Serper Live
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SERPER_LIVE_TOKEN | Yes | API token from https://serper.live/account/tokens. Required for searches; without it `list_countries` still works. | |
| SERPER_LIVE_API_URL | No | API base URL, default `https://api.serper.live` | https://api.serper.live |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| google_searchA | Run a live Google search for a country, language and device and return the organic results in Google's order: position, title, URL, domain and snippet. Ads, sitelinks, video and image blocks are left out, so position is the organic rank. Every call is a real, uncached search that usually takes 2–3 seconds and is billed to the Serper.live balance per page of up to 10 results (https://serper.live/pricing). Use it to see the whole result list; to check where one site ranks, use domain_position instead. |
| domain_positionA | Find where a domain ranks in Google's organic results for a keyword, in a country and on a device, right now. Prefer it over google_search when only one site matters: it returns that site's best position and every other position, or a note that the site is outside the checked depth. A subdomain counts as the domain: example.com also matches blog.example.com. Billed like google_search, per started 10 results of depth (https://serper.live/pricing). |
| list_countriesA | List the countries Serper.live can search right now, with the default Google interface language of each. Call it when unsure whether a market is open, then pass a returned code as country to google_search or domain_position. Desktop and mobile are available in every market. Free, no token needed. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
The three tools target clearly distinct jobs: full result-list search (google_search), single-site rank lookup (domain_position), and market discovery (list_countries). The descriptions explicitly cross-reference each other, telling the agent when to prefer domain_position over google_search. No meaningful ambiguity remains.
All names are snake_case and readable, but the internal pattern is mixed: list_countries is verb_noun, domain_position is noun_noun, and google_search is noun_verb. The convention isn't strictly uniform, though it stays predictable enough that an agent won't be confused.
Three tools is on the lean side, but each covers a genuinely distinct capability (search, rank check, market enumeration) for a focused search API. Nothing feels redundant or missing for the stated scope.
The surface covers the core lifecycle: discover available markets, run a search, and check a specific domain's rank. There are minor gaps (e.g. no explicit pagination control or separate news/image search modes), but these are deliberate exclusions and agents can work around them.