Universal Web Retrieval MCP

web_search

Search the web through a configurable provider chain, using automatic failover or concurrent fanout, and return ranked JSON results with titles, URLs, and snippets.

Instructions

Web search through a configurable provider chain with automatic failover. Two modes: mode="failover" (default) walks the chain one provider at a time and returns the first success (including an empty answer); mode="fanout" queries up to UWR_SEARCH_FANOUT providers concurrently, then merges and rank-fuses the results (even an all-empty set of OK answers succeeds with results: []; provider="fanout", every row carries sources; costs N× provider quota per search). Default chain: AnySearch -> Tavily -> DDGS; operators can reorder/extend it with UWR_SEARCH_CHAIN (e.g. anysearch,tavily,yuanbao,bocha,deepseek,kimi,ddgs) and pick the default mode with UWR_SEARCH_MODE. Auth is automatic: a configured API key enables keyed mode, otherwise the provider's official keyless access is used. Returns JSON: {success, provider, mode, latency_ms, attempts, results: [{title, url, snippet, published?, site?, sources?}]}. providers overrides the chain order for this one call (e.g. ["bocha"] or ["yuanbao","tavily"]); in fanout mode its first N eligible entries are queried.

Input Schema

Name	Required	Description	Default
`mode`	No
`limit`	No
`query`	Yes
`providers`	No

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv0.3.0Oct 23, 2026

addedInput schema / properties / mode

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Mode"
+}

addedInput schema / properties / providers

Added value: +{
+  "anyOf": [
+    {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Providers"
+}

First observedv0.1.0Sep 14, 2026

TDQS

A4.2/5.0

Behavior5/5

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

With no annotations, the description carries the full burden and does so well: it discloses auth behavior (configured key enables keyed mode, otherwise keyless), configurable chain/mode via env vars, the quota cost of fanout, and that an all-empty set of OK answers still counts as success with `results: []`. These are exactly the non-obvious traits an agent needs.

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?

The purpose is front-loaded in the first sentence, followed by mode semantics and then configuration details. It is dense but nearly every clause carries operational meaning; the redundant explicit return-shape listing is the main piece that overlaps with the existing output schema.

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 4-parameter tool with no annotations, it covers modes, auth, chain configuration, cost, and failure semantics, and an output schema exists so return values need no explanation. The only material gap is the undocumented `limit` parameter.

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?

Schema coverage is 0% (bare titles only), so the description must compensate, and it does for most parameters: `mode` values 'failover'/'fanout' are defined, `providers` is explained with examples and the 'first N eligible' rule in fanout. `query` is self-evident, but `limit` (default 5) is never mentioned, leaving one parameter undefined.

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?

States a specific verb+resource ('Web search') plus the distinctive mechanism (configurable provider chain with automatic failover) and the two execution modes. It is unambiguous about what the tool does, but never mentions the siblings web_fetch or list_providers, so the agent gets no explicit differentiation from them.

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?

Gives clear conditions for the main decision: failover walks the chain and returns the first success, fanout queries up to UWR_SEARCH_FANOUT providers concurrently and costs N× provider quota — enough to pick a mode. It also explains when to pass `providers`. It lacks guidance on when to use this versus web_fetch or list_providers.

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

Deploy Server