Skip to main content
Glama
SearXNG MCP Server

SearXNG MCP Server

Searxng Ingest Search

searxng_ingest_search

Run SearXNG searches and ingest results into the medulla knowledge graph as typed search documents, queries, and engine links.

Instructions

Run a SearXNG search and natively ingest its results into medulla.

Wire-First: performs the search, then pushes each result into the knowledge graph as a search :Document (+ :SearchQuery / :SearchEngine typed nodes and their :resultOf / :fromEngine links). Best-effort: ingested is None when no engine is reachable. CONCEPT:AU-KG.ingest.enterprise-source-extractor.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "searxng_ingest_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryYesSearch query to submit to SearXNG
pagenoNoPage number of results to fetch
enginesNoOptional list of specific search engines to use
languageNoLanguage code for search results (e.g. en-US)en-US
categoriesNoOptional list of categories to search in (e.g. general, news, science)

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.3.2

TDQS

B3.4/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full burden and does disclose the important behaviors: this is a mutating tool that pushes each result into a knowledge graph as typed nodes with :resultOf / :fromEngine links, and it is best-effort with 'ingested' being None when no engine is reachable. That failure-mode disclosure is genuinely useful. It stops short of covering idempotency or duplicate handling on re-ingest, which matters for a write tool with no destructiveHint.

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

Conciseness3/5

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

The core statement is front-loaded and efficient, but the remainder is padded with internal vocabulary ('Wire-First', 'CONCEPT:AU-KG.ingest.enterprise-source-extractor') that conveys little to an agent choosing a tool. The node-type and link-name detail is informative; the trailing concept tag is not.

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?

An output schema exists, so return values need not be explained, and the five parameters are fully covered by the schema. For a mutating tool with zero annotations, the description gives adequate behavioral context: what gets written, in what shape, and what happens on failure. Only re-run/idempotency semantics are missing.

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 query, pageno, engines, language, and categories with defaults and examples. The description adds no format, syntax, or interaction detail beyond that, so the baseline of 3 applies.

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

Purpose4/5

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

The first sentence gives a concrete verb and resource ('Run a SearXNG search') and immediately states the distinctive side effect ('natively ingest its results into medulla'). That ingest step implicitly distinguishes it from plain search siblings such as searxng_search_app, but no sibling is named explicitly, so the differentiation is left to inference.

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

Usage Guidelines2/5

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

There is no explicit when-to-use or when-not guidance, and no alternative is named. 'Wire-First' gestures at a preferred workflow in internal jargon but never states the condition under which an agent should choose this over searxng_search_app or web_search, leaving the selection decision to the reader.

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