Skip to main content
Glama

Bright Data

by io.github.pipeworx-io

Brightdata Serp

brightdata_serp
Read-onlyIdempotent

Run a Google search through the Bright Data SERP API and return parsed organic results (rank, title, link, description) with geo-targeting. Uses the same Bright Data request API with a SERP-type zone — create a SERP API zone in your Bright Data dashboard and pass its name as zone (Web Unlocker zones return raw HTML for Google). BYOK: Bright Data API token via _apiKey; pay-per-request pricing on the Bright Data side. Example: brightdata_serp({ query: "best espresso machine", zone: "serp_api1", country: "us", _apiKey: "your-brightdata-token" })

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
numNoMaximum organic results to return (client-side cap; Google serves ~10 per page — use `start` for deeper pages). Default 10.
zoneNoYour SERP API zone name from the Bright Data control panel (a SERP-type zone is required for parsed Google results). Default "serp_api1" — the typical auto-generated name; check your dashboard for the exact name.
queryYesThe Google search query, e.g. "best espresso machine 2026"
startNoPagination offset: 0 = first page (default), 10 = second page, 20 = third.
_apiKeyYesYour Bright Data API token (account settings or zone Overview tab). Requires a Bright Data account with a SERP API zone; sign up at https://brightdata.com
countryNoTwo-letter country code for localized results (sent as Google's `gl` parameter), e.g. "us", "gb", "jp". Optional.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed1 schema field changed
    • addedInput schema / examples
      Added value: +[
+  {
+    "_apiKey": "your-brightdata-token",
+    "query": "best espresso machine 2026"
+  },
+  {
+    "_apiKey": "your-brightdata-token",
+    "country": "us",
+    "num": 20,
+    "query": "restaurants near me",
+    "start": 10,
+    "zone": "serp_api1"
+  }
+]
  2. First observed

TDQS

A4.2/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate read-only, open-world, idempotent, non-destructive. The description adds that it uses a SERP-type zone and returns parsed results. No contradictions, but minimal extra behavioral disclosure (no rate limits or auth details beyond what's in params).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences plus a practical example. No fluff, front-loaded with purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema, but description mentions return fields (rank, title, link, description). Parameters are well-documented. Could add more on pricing or error handling, but sufficient for agent invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema covers all 6 parameters with descriptions. The description adds an example call and clarifies defaults for zone and start. Slight improvement over schema alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool runs a Google search via Bright Data SERP API and returns parsed organic results with geo-targeting. It distinguishes from brightdata_unlock (raw HTML) and other search tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains when to use (parsed Google results with geo-targeting) and mentions alternatives (Web Unlocker zones for raw HTML). It lacks explicit 'when not to use' but provides enough context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Bright Data toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.8/5.0
Disambiguation2/5

The ask_pipeworx family (ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research) has significant boundary overlap, and ask_pipeworx_beta is explicitly identical to ask_pipeworx today. The six polymarket_* tools plus bet_research also cover heavily overlapping prediction-market territory, so an agent could easily route a query to the wrong one despite detailed descriptions.

Naming Consistency4/5

Most tools follow a consistent snake_case verb_noun pattern (ask_pipeworx, compare_entities, generate_llms_txt, list_subscriptions, validate_claim, scan_dependency). Minor deviations exist — entity_profile is noun-noun, brightdata_serp/brightdata_unlock use a vendor prefix, and remember/recall/forget are bare verbs — but the overall style is predictable and readable.

Tool Count2/5

At 33 tools this exceeds the 25+ threshold that signals an over-heavy surface. While the server covers multiple domains (data lookup, prediction markets, memory, subscriptions, AI visibility), many of those domains carry redundant variants that could be consolidated, making the count feel bloated rather than well-scoped.

Completeness4/5

The surface covers the core workflows well: querying (ask_pipeworx variants), deep research, entity resolution, entity profiles, comparisons, change feeds, claim verification, discovery/onboarding, subscriptions (list/subscribe/unsubscribe), memory (remember/recall/forget), and feedback. Minor gaps exist — there is no direct tool to fetch a returned pipeworx:// citation URI, and memory lacks an explicit update operation — but agents can work around these.

Resources