Skip to main content
Glama
Byski

mcp-searchapi

by Byski
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Hybrid

mcp-searchapi

An MCP server for SearchApi.io. Eight search engines exposed as discrete tools, returning trimmed structured results instead of raw SERP payloads.

npx -y mcp-searchapi

Why this exists

Two SearchApi MCP packages were already on npm when this was written. Both are single-version releases from mid-2025 that have not been updated since, neither has a test suite, and one of them targets SearchAPI**.site**, a different product. So this is not a third copy of the same thing:

One tool per engine, not one search tool with a mode flag. A model picks google_jobs correctly far more often than it picks search(engine="google_jobs"). Every parameter carries a description written as guidance, because those descriptions are the prompt the model actually reads.

Trimmed structured output. SearchApi returns results under a different key per engine (organic_results, local_results, shopping_results, videos, jobs), each with a different field set, and the payloads are large. Measured against live responses on 7 August 2026:

Tool

Raw payload

Returned at limit: 10

Saved

google_search

171,668 B

2,507 B

98.5%

google_shopping

117,262 B

4,391 B

96.3%

google_maps

71,607 B

3,172 B

95.6%

youtube_search

56,836 B

3,587 B

93.7%

google_jobs

86,433 B

7,772 B

91.0%

google_news

38,176 B

4,221 B

88.9%

amazon_search

47,732 B

7,718 B

83.8%

google_scholar

19,066 B

5,813 B

69.5%

The percentage matters less than the ceiling: whatever the engine sends back, a page of results stays under 8KB. Handing a model 171KB of ad blocks, favicons and pagination tokens spends its context window on things it will never use.

Every result normalises to a common core (position, title, url, snippet) plus the extras that matter for that engine: price and rating for shopping, coordinates and opening state for maps, company and posting date for jobs, channel and view count for YouTube, citation counts for Scholar.

Related MCP server: evo-scry

Setup

Get a key at searchapi.io. The free tier is 100 searches a month.

Claude Desktop

~/Library/Application Support/Claude/claude_desktop_config.json on macOS, %APPDATA%\Claude\claude_desktop_config.json on Windows:

{
  "mcpServers": {
    "searchapi": {
      "command": "npx",
      "args": ["-y", "mcp-searchapi"],
      "env": { "SEARCHAPI_API_KEY": "your-key" }
    }
  }
}

Cursor

~/.cursor/mcp.json:

{
  "mcpServers": {
    "searchapi": {
      "command": "npx",
      "args": ["-y", "mcp-searchapi"],
      "env": { "SEARCHAPI_API_KEY": "your-key" }
    }
  }
}

VS Code

.vscode/mcp.json:

{
  "servers": {
    "searchapi": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "mcp-searchapi"],
      "env": { "SEARCHAPI_API_KEY": "your-key" }
    }
  }
}

Hosted

SEARCHAPI_API_KEY=your-key npx -y mcp-searchapi --http --port 3000

Serves streamable HTTP at /mcp and a health check at /health. Stateless, so it scales horizontally without sticky sessions.

Tools

Tool

Engine

Use it for

Extra fields

google_search

Google

General questions, fact-checking, finding sources

source, domain

google_news

Google News

Recent events, "what's happening with X"

source, date

google_shopping

Google Shopping

Price comparison, product availability

price, rating, reviews, seller, delivery

google_jobs

Google Jobs

Vacancies, hiring, job market

company, location, postedAt, scheduleType

google_scholar

Google Scholar

Papers, citations, academic sources

publication, authors, citedBy

google_maps

Google Maps

Places, local business, "near me"

address, rating, openState, latitude, longitude

youtube_search

YouTube

Videos, tutorials, talks

channel, views, length, publishedTime

amazon_search

Amazon

Amazon product lookups

asin, price, rating, isSponsored

Parameters

query is required everywhere. limit (default 10, max 50) caps what comes back to the model. The rest are offered only on the engines that accept them:

Parameter

Meaning

Available on

location

Geo-target as City,Country

search, news, shopping, jobs, maps

gl

Two-letter country code

search, news, shopping, maps, youtube, amazon

hl

Two-letter language code

all except amazon

num

Results to request from the engine

search, news, shopping, scholar

page

Page number, from 1

all except youtube

google_jobs deliberately does not offer gl: the API rejects country codes on that engine (gl=ie returns HTTP 400 Unsupported value). Use location instead. Advertising a parameter the API will reject is worse than not having it, because the model has no way to discover the constraint.

Example

google_jobs(query: "backend engineer", location: "Dublin,Ireland", limit: 3)
{
  "engine": "google_jobs",
  "query": "backend engineer",
  "totalResults": 10,
  "results": [
    {
      "position": 1,
      "title": "Backend Engineer",
      "url": "https://...",
      "company": "Example Ltd",
      "location": "Dublin, Ireland",
      "via": "LinkedIn",
      "postedAt": "2 days ago",
      "scheduleType": "Full-time",
      "snippet": "..."
    }
  ]
}

totalResults reports what the engine returned, not what was kept, so the model can tell there is more available behind a higher limit.

Errors

Failures come back as tool errors with something actionable, not a bare status code:

Condition

Message

Missing key

Server exits at startup rather than failing on the first call

401

Names SEARCHAPI_API_KEY and links where to get one

429

Says quota or rate limit, and notes the free tier is 100/month

400

Passes through the API's own message, for example the gl rejection above

Timeout

Reports the elapsed limit; defaults to 30s

No results

Not an error. Returns an empty results array with a notice

Development

npm install
npm test           # 77 tests, no network
npm run typecheck
npm run build

SEARCHAPI_API_KEY=... node scripts/smoke.mjs   # end-to-end, costs 1 search

Tests run against real captured API responses in test/fixtures/, one per engine plus an empty-result case, so they exercise the shapes the API actually returns rather than the shapes it was assumed to return. Nothing in npm test touches the network.

Adding an engine is a data change: append an entry to ENGINES in src/engines.ts with its result key, supported parameters and a normaliser. The server registers tools from that registry.

Licence

MIT

Available Tools

8 tools
google_jobsgoogle_jobsA

Search Google Jobs for job listings with company, location and apply links. Use this for any hiring, vacancy or job market question. This engine does not accept a country code. Pass location (for example 'Dublin,Ireland') to geo-target.

ParametersJSON Schema
NameRequiredDescriptionDefault
hlNoTwo-letter language code for the results, for example 'en', 'fr'.
pageNoPage number for paginating through results. Starts at 1.
limitNoMaximum results to return to you. Kept low by default because search payloads are large; raise it only when you genuinely need more.
queryYesThe job search query, for example 'backend engineer'. Include the place in the query as well as in `location` for best results.
locationNoGeographic location to search from, as 'City,Country' (for example 'Dublin,Ireland'). Results are localised to this place.

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It transparently states a limitation ('does not accept a country code') and explains how to geo-target via the 'location' parameter. This adds meaningful behavior beyond what the schema alone provides, though it doesn't cover every edge like pagination specifics.

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?

The description is three sentences long, each earning its place: the first defines what the tool does, the second specifies when to use it, and the third gives a critical usage constraint. It is front-loaded and contains zero filler.

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?

For a search tool with no output schema and five parameters, the description is sufficiently complete. It covers the core purpose, usage context, and a key behavioral limitation. The parameter nuances are already well-handled by the schema, so the description doesn't need to repeat them.

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?

The schema covers all parameters with clear descriptions (100% coverage), so the baseline is 3. The description adds extra value by explaining how to use 'location' for geo-targeting and advising to include the place in the query as well as in 'location' for best results. This enriches the schema's descriptions.

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's function: 'Search Google Jobs for job listings with company, location and apply links.' It uses a specific verb and resource, and explicitly differentiates it from generic search siblings by saying 'Use this for any hiring, vacancy or job market question.' This leaves no ambiguity about the tool's purpose.

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 provides explicit when-to-use guidance: 'Use this for any hiring, vacancy or job market question.' It also gives a key exclusion: 'This engine does not accept a country code,' and recommends passing 'location' for geo-targeting. While it doesn't name alternative tools, the guidance is clear and actionable.

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

google_mapsgoogle_mapsA

Search Google Maps for places and local businesses with addresses, ratings, hours and coordinates. Use this for 'near me', 'where can I', or any location-bound question.

ParametersJSON Schema
NameRequiredDescriptionDefault
glNoTwo-letter country code for the search, for example 'ie', 'us', 'gb'.
hlNoTwo-letter language code for the results, for example 'en', 'fr'.
pageNoPage number for paginating through results. Starts at 1.
limitNoMaximum results to return to you. Kept low by default because search payloads are large; raise it only when you genuinely need more.
queryYesWhat to look for and where, for example 'coffee shops in Athlone'.
locationNoGeographic location to search from, as 'City,Country' (for example 'Dublin,Ireland'). Results are localised to this place.

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations provided, the description carries the transparency burden. It discloses that results include addresses, ratings, hours, and coordinates, and that the tool is for location-bound queries, which implies a read-only search behavior. It does not mention pagination, rate limits, or localization nuances, but the schema covers those details.

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?

The description is two sentences, front-loaded with the core purpose and immediately followed by usage guidance. No wasted words.

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?

With no output schema, the description compensates by enumerating the return data (addresses, ratings, hours, coordinates). It also mentions the typical use cases, though it doesn't cover all param nuances; those are in the schema, so the overall picture is solid.

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

Parameters3/5

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

All six parameters have thorough schema descriptions (100% coverage), so the baseline is 3. The main description adds no additional parameter semantics beyond the schema, though the example query in the schema ('coffee shops in Athlone') is echoed in the description's 'location-bound question'.

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 uses the verb 'Search' with the resource 'Google Maps for places and local businesses', and lists specific output data (addresses, ratings, hours, coordinates). This clearly distinguishes it from sibling search tools like google_news or google_shopping, which target other content types.

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?

It explicitly states 'Use this for "near me", "where can I", or any location-bound question,' giving clear context for when to invoke the tool. However, it does not name alternative tools for non-location queries or state explicit exclusions, so it falls short of a 5.

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

google_newsgoogle_newsA

Search Google News for recent news articles. Use this instead of google_search when recency matters or the user asks what is happening with a topic.

ParametersJSON Schema
NameRequiredDescriptionDefault
glNoTwo-letter country code for the search, for example 'ie', 'us', 'gb'.
hlNoTwo-letter language code for the results, for example 'en', 'fr'.
numNoHow many results to request from the engine. Defaults to the engine's own default.
pageNoPage number for paginating through results. Starts at 1.
limitNoMaximum results to return to you. Kept low by default because search payloads are large; raise it only when you genuinely need more.
queryYesThe news topic to search for.
locationNoGeographic location to search from, as 'City,Country' (for example 'Dublin,Ireland'). Results are localised to this place.

TDQS

A4/5.0
Behavior2/5

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

No annotations are provided, so the description must carry the full burden of behavioral disclosure. It only states the basic function and usage recommendation without covering result format, pagination behavior, rate limits, or any other nuances. This is a significant gap for a tool with no annotation support.

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?

The description is two sentences long, front-loading the primary action and immediately following with clear usage guidance. There is zero redundancy or fluff, making it highly efficient.

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?

For a search tool with seven parameters, a required query, and no output schema, the description provides essential context: what it does and when to prefer it. The schema covers all parameters, and the recency emphasis clarifies the key distinction from siblings. It could mention result ordering or limitations, but it remains complete enough for an agent to select and invoke it correctly.

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

Parameters3/5

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

Schema description coverage is 100%, so all seven parameters are already well-documented in the schema. The description itself adds no parameter-specific insights, keeping the score at the baseline of 3 per the calibration guidance.

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 it searches Google News for recent news articles, giving a specific verb and resource. The mention of 'recent' and 'what is happening with a topic' distinguishes it from general google_search and other sibling tools, leaving no ambiguity about scope.

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

Usage Guidelines5/5

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

The description provides explicit usage guidance: 'Use this instead of google_search when recency matters or the user asks what is happening with a topic.' It names the alternative and gives concrete conditions, which exceeds minimal expectations and directly aids tool selection.

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

google_scholargoogle_scholarA

Search Google Scholar for academic papers, citations and authors. Use this for research questions where peer-reviewed sources matter.

ParametersJSON Schema
NameRequiredDescriptionDefault
hlNoTwo-letter language code for the results, for example 'en', 'fr'.
numNoHow many results to request from the engine. Defaults to the engine's own default.
pageNoPage number for paginating through results. Starts at 1.
limitNoMaximum results to return to you. Kept low by default because search payloads are large; raise it only when you genuinely need more.
queryYesThe academic topic, paper title or author to search for.

TDQS

A3.7/5.0
Behavior2/5

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

No annotations are provided, so the description must carry the full behavioral disclosure burden. It only says 'Search' without revealing any behavioral traits such as whether the operation is read-only, how pagination behaves, rate limits, or the format of returned results. For a mutating side-effect free search tool this is a modest gap, but without annotations it is a clear shortfall.

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?

The description is two sentences, tightly written, and front-loaded: the first sentence states the action, the second adds usage context. Every sentence contributes, and there is no redundant phrasing or unnecessary detail.

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

Completeness3/5

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

The tool has 5 parameters, no output schema, and no annotations. The description clearly communicates purpose and usage but omits any explanation of return values, pagination, or configuration behavior. For a simple search tool this is functionally adequate, but it leaves room for more contextual guidance, hence a 3 rather than a higher score.

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

Parameters3/5

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

The schema provides 100% coverage for all five parameters, each with a description, so the baseline is 3. The tool description itself adds no parameter-level meaning (it doesn't reference query, num, or limit), but since the schema already documents them, no penalty is warranted.

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 opens with a specific verb+resource: 'Search Google Scholar for academic papers, citations and authors.' This clearly distinguishes it from sibling search tools like google_search or google_news by narrowing the domain to academic content and explicitly naming the resource. The mention of 'peer-reviewed sources' further reinforces its unique niche.

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 second sentence, 'Use this for research questions where peer-reviewed sources matter,' gives clear guidance on when to employ the tool. It lacks explicit alternatives or when-not-to-use instructions, though the sibling context (e.g., google_search) makes the comparison implicit. Thus it earns a 4, not a 5.

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

google_shoppinggoogle_shoppingA

Search Google Shopping for products with prices, sellers and ratings. Use this for price comparison and product availability questions.

ParametersJSON Schema
NameRequiredDescriptionDefault
glNoTwo-letter country code for the search, for example 'ie', 'us', 'gb'.
hlNoTwo-letter language code for the results, for example 'en', 'fr'.
numNoHow many results to request from the engine. Defaults to the engine's own default.
pageNoPage number for paginating through results. Starts at 1.
limitNoMaximum results to return to you. Kept low by default because search payloads are large; raise it only when you genuinely need more.
queryYesThe product to search for.
locationNoGeographic location to search from, as 'City,Country' (for example 'Dublin,Ireland'). Results are localised to this place.

TDQS

A3.8/5.0
Behavior2/5

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

No annotations are provided, so the description must fully disclose behavioral traits. It only states what is searched and returned, but does not mention localization effects (despite location parameter), pagination, result limits, price currency, or potential variability in availability/ratings. This is a significant transparency gap.

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?

The description is two sentences with no filler. The first sentence front-loads the core action ('Search Google Shopping for products with prices, sellers and ratings') and the second adds a clear use case. Every word earns its place.

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 exists, so the description should hint at return content; 'products with prices, sellers and ratings' does that. However, it omits important behavioral context like pagination, result limits, and localization effects that the schema documents but the description does not reinforce. For a straightforward search tool it is mostly complete, but lacks edge-case disclosure.

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

Parameters3/5

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

Schema coverage is 100% with detailed descriptions for all 7 parameters, so the baseline is 3. The tool description adds no additional meaning beyond the schema, but the schema already does a solid job, so a mid score is appropriate.

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 verb 'Search' and resource 'Google Shopping', and specifies the returned data: 'products with prices, sellers and ratings'. It also differentiates from siblings by saying 'Use this for price comparison and product availability questions', which is distinct from generic Google 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 provides explicit usage context: 'Use this for price comparison and product availability questions'. However, it does not mention when not to use the tool or name alternative tools, so it lacks full exclusion guidance.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 8 tool updatesv0.1.0
    • First observedamazon_search
    • First observedgoogle_jobs
    • First observedgoogle_maps
    • First observedgoogle_news
    • First observedgoogle_scholar
    • First observedgoogle_search
    • First observedgoogle_shopping
    • First observedyoutube_search
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.2/5.0
Disambiguation5/5

Each tool targets a distinct search vertical (general web, news, shopping, jobs, academic, maps, videos, Amazon). The descriptions clearly specify when to use each, leaving no ambiguity between them.

Naming Consistency4/5

Most tools follow a 'google_<service>' pattern, but youtube_search and amazon_search use a '<service>_search' pattern, creating a minor inconsistency. The overall style is still readable and predictable.

Tool Count5/5

With 8 tools, the server is well-scoped for a search aggregation service. Each tool covers a major search category without unnecessary redundancy.

Completeness5/5

The tool surface covers a broad range of search needs: general web, news, shopping, jobs, academic, maps, videos, and e-commerce. For a search-focused server, this is a comprehensive set with no obvious missing core capabilities.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • metasearch-mcp

    YeonwooSung
    A
    license
    Not graded
    quality
    D
    maintenance
    MCP server for using various search tools like Tavily API. Planning to support various search tools (i.e. wiki search, searxng, etc)
    3
    MIT

  • evo-scry

    krich11
    A
    license
    Not graded
    quality
    D
    maintenance
    MCP server for internet search via direct Google and DuckDuckGo HTML scraping with AI-powered result normalization and optional summarization, requiring no API keys for search.
    MIT

  • searxng-mcp

    fighter3005
    F
    license
    A
    quality
    C
    maintenance
    MCP server that provides a search_web tool to query a self-hosted SearXNG instance and return structured web search results.
    1
    -

  • mcp-server-searchapi

    roy6732856
    A
    license
    A
    quality
    B
    maintenance
    An MCP server for SearchApi that provides Google web, news, scholar, and YouTube search as agent-ready MCP tools.
    4
    17
    MIT

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Byski/mcp-searchapi'

If you have feedback or need assistance with the MCP directory API, please join our Discord server