Skip to main content
Glama
lennney

Agent Search MCP

free_search

Read-onlyIdempotent

Search the web with configurable search engines and automatic fallback. Provides deduplicated results with confidence and relevance signals for quick fact-finding.

Instructions

Search the web with an explicit adapter set and bounded fallback.

Best for: Quick fact-finding, general search, when date/domain filters are not needed. Not recommended for: Filtered or verified-only results — use free_search_advanced. For full page content — use free_extract.

Twelve adapters are selectable; the default request uses DuckDuckGo + Sogou only. Adapters that share one upstream family are tried sequentially on failure and never double-count as corroboration. Explicitly requested optional API adapters run only when credentials are present and the free basket is short or below the quality gate. Results are deduplicated and include separate confidence, relevance, and source-count signals.

@readOnly true @idempotent true — makes outbound HTTP requests to configured search engines. Injection detection and SSRF protection active.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoNumber of results to return (1-50). Default 10. Higher values increase token usage.
queryYesSearch query string. Use natural language (e.g., "latest AI news 2026"). For Chinese coverage, include Sogou or Baidu in engines.
enginesNoSearch engines to use (default: duckduckgo + sogou). Free engines work without API keys. Optional API engines require their corresponding environment-variable credentials. For Chinese results, include sogou or baidu.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
metaYes
queryYes
enginesYes
resultsYes
cache_hitNo
rate_limitsNo
security_noteYes
partialFailuresNo
detected_languageNo
Behavior5/5

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

Beyond readOnly and idempotent annotations, the description details adapter fallback behavior, optional API credentials, deduplication, confidence signals, and security protections.

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 well-structured and concise, with each section serving a clear purpose: main action, usage guidelines, internal behavior, and safety notes.

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

Completeness5/5

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

Given the tool's complexity (multiple engines, dedup, signals, security), the description covers all essential behavioral aspects and appropriate usage context, leaving no major gaps.

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?

Input schema already has 100% description coverage; the description adds context like Chinese coverage with Sogou/Baidu and notes about default engines and credentials, enhancing parameter understanding.

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 'Search the web' and distinguishes from siblings by explicitly naming free_search_advanced for filtered/verified results and free_extract for full page content.

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 'Best for' and 'Not recommended for' sections, directly stating when to use and when to use alternatives, including sibling tool names.

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

Install Server

Other Tools

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/lennney/agent-search-mcp'

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