web-search-plus-mcp

web_search

Perform web searches across multiple providers with auto-routing, returning results with routing evidence, cache provenance, and typed errors. Use filters for freshness, domains, and research mode.

Instructions

Source-only web search through the Web Search Plus v3 runtime. Routes across configured source-result providers and returns additive v3 evidence, routing receipts, provider attempts, cache provenance, and typed errors.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`mode`	No	normal fast path or opt-in research mode.	normal
`count`	No	Number of results
`depth`	No	Exa depth: normal, deep multi-source search, or deep-reasoning.	normal
`query`	Yes	Search query
`country`	No	ISO 3166-1 alpha-2 country override (e.g. at, fr).
`language`	No	ISO 639-1 language override (e.g. de), or auto via config defaults.
`no_cache`	No	Bypass the search cache and fetch live results. Use for recency queries when a cached hit would be stale.
`provider`	No	Force a specific provider, or use auto-routing.	auto
`cache_ttl`	No	Search-cache TTL in seconds. Default is 3600 if omitted.
`freshness`	No	Unified recency filter alias for providers that support freshness.
`time_range`	No	Recency filter.
`search_type`	No	Search vertical. Serper and TinyFish serve news natively; other providers report unsupported metadata.	search
`quality_report`	No	Attach routing/result diagnostics.
`exclude_domains`	No	Exclude these domains.
`include_domains`	No	Restrict to these domains.
`research_time_budget`	No	Best-effort budget for research mode.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv4.3.1Sep 24, 2026

addedInput schema / properties / cache_ttl

Added value: +{
+  "description": "Search-cache TTL in seconds. Default is 3600 if omitted.",
+  "maximum": 86400,
+  "minimum": 1,
+  "type": "integer"
+}

addedInput schema / properties / no_cache

Added value: +{
+  "default": false,
+  "description": "Bypass the search cache and fetch live results. Use for recency queries when a cached hit would be stale.",
+  "type": "boolean"
+}

Changed1 schema field changedv4.0.2Aug 22, 2026

changedInput schema / properties / provider / enum

Previous value: -[
-  "auto",
-  "serper",
-  "serpbase",
-  "brave",
-  "tavily",
-  "querit",
-  "linkup",
-  "exa",
-  "firecrawl",
-  "parallel",
-  "you",
-  "searxng",
-  "keenable",
-  "hound",
-  "octen",
-  "tinyfish"
-]New value: +[
+  "auto",
+  "serper",
+  "serpbase",
+  "brave",
+  "tavily",
+  "querit",
+  "linkup",
+  "exa",
+  "firecrawl",
+  "parallel",
+  "you",
+  "searxng",
+  "keenable",
+  "donsetch",
+  "octen",
+  "tinyfish"
+]

Changed2 schema fields changedv3.6.0Aug 7, 2026

changedInput schema / properties / provider / enum

Previous value: -[
-  "auto",
-  "serper",
-  "serpbase",
-  "brave",
-  "tavily",
-  "querit",
-  "linkup",
-  "exa",
-  "firecrawl",
-  "parallel",
-  "you",
-  "searxng",
-  "keenable",
-  "hound",
-  "octen"
-]New value: +[
+  "auto",
+  "serper",
+  "serpbase",
+  "brave",
+  "tavily",
+  "querit",
+  "linkup",
+  "exa",
+  "firecrawl",
+  "parallel",
+  "you",
+  "searxng",
+  "keenable",
+  "hound",
+  "octen",
+  "tinyfish"
+]

changedInput schema / properties / search_type / description

Previous value: -"Search vertical. Serper serves news natively; other providers report unsupported metadata."New value: +"Search vertical. Serper and TinyFish serve news natively; other providers report unsupported metadata."

Changed1 schema field changedv3.3.1Jul 29, 2026

changedInput schema / properties / provider / enum

Previous value: -[
-  "auto",
-  "serper",
-  "serpbase",
-  "brave",
-  "tavily",
-  "querit",
-  "linkup",
-  "exa",
-  "firecrawl",
-  "parallel",
-  "you",
-  "searxng",
-  "keenable"
-]New value: +[
+  "auto",
+  "serper",
+  "serpbase",
+  "brave",
+  "tavily",
+  "querit",
+  "linkup",
+  "exa",
+  "firecrawl",
+  "parallel",
+  "you",
+  "searxng",
+  "keenable",
+  "hound",
+  "octen"
+]

Changed2 schema fields changedJul 14, 2026

changedInput schema / properties / depth / description

Previous value: -"Exa depth: normal, deep synthesis, or deep-reasoning."New value: +"Exa depth: normal, deep multi-source search, or deep-reasoning."

changedInput schema / properties / provider / enum

Previous value: -[
-  "auto",
-  "serper",
-  "serpbase",
-  "brave",
-  "tavily",
-  "querit",
-  "linkup",
-  "exa",
-  "firecrawl",
-  "parallel",
-  "perplexity",
-  "kilo-perplexity",
-  "you",
-  "searxng",
-  "keenable"
-]New value: +[
+  "auto",
+  "serper",
+  "serpbase",
+  "brave",
+  "tavily",
+  "querit",
+  "linkup",
+  "exa",
+  "firecrawl",
+  "parallel",
+  "you",
+  "searxng",
+  "keenable"
+]

Changed4 schema fields changedv0.16.0Jul 4, 2026

addedInput schema / properties / country

Added value: +{
+  "description": "ISO 3166-1 alpha-2 country override (e.g. at, fr).",
+  "type": "string"
+}

addedInput schema / properties / freshness

Added value: +{
+  "description": "Unified recency filter alias for providers that support freshness.",
+  "enum": [
+    "day",
+    "week",
+    "month",
+    "year"
+  ],
+  "type": "string"
+}

addedInput schema / properties / language

Added value: +{
+  "description": "ISO 639-1 language override (e.g. de), or auto via config defaults.",
+  "type": "string"
+}

addedInput schema / properties / search_type

Added value: +{
+  "default": "search",
+  "description": "Search vertical. Serper serves news natively; other providers report unsupported metadata.",
+  "enum": [
+    "search",
+    "news"
+  ],
+  "type": "string"
+}

Changed1 schema field changedv0.13.0Jun 30, 2026

changedInput schema / properties / provider / enum

Previous value: -[
-  "auto",
-  "serper",
-  "serpbase",
-  "brave",
-  "tavily",
-  "querit",
-  "linkup",
-  "exa",
-  "firecrawl",
-  "parallel",
-  "perplexity",
-  "kilo-perplexity",
-  "you",
-  "searxng"
-]New value: +[
+  "auto",
+  "serper",
+  "serpbase",
+  "brave",
+  "tavily",
+  "querit",
+  "linkup",
+  "exa",
+  "firecrawl",
+  "parallel",
+  "perplexity",
+  "kilo-perplexity",
+  "you",
+  "searxng",
+  "keenable"
+]

Changed1 schema field changedv0.12.0Jun 22, 2026

changedInput schema / properties / provider / enum

Previous value: -[
-  "auto",
-  "serper",
-  "brave",
-  "tavily",
-  "exa",
-  "linkup",
-  "firecrawl",
-  "parallel",
-  "perplexity",
-  "kilo-perplexity",
-  "you",
-  "searxng",
-  "serpbase",
-  "querit"
-]New value: +[
+  "auto",
+  "serper",
+  "serpbase",
+  "brave",
+  "tavily",
+  "querit",
+  "linkup",
+  "exa",
+  "firecrawl",
+  "parallel",
+  "perplexity",
+  "kilo-perplexity",
+  "you",
+  "searxng"
+]

Changed1 schema field changedv0.9.0May 19, 2026

changedInput schema / properties / provider / enum

Previous value: -[
-  "auto",
-  "serper",
-  "brave",
-  "tavily",
-  "exa",
-  "linkup",
-  "firecrawl",
-  "perplexity",
-  "kilo-perplexity",
-  "you",
-  "searxng",
-  "serpbase",
-  "querit"
-]New value: +[
+  "auto",
+  "serper",
+  "brave",
+  "tavily",
+  "exa",
+  "linkup",
+  "firecrawl",
+  "parallel",
+  "perplexity",
+  "kilo-perplexity",
+  "you",
+  "searxng",
+  "serpbase",
+  "querit"
+]

Addedv0.8.0May 17, 2026
Removedv0.7.0May 15, 2026

Changed1 schema field changedv0.5.1May 14, 2026

changedInput schema / properties / provider / enum

Previous value: -[
-  "auto",
-  "serper",
-  "brave",
-  "tavily",
-  "exa",
-  "querit",
-  "linkup",
-  "firecrawl",
-  "perplexity",
-  "you",
-  "searxng"
-]New value: +[
+  "auto",
+  "serper",
+  "brave",
+  "tavily",
+  "exa",
+  "querit",
+  "linkup",
+  "firecrawl",
+  "perplexity",
+  "kilo-perplexity",
+  "you",
+  "searxng"
+]

Changed12 schema fields changedv0.2.1May 7, 2026

changedInput schema / properties / count / description

Previous value: -"Number of results (default: 5)"New value: +"Number of results"

addedInput schema / properties / count / maximum
```
Added value: +20
```
addedInput schema / properties / count / minimum
```
Added value: +1
```

addedInput schema / properties / depth

Added value: +{
+  "default": "normal",
+  "description": "Exa depth: normal, deep synthesis, or deep-reasoning.",
+  "enum": [
+    "normal",
+    "deep",
+    "deep-reasoning"
+  ],
+  "type": "string"
+}

addedInput schema / properties / exclude_domains

Added value: +{
+  "description": "Exclude these domains.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

addedInput schema / properties / include_domains

Added value: +{
+  "description": "Restrict to these domains.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

addedInput schema / properties / mode

Added value: +{
+  "default": "normal",
+  "description": "normal fast path or opt-in research mode.",
+  "enum": [
+    "normal",
+    "research"
+  ],
+  "type": "string"
+}

changedInput schema / properties / provider / description

Previous value: -"Force a specific provider (default: auto)"New value: +"Force a specific provider, or use auto-routing."

changedInput schema / properties / provider / enum

Previous value: -[
-  "auto",
-  "serper",
-  "tavily",
-  "exa"
-]New value: +[
+  "auto",
+  "serper",
+  "brave",
+  "tavily",
+  "exa",
+  "querit",
+  "linkup",
+  "firecrawl",
+  "perplexity",
+  "you",
+  "searxng"
+]

addedInput schema / properties / quality_report

Added value: +{
+  "default": false,
+  "description": "Attach routing/result diagnostics.",
+  "type": "boolean"
+}

addedInput schema / properties / research_time_budget

Added value: +{
+  "default": 55,
+  "description": "Best-effort budget for research mode.",
+  "maximum": 75,
+  "minimum": 1,
+  "type": "number"
+}

addedInput schema / properties / time_range

Added value: +{
+  "description": "Recency filter.",
+  "enum": [
+    "hour",
+    "day",
+    "week",
+    "month",
+    "year"
+  ],
+  "type": "string"
+}

First observedv1.0.0Mar 14, 2026

TDQS

C2.9/5.0

Behavior3/5

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

With no annotations, the description carries the full burden of behavioral disclosure. It does reveal non-obvious behavior such as routing across providers, returning cache provenance, and emitting typed errors. However, it does not explain how results are structured, how caching affects behavior, or what side effects or limitations exist.

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 description is a single sentence and front-loaded with 'web search', but it is dense with undefined jargon such as 'additive v3 evidence' and 'routing receipts'. It is concise in length but not in clarity, and the value of several phrases is questionable.

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

Completeness2/5

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

For a 16-parameter tool with no annotations and no output schema, the description is far too thin. It does not explain the shape of returned evidence, the meaning of 'source-only', how provider routing works in practice, or when to set key options like mode, depth, or provider. An agent would need to rely entirely on the schema.

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 baseline is 3 even though the description itself adds no parameter-level meaning. The description's mentions of routing and cache provenance thematically relate to parameters like provider and no_cache, but it does not enrich the parameter semantics beyond the schema.

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 description names a specific verb and resource ('web search') and differentiates it from the sibling web_extract by emphasizing search rather than extraction. However, 'source-only' and 'Web Search Plus v3 runtime' are jargon that obscure rather than clarify the core function.

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 guidance on when to use this tool versus web_extract or any alternative. The description implies a search use case but does not state when it is appropriate, when it is not, or what conditions would route an agent to a sibling tool.

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

Deploy Server

web_search

Instructions

Input Schema

Schema Changelog

TDQS

Other Tools