Skip to main content
Glama
DasDigitaleMomentum

searxNcrawl

by DasDigitaleMomentum
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Search

search

Search the web via the configured search providers (SearXNG, You.com).

Instructions

Search the web via the configured search providers (SearXNG, You.com).

All configured providers are queried in parallel. Their results are merged (URL dedup, round-robin, results found by several providers first) and each result lists the providers that returned it.

Input Schema

NameRequiredDescriptionDefault
queryYesSearch query string (required)
pagenoNoPage number for results (minimum 1). Default: 1
enginesNoSearXNG only. Specific search engines to use. Default: None (all available)
languageNoLanguage code for results (e.g., 'en', 'de', 'fr'). Default: 'en'en
providersNoSubset of configured providers to query ('searxng', 'youcom'). Default: None (all configured providers)
categoriesNoSearXNG only. Categories to search (e.g., ['general', 'images', 'news']). Default: None (all)
safesearchNoSafe search level - 0 (off), 1 (moderate), 2 (strict). Default: 1
time_rangeNoTime range filter - 'day', 'week', 'month', or 'year'. Default: None (no filter)
max_resultsNoMaximum results to return (1-50). Default: 10
max_retriesNoMaximum attempts per provider for transient request errors (default: 3)
include_contentNoAlso crawl each result page and add its Markdown as "markdown" (or "crawl_error" if the page fails). Default: false

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.33.1
    • addedInput schema / properties / include_content
      Added value: +{
+  "default": false,
+  "description": "Also crawl each result page and add its Markdown as\n\"markdown\" (or \"crawl_error\" if the page fails). Default: false",
+  "type": "boolean"
+}
  2. Changed4 schema fields changedv0.32.0
    • changedInput schema / properties / categories / description
      Previous value: -"Categories to search (e.g., ['general', 'images', 'news']). Default: None (all)"New value: +"SearXNG only. Categories to search (e.g., ['general', 'images', 'news']). Default: None (all)"
    • changedInput schema / properties / engines / description
      Previous value: -"Specific search engines to use. Default: None (all available)"New value: +"SearXNG only. Specific search engines to use. Default: None (all available)"
    • changedInput schema / properties / max_retries / description
      Previous value: -"Maximum attempts for transient RequestError failures (default: 3)"New value: +"Maximum attempts per provider for transient request errors (default: 3)"
    • addedInput schema / properties / providers
      Added value: +{
+  "anyOf": [
+    {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Subset of configured providers to query ('searxng', 'youcom').\nDefault: None (all configured providers)"
+}
  3. First observedv0.30.0

TDQS

A3.8/5.0
Behavior3/5

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

With no annotations, the description carries the full behavioral burden. It helpfully discloses parallel provider querying, URL dedup, round-robin merging, and per-result provider attribution, but omits failure handling when one provider fails and rate-limit behavior.

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 purpose is front-loaded in the first sentence, followed by concise behavioral detail. Three sentences with no wasted text.

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 an 11-parameter search tool with full schema coverage but no output schema, the description covers the essential aggregation behavior and result attribution. It could say more about result shape and partial-failure behavior, but it is adequate for correct invocation.

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 the schema already documents all 11 parameters. The description adds context about provider merging but no parameter-specific semantics beyond what the schema provides.

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 states a specific verb+resource ("Search the web") and names the configured providers. Siblings crawl and crawl_site are page-fetching tools, so the query-based discovery purpose is clearly distinguishable.

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

Usage Guidelines3/5

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

Usage is implied by "Search the web", but there is no explicit guidance on when to use this versus crawl/crawl_site, nor any exclusions. The agent must infer that search is for discovery and crawl for known URLs.

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

Deploy Server

Other Tools