Skip to main content
Glama
wtznicy

MyWebSearch

by wtznicy
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

search

Read-onlyIdempotent

Query multiple web engines without API keys. Use one query or up to four concurrent queries; auto-route by language for Chinese or English results.

Instructions

Search the web across multiple engines with no API key required. Requires either "query" (single query string) or "queries" (array of 1-4 queries for fan-out). searchMode: omit/auto = server SEARCH_MODE; request/playwright force that mode. Engine guidance: for Chinese queries prefer engines=["baidu","sogou","csdn","juejin"] (domestic engines have far better Chinese content coverage); for English/official docs use bing; overseas engines (duckduckgo/brave/startpage/exa) need a proxy. Omit engines to use server-side auto routing. Cite the relevant result URLs as markdown links in your answer. For OFFICIAL library/framework documentation, prefer resolveLibraryId + queryDocs (more reliable, works without proxy). Use the site: operator for site-specific queries (e.g. "update site:docs.elastic.co").

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoMax results (default: server DEFAULT_SEARCH_LIMIT, usually 10)
queryNoSingle search query (required if 'queries' is omitted; use 'queries' for multi-intent fan-out)
enginesNoSearch engines to use (default: server default, which may auto-route by query language)
queriesNo1-4 queries run concurrently and merged (required if 'query' is omitted) — for covering multiple intents in one call (e.g. official docs / Chinese community / English)
minResultsNoAuto-run additional engines when fewer than this many USABLE results (relevant, non-entry-page) come back (default: server DEFAULT_MIN_RESULTS, usually 5; max 50 — larger values only burn the search deadline)
searchModeNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.0.21
    • changedInput schema / properties / queries / description
      Previous value: -"1-4 queries run concurrently and merged (dedup by URL) — for covering multiple intents in one call (e.g. official docs / Chinese community / English)"New value: +"1-4 queries run concurrently and merged (required if 'query' is omitted) — for covering multiple intents in one call (e.g. official docs / Chinese community / English)"
    • changedInput schema / properties / query / description
      Previous value: -"Single search query (use queries for multi-intent fan-out)"New value: +"Single search query (required if 'queries' is omitted; use 'queries' for multi-intent fan-out)"
  2. Changed2 schema fields changedv1.0.17
    • changedInput schema / properties / minResults / description
      Previous value: -"Auto-run additional engines when fewer than this many USABLE results (relevant, non-entry-page) come back (default: server DEFAULT_MIN_RESULTS, usually 5)"New value: +"Auto-run additional engines when fewer than this many USABLE results (relevant, non-entry-page) come back (default: server DEFAULT_MIN_RESULTS, usually 5; max 50 — larger values only burn the search deadline)"
    • addedInput schema / properties / minResults / maximum
      Added value: +50
  3. Changed8 schema fields changedv1.0.15
    • removedInput schema / properties / engines / default
      Removed value: -[
-  "bing"
-]
    • addedInput schema / properties / engines / description
      Added value: +"Search engines to use (default: server default, which may auto-route by query language)"
    • removedInput schema / properties / limit / default
      Removed value: -10
    • addedInput schema / properties / limit / description
      Added value: +"Max results (default: server DEFAULT_SEARCH_LIMIT, usually 10)"
    • changedInput schema / properties / minResults / description
      Previous value: -"Auto-run additional engines when fewer than this many results come back (default: disabled)"New value: +"Auto-run additional engines when fewer than this many USABLE results (relevant, non-entry-page) come back (default: server DEFAULT_MIN_RESULTS, usually 5)"
    • addedInput schema / properties / queries
      Added value: +{
+  "description": "1-4 queries run concurrently and merged (dedup by URL) — for covering multiple intents in one call (e.g. official docs / Chinese community / English)",
+  "items": {
+    "maxLength": 500,
+    "minLength": 1,
+    "type": "string"
+  },
+  "maxItems": 4,
+  "minItems": 1,
+  "type": "array"
+}
    • addedInput schema / properties / query / description
      Added value: +"Single search query (use queries for multi-intent fan-out)"
    • removedInput schema / required
      Removed value: -[
-  "query"
-]
  4. First observedv1.0.11

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already cover readOnly/idempotent/openWorld, and the description adds meaningful extras: no API key required, the proxy constraint for duckduckgo/brave/startpage/exa, auto-run behavior of minResults, and searchMode forcing semantics. Return-format behavior is partially covered by the citation instruction but not fully.

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

Conciseness4/5

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

Front-loads purpose and the required-parameter rule, then layers engine/alternative guidance. Dense but almost every clause carries actionable information; the engine list and proxy note are borderline verbose but justified for routing correctness.

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, and the description compensates with the instruction to cite result URLs as markdown links. Combined with param guidance and sibling alternatives, an agent has enough to call it correctly, though the return shape (fields per result) is not described.

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?

With 83% schema coverage the baseline is 3, but the description adds real meaning beyond the schema: the query-vs-queries fan-out distinction, the searchMode omit/auto vs request/playwright behavior (the enum itself is undescribed in the schema), and engine routing guidance that maps to the engines parameter.

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?

Opens with a specific verb+resource ('Search the web across multiple engines') and adds a distinguishing trait (no API key required). It clearly separates itself from siblings like queryDocs and resolveLibraryId, which it explicitly names as preferred for official docs.

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?

Provides explicit routing: when to use this tool vs resolveLibraryId+queryDocs for official documentation, which engines suit Chinese vs English queries, proxy requirements for overseas engines, and the site: operator for site-specific queries. When-not guidance is present and actionable.

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