Use Claude Code, Cursor or VS Code instead.
Your choice stays on this device in a cookie; no account needed.
X-API-Key secret required HTTP headerThese 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 7, 2026
The registry name was verified against the domain serpgrab.com (the registry checks domain ownership)
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.
You need to fill in: X-API-Key
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 (0.1.2) reached the registry 13 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.
A hosted MCP server that gives AI agents real-time Google search and Google Maps results, from serpgrab. There is nothing to install: add one URL to your MCP client.
https://api.serpgrab.com/mcp
This repository holds the setup docs and client config examples. The server itself runs on our infrastructure and is not open source. It is listed in the official MCP registry as com.serpgrab/google-search.
place_id.Results come back as compact text written for a model's context, not raw JSON.
google_search| Argument | Default | |
|---|---|---|
query | (required) | The search, as typed into Google |
pages | 1 | Result pages to read, 1-3 (about 10 results each) |
country | us | Two-letter country Google searches from (gl) |
language | en | Interface language (hl) |
location | Search as if from a place, e.g. Austin, Texas, United States | |
time | hour, day, week, month or year: only recent results |
google_maps_search| Argument | Default | |
|---|---|---|
query | (required) | What to look for, e.g. pizza in austin tx |
ll | Map position, @latitude,longitude,zoomz, e.g. @30.2672,-97.7431,14z | |
page | 1 | Results page, 20 places each |
country | us | Two-letter country (gl) |
language | en | Interface language (hl) |
Free: 250 searches a month, email signup, no card: https://serpgrab.com/#signup
Connecting and listing the tools work without a key; running a tool needs one. Each results page the agent reads is one search.
Replace YOUR_KEY with your serpgrab key.
claude mcp add --transport http serpgrab https://api.serpgrab.com/mcp \
--header "X-API-Key: YOUR_KEY"
In ~/.cursor/mcp.json, or .cursor/mcp.json in a project:
{
"mcpServers": { "serpgrab": { "url": "https://api.serpgrab.com/mcp", "headers": { "X-API-Key": "YOUR_KEY" } } } }
In .vscode/mcp.json, or run MCP: Open User Configuration:
{
"servers": { "serpgrab": { "type": "http", "url": "https://api.serpgrab.com/mcp", "headers": { "X-API-Key": "YOUR_KEY" } } } }
In Cascade's MCP menu, choose Open MCP config file and add:
{
"mcpServers": { "serpgrab": { "serverUrl": "https://api.serpgrab.com/mcp", "headers": { "X-API-Key": "YOUR_KEY" } } } }
In ~/.codex/config.toml:
[mcp_servers.serpgrab]
url = "https://api.serpgrab.com/mcp" http_headers = { "X-API-Key" = "YOUR_KEY" }
Put the key in the URL and choose no authentication:
https://api.serpgrab.com/mcp?api_key=YOUR_KEY
We don't log keys sent in the URL, but the client stores the URL with its settings, so keep it as private as the key.
Connect through mcp-remote:
{
"mcpServers": { "serpgrab": { "command": "npx", "args": ["-y", "mcp-remote", "https://api.serpgrab.com/mcp", "--header", "X-API-Key:YOUR_KEY"] } } }
Pro is $15 a month for 5,000 searches, on RapidAPI. Subscribers connect through RapidAPI's gateway with their RapidAPI key:
claude mcp add --transport http serpgrab https://google-serp-search-results-json.p.rapidapi.com/mcp \
--header "X-RapidAPI-Key: YOUR_RAPIDAPI_KEY" \ --header "X-RapidAPI-Host: google-serp-search-results-json.p.rapidapi.com"
RapidAPI counts every request to the server, so connecting uses about three of your plan's requests, and each tool call one more.
Streamable HTTP, stateless, with JSON replies (no SSE stream). Only POST is used.
serpgrab returns Google results in SerpApi's JSON format, so the same key also works for your own code: see the migration guide and the OpenAPI spec.
Setup page: https://serpgrab.com/mcp. Questions or a tool you'd like: hello@serpgrab.com.
The docs and examples in this repository are MIT licensed.