Parallel Search MCP
Server Details
The best web search for your AI Agent
- Status
- Healthy
- Uptime
- 52.5% over 38 days
- OAuth
- Works in Glama
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Server Listing
- Parallel Search MCP
TDQS
Scored across 2 tools
web_fetch retrieves content from a known URL while web_search_preview discovers URLs via query; these are complementary, non-overlapping operations with no risk of misselection.
Both names use snake_case with a shared web_ prefix, which is largely consistent. The 'preview' suffix on web_search is an odd, unexplained deviation that breaks strict symmetry with web_fetch.
Two tools is thin for a search-oriented server; the search-plus-fetch pair covers the minimal loop but leaves room for obvious additions like news/image search or batch fetch. Borderline rather than clearly well-scoped.
The search-then-fetch cycle is the core workflow and both halves are present, so no dead ends for typical use. Minor gaps exist (no news/specialized search, no bulk or crawl operations), but agents can work around them.
Available Tools
2 toolsweb_fetchARead-onlyInspect
Purpose: Fetch and extract relevant content from specific web URLs.
Ideal Use Cases:
Extracting content from specific URLs you've already identified
Exploring URLs returned by a web search in greater depth
| Name | Required | Description | Default |
|---|---|---|---|
| urls | Yes | List of URLs to extract content from. Must be valid HTTP/HTTPS URLs. Maximum 10 URLs per request. | |
| objective | No | Natural-language description of what information you're looking for from the URLs. Limit to 200 characters. |
Output Schema
| Name | Required | Description |
|---|---|---|
| usage | No | Usage metrics for the extract request. |
| errors | Yes | Extract errors: requested URLs not in the results. |
| results | Yes | Successful extract results. |
| warnings | No | Warnings for the extract request, if any. |
| extract_id | Yes | Extract request ID, e.g. `extract_cad0a6d2dec046bd95ae900527d880e7` |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already declare readOnlyHint=true and openWorldHint=true, so safety and variability are covered. The description adds 'extract relevant content' and objective-based filtering but gives no detail on partial-failure behavior, rate limits, or how extraction is performed, which is a modest, not severe, gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The 'Purpose' and 'Ideal Use Cases' headings make the content easy to parse and the purpose is front-loaded. There is minor redundancy between 'specific web URLs' and 'specific URLs you've already identified,' but no filler or irrelevant explanation.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple fetch tool with two parameters, full schema coverage, and an output schema, the description provides enough context about when and why to invoke it. It lacks details about failure modes or concurrency, but those are not critical given the schema and annotations already carry that burden.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the parameters are fully documented in the input schema. The description's 'relevant content' phrase implies the objective parameter influences extraction, but it does not add new meaning beyond what the schema already provides, keeping this at the baseline 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific verb + resource: 'Fetch and extract relevant content from specific web URLs.' The two ideal use cases explicitly contrast with the sibling search tool ('URLs returned by a web search'), so an agent can immediately distinguish this from web_search_preview.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It provides clear context by listing ideal use cases: extracting from already-identified URLs or deepening exploration of search results. It implies when to use it instead of a search tool, but it does not explicitly state when not to use it or name the sibling as an alternative, so it stops short of full exclusion guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
web_search_previewBRead-onlyInspect
Purpose: Perform web searches and return results in an LLM-friendly format and with parameters tuned for LLMs.
| Name | Required | Description | Default |
|---|---|---|---|
| objective | Yes | Natural-language description of what the web search is trying to find. Try to make the search objective atomic, looking for a specific piece of information. May include guidance about preferred sources or freshness. | |
| search_queries | Yes | List of keyword search queries of 3-6 words, which may include search operators. The search queries should be related to the objective. Limited to 3 entries of 100 characters each. |
Output Schema
| Name | Required | Description |
|---|---|---|
| usage | No | Usage metrics for the search request. |
| results | Yes | A list of WebSearchResult objects, ordered by decreasing relevance. |
| warnings | No | Warnings for the search request, if any. |
| search_id | Yes | Search ID. Example: `search_cad0a6d2dec046bd95ae900527d880e7` |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate read-only and open-world behavior. The description adds the LLM-friendly output format but does not mention limitations, result scope, pagination, or any other runtime behavior that the annotations do not cover.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The purpose is stated in one concise, front-loaded sentence with no filler. Slight redundancy exists between 'LLM-friendly format' and 'parameters tuned for LLMs,' but the structure is still efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description is adequate for a simple, read-only search tool, especially with annotations and schema coverage. However, it lacks use-case boundaries, alternative tool routing, and any note on result limitations, making it incomplete for fully autonomous selection.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already documents both parameters thoroughly, so the description adds little parameter-specific meaning. The phrase 'parameters tuned for LLMs' is vague and does not clarify individual parameter semantics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly identifies the action ('perform web searches') and the output characteristic ('LLM-friendly format'). It is specific enough to be understood, though it does not explicitly contrast with the sibling tool web_fetch.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is given about when to choose this tool over alternatives, when not to use it, or what type of query is best suited. The sibling web_fetch is not mentioned, so an agent receives no decision-making help.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
2 tool updates
- Changed
web_fetch1 field changed- changed
Output schema / $defs / UsageItem / properties / name / examplesPrevious value: -[ - "sku_search_additional_results", - "sku_extract_excerpts" -]New value: +[ + "sku_search", + "sku_extract_excerpts" +]
- Changed
web_search_preview1 field changed- changed
Output schema / $defs / UsageItem / properties / name / examplesPrevious value: -[ - "sku_search_additional_results", - "sku_extract_excerpts" -]New value: +[ + "sku_search", + "sku_extract_excerpts" +]
3 tool updates
- Changed
web_fetch12 fields changed- added
Input schema / properties / objective / anyOfAdded value: +[ + { + "type": "string" + }, + { + "type": "null" + } +] - added
Input schema / properties / objective / defaultAdded value: +null - changed
Input schema / properties / objective / descriptionPrevious value: -"What information you're looking for from the URLs."New value: +"Natural-language description of what\ninformation you're looking for from the URLs. Limit to 200 characters." - removed
Input schema / properties / objective / maxLengthRemoved value: -200 - added
Input schema / properties / objective / titleAdded value: +"Objective" - removed
Input schema / properties / objective / typeRemoved value: -"string" - changed
Input schema / properties / urls / descriptionPrevious value: -"URLs to extract content from."New value: +"List of URLs to extract content from. Must be valid\nHTTP/HTTPS URLs. Maximum 10 URLs per request." - removed
Input schema / properties / urls / items / formatRemoved value: -"uri" - removed
Input schema / properties / urls / maxItemsRemoved value: -10 - added
Input schema / properties / urls / titleAdded value: +"Urls" - added
Input schema / titleAdded value: +"extract_toolArguments" - changed
Output schema / (root)Previous value: -nullNew value: +{ + "$defs": { + "ExtractError": { + "description": "Extract error details.", + "properties": { + "content": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "description": "Content returned for http client or server errors, if any.", + "title": "Content" + }, + "error_type": { + "description": "Error type.", + "title": "Error Type", + "type": "string" + }, + "http_status_code": { + "anyOf": [ + { + "type": "integer" + }, + { + "type": "null" + } + ], + "description": "HTTP status code, if available.", + "title": "Http Status Code" + }, + "url": { + "title": "Url", + "type": "string" + } + }, + "required": [ + "url", + "error_type", + "http_status_code", + "content" + ], + "title": "ExtractError", + "type": "object" + }, + "ExtractResult": { + "description": "Extract result for a single URL.", + "properties": { + "excerpts": { + "anyOf": [ + { + "items": { + "type": "string" + }, + "type": "array" + }, + { + "type": "null" + } + ], + "default": null, + "description": "Relevant excerpted content from the URL, formatted as markdown.", + "title": "Excerpts" + }, + "full_content": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "Full content from the URL formatted as markdown, if requested.", + "title": "Full Content" + }, + "publish_date": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "Publish date of the webpage in YYYY-MM-DD format, if available.", + "title": "Publish Date" + }, + "title": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "Title of the webpage, if available.", + "title": "Title" + }, + "url": { + "description": "URL associated with the search result.", + "title": "Url", + "type": "string" + } + }, + "required": [ + "url" + ], + "title": "ExtractResult", + "type": "object" + }, + "UsageItem": { + "description": "Usage item for a single operation.", + "properties": { + "count": { + "description": "Count of the SKU.", + "examples": [ + 1 + ], + "title": "Count", + "type": "integer" + }, + "name": { + "description": "Name of the SKU.", + "examples": [ + "sku_search_additional_results", + "sku_extract_excerpts" + ], + "title": "Name", + "type": "string" + } + }, + "required": [ + "name", + "count" + ], + "title": "UsageItem", + "type": "object" + }, + "Warning": { + "description": "Human-readable message for a task.", + "properties": { + "detail": { + "anyOf": [ + { + "additionalProperties": true, + "type": "object" + }, + { + "type": "null" + } + ], + "default": null, + "description": "Optional detail supporting the warning.", + "title": "Detail" + }, + "message": { + "description": "Human-readable message.", + "title": "Message", + "type": "string" + }, + "type": { + "description": "Type of warning. Note that adding new warning types is considered a backward-compatible change.", + "enum": [ + "spec_validation_warning", + "input_validation_warning", + "warning" + ], + "examples": [ + "spec_validation_warning", + "input_validation_warning" + ], + "title": "Type", + "type": "string" + } + }, + "required": [ + "type", + "message" + ], + "title": "Warning", + "type": "object" + } + }, + "description": "Fetch result.", + "properties": { + "errors": { + "description": "Extract errors: requested URLs not in the results.", + "items": { + "$ref": "#/$defs/ExtractError" + }, + "title": "Errors", + "type": "array" + }, + "extract_id": { + "description": "Extract request ID, e.g. `extract_cad0a6d2dec046bd95ae900527d880e7`", + "title": "Extract Id", + "type": "string" + }, + "results": { + "description": "Successful extract results.", + "items": { + "$ref": "#/$defs/ExtractResult" + }, + "title": "Results", + "type": "array" + }, + "usage": { + "anyOf": [ + { + "items": { + "$ref": "#/$defs/UsageItem" + }, + "type": "array" + }, + { + "type": "null" + } + ], + "default": null, + "description": "Usage metrics for the extract request.", + "title": "Usage" + }, + "warnings": { + "anyOf": [ + { + "items": { + "$ref": "#/$defs/Warning" + }, + "type": "array" + }, + { + "type": "null" + } + ], + "default": null, + "description": "Warnings for the extract request, if any.", + "title": "Warnings" + } + }, + "required": [ + "extract_id", + "results", + "errors" + ], + "title": "ExtractResponse", + "type": "object" +}
- Removed
web_search - Added
web_search_preview
3 tool updates
- Changed
web_fetch12 fields changed- removed
Input schema / properties / objective / anyOfRemoved value: -[ - { - "type": "string" - }, - { - "type": "null" - } -] - removed
Input schema / properties / objective / defaultRemoved value: -null - changed
Input schema / properties / objective / descriptionPrevious value: -"Natural-language description of what\ninformation you're looking for from the URLs. Limit to 200 characters."New value: +"What information you're looking for from the URLs." - added
Input schema / properties / objective / maxLengthAdded value: +200 - removed
Input schema / properties / objective / titleRemoved value: -"Objective" - added
Input schema / properties / objective / typeAdded value: +"string" - changed
Input schema / properties / urls / descriptionPrevious value: -"List of URLs to extract content from. Must be valid\nHTTP/HTTPS URLs. Maximum 10 URLs per request."New value: +"URLs to extract content from." - added
Input schema / properties / urls / items / formatAdded value: +"uri" - added
Input schema / properties / urls / maxItemsAdded value: +10 - removed
Input schema / properties / urls / titleRemoved value: -"Urls" - removed
Input schema / titleRemoved value: -"extract_toolArguments" - changed
Output schema / (root)Previous value: -{ - "$defs": { - "ExtractError": { - "description": "Extract error details.", - "properties": { - "content": { - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "description": "Content returned for http client or server errors, if any.", - "title": "Content" - }, - "error_type": { - "description": "Error type.", - "title": "Error Type", - "type": "string" - }, - "http_status_code": { - "anyOf": [ - { - "type": "integer" - }, - { - "type": "null" - } - ], - "description": "HTTP status code, if available.", - "title": "Http Status Code" - }, - "url": { - "title": "Url", - "type": "string" - } - }, - "required": [ - "url", - "error_type", - "http_status_code", - "content" - ], - "title": "ExtractError", - "type": "object" - }, - "ExtractResult": { - "description": "Extract result for a single URL.", - "properties": { - "excerpts": { - "anyOf": [ - { - "items": { - "type": "string" - }, - "type": "array" - }, - { - "type": "null" - } - ], - "default": null, - "description": "Relevant excerpted content from the URL, formatted as markdown.", - "title": "Excerpts" - }, - "full_content": { - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "default": null, - "description": "Full content from the URL formatted as markdown, if requested.", - "title": "Full Content" - }, - "publish_date": { - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "default": null, - "description": "Publish date of the webpage in YYYY-MM-DD format, if available.", - "title": "Publish Date" - }, - "title": { - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "default": null, - "description": "Title of the webpage, if available.", - "title": "Title" - }, - "url": { - "description": "URL associated with the search result.", - "title": "Url", - "type": "string" - } - }, - "required": [ - "url" - ], - "title": "ExtractResult", - "type": "object" - }, - "UsageItem": { - "description": "Usage item for a single operation.", - "properties": { - "count": { - "description": "Count of the SKU.", - "examples": [ - 1 - ], - "title": "Count", - "type": "integer" - }, - "name": { - "description": "Name of the SKU.", - "examples": [ - "sku_search_additional_results", - "sku_extract_excerpts" - ], - "title": "Name", - "type": "string" - } - }, - "required": [ - "name", - "count" - ], - "title": "UsageItem", - "type": "object" - }, - "Warning": { - "description": "Human-readable message for a task.", - "properties": { - "detail": { - "anyOf": [ - { - "additionalProperties": true, - "type": "object" - }, - { - "type": "null" - } - ], - "default": null, - "description": "Optional detail supporting the warning.", - "title": "Detail" - }, - "message": { - "description": "Human-readable message.", - "title": "Message", - "type": "string" - }, - "type": { - "description": "Type of warning. Note that adding new warning types is considered a backward-compatible change.", - "enum": [ - "spec_validation_warning", - "input_validation_warning", - "warning" - ], - "examples": [ - "spec_validation_warning", - "input_validation_warning" - ], - "title": "Type", - "type": "string" - } - }, - "required": [ - "type", - "message" - ], - "title": "Warning", - "type": "object" - } - }, - "description": "Fetch result.", - "properties": { - "errors": { - "description": "Extract errors: requested URLs not in the results.", - "items": { - "$ref": "#/$defs/ExtractError" - }, - "title": "Errors", - "type": "array" - }, - "extract_id": { - "description": "Extract request ID, e.g. `extract_cad0a6d2dec046bd95ae900527d880e7`", - "title": "Extract Id", - "type": "string" - }, - "results": { - "description": "Successful extract results.", - "items": { - "$ref": "#/$defs/ExtractResult" - }, - "title": "Results", - "type": "array" - }, - "usage": { - "anyOf": [ - { - "items": { - "$ref": "#/$defs/UsageItem" - }, - "type": "array" - }, - { - "type": "null" - } - ], - "default": null, - "description": "Usage metrics for the extract request.", - "title": "Usage" - }, - "warnings": { - "anyOf": [ - { - "items": { - "$ref": "#/$defs/Warning" - }, - "type": "array" - }, - { - "type": "null" - } - ], - "default": null, - "description": "Warnings for the extract request, if any.", - "title": "Warnings" - } - }, - "required": [ - "extract_id", - "results", - "errors" - ], - "title": "ExtractResponse", - "type": "object" -}New value: +null
- Added
web_search - Removed
web_search_preview
2 tool updates
- Changed
web_fetch1 field changed- changed
Output schema / (root)Previous value: -nullNew value: +{ + "$defs": { + "ExtractError": { + "description": "Extract error details.", + "properties": { + "content": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "description": "Content returned for http client or server errors, if any.", + "title": "Content" + }, + "error_type": { + "description": "Error type.", + "title": "Error Type", + "type": "string" + }, + "http_status_code": { + "anyOf": [ + { + "type": "integer" + }, + { + "type": "null" + } + ], + "description": "HTTP status code, if available.", + "title": "Http Status Code" + }, + "url": { + "title": "Url", + "type": "string" + } + }, + "required": [ + "url", + "error_type", + "http_status_code", + "content" + ], + "title": "ExtractError", + "type": "object" + }, + "ExtractResult": { + "description": "Extract result for a single URL.", + "properties": { + "excerpts": { + "anyOf": [ + { + "items": { + "type": "string" + }, + "type": "array" + }, + { + "type": "null" + } + ], + "default": null, + "description": "Relevant excerpted content from the URL, formatted as markdown.", + "title": "Excerpts" + }, + "full_content": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "Full content from the URL formatted as markdown, if requested.", + "title": "Full Content" + }, + "publish_date": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "Publish date of the webpage in YYYY-MM-DD format, if available.", + "title": "Publish Date" + }, + "title": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "Title of the webpage, if available.", + "title": "Title" + }, + "url": { + "description": "URL associated with the search result.", + "title": "Url", + "type": "string" + } + }, + "required": [ + "url" + ], + "title": "ExtractResult", + "type": "object" + }, + "UsageItem": { + "description": "Usage item for a single operation.", + "properties": { + "count": { + "description": "Count of the SKU.", + "examples": [ + 1 + ], + "title": "Count", + "type": "integer" + }, + "name": { + "description": "Name of the SKU.", + "examples": [ + "sku_search_additional_results", + "sku_extract_excerpts" + ], + "title": "Name", + "type": "string" + } + }, + "required": [ + "name", + "count" + ], + "title": "UsageItem", + "type": "object" + }, + "Warning": { + "description": "Human-readable message for a task.", + "properties": { + "detail": { + "anyOf": [ + { + "additionalProperties": true, + "type": "object" + }, + { + "type": "null" + } + ], + "default": null, + "description": "Optional detail supporting the warning.", + "title": "Detail" + }, + "message": { + "description": "Human-readable message.", + "title": "Message", + "type": "string" + }, + "type": { + "description": "Type of warning. Note that adding new warning types is considered a backward-compatible change.", + "enum": [ + "spec_validation_warning", + "input_validation_warning", + "warning" + ], + "examples": [ + "spec_validation_warning", + "input_validation_warning" + ], + "title": "Type", + "type": "string" + } + }, + "required": [ + "type", + "message" + ], + "title": "Warning", + "type": "object" + } + }, + "description": "Fetch result.", + "properties": { + "errors": { + "description": "Extract errors: requested URLs not in the results.", + "items": { + "$ref": "#/$defs/ExtractError" + }, + "title": "Errors", + "type": "array" + }, + "extract_id": { + "description": "Extract request ID, e.g. `extract_cad0a6d2dec046bd95ae900527d880e7`", + "title": "Extract Id", + "type": "string" + }, + "results": { + "description": "Successful extract results.", + "items": { + "$ref": "#/$defs/ExtractResult" + }, + "title": "Results", + "type": "array" + }, + "usage": { + "anyOf": [ + { + "items": { + "$ref": "#/$defs/UsageItem" + }, + "type": "array" + }, + { + "type": "null" + } + ], + "default": null, + "description": "Usage metrics for the extract request.", + "title": "Usage" + }, + "warnings": { + "anyOf": [ + { + "items": { + "$ref": "#/$defs/Warning" + }, + "type": "array" + }, + { + "type": "null" + } + ], + "default": null, + "description": "Warnings for the extract request, if any.", + "title": "Warnings" + } + }, + "required": [ + "extract_id", + "results", + "errors" + ], + "title": "ExtractResponse", + "type": "object" +}
- Changed
web_search_preview2 fields changed- changed
Input schema / titlePrevious value: -"web_search_previewArguments"New value: +"search_toolArguments" - changed
Output schema / (root)Previous value: -nullNew value: +{ + "$defs": { + "UsageItem": { + "description": "Usage item for a single operation.", + "properties": { + "count": { + "description": "Count of the SKU.", + "examples": [ + 1 + ], + "title": "Count", + "type": "integer" + }, + "name": { + "description": "Name of the SKU.", + "examples": [ + "sku_search_additional_results", + "sku_extract_excerpts" + ], + "title": "Name", + "type": "string" + } + }, + "required": [ + "name", + "count" + ], + "title": "UsageItem", + "type": "object" + }, + "Warning": { + "description": "Human-readable message for a task.", + "properties": { + "detail": { + "anyOf": [ + { + "additionalProperties": true, + "type": "object" + }, + { + "type": "null" + } + ], + "default": null, + "description": "Optional detail supporting the warning.", + "title": "Detail" + }, + "message": { + "description": "Human-readable message.", + "title": "Message", + "type": "string" + }, + "type": { + "description": "Type of warning. Note that adding new warning types is considered a backward-compatible change.", + "enum": [ + "spec_validation_warning", + "input_validation_warning", + "warning" + ], + "examples": [ + "spec_validation_warning", + "input_validation_warning" + ], + "title": "Type", + "type": "string" + } + }, + "required": [ + "type", + "message" + ], + "title": "Warning", + "type": "object" + }, + "WebSearchResult": { + "description": "A single search result from the web search API.", + "properties": { + "excerpts": { + "anyOf": [ + { + "items": { + "type": "string" + }, + "type": "array" + }, + { + "type": "null" + } + ], + "default": null, + "description": "Relevant excerpted content from the URL, formatted as markdown.", + "title": "Excerpts" + }, + "publish_date": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "Publish date of the webpage in YYYY-MM-DD format, if available.", + "title": "Publish Date" + }, + "title": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "default": null, + "description": "Title of the webpage, if available.", + "title": "Title" + }, + "url": { + "description": "URL associated with the search result.", + "title": "Url", + "type": "string" + } + }, + "required": [ + "url" + ], + "title": "WebSearchResult", + "type": "object" + } + }, + "description": "Output for the Search API.", + "properties": { + "results": { + "description": "A list of WebSearchResult objects, ordered by decreasing relevance.", + "items": { + "$ref": "#/$defs/WebSearchResult" + }, + "title": "Results", + "type": "array" + }, + "search_id": { + "description": "Search ID. Example: `search_cad0a6d2dec046bd95ae900527d880e7`", + "title": "Search Id", + "type": "string" + }, + "usage": { + "anyOf": [ + { + "items": { + "$ref": "#/$defs/UsageItem" + }, + "type": "array" + }, + { + "type": "null" + } + ], + "default": null, + "description": "Usage metrics for the search request.", + "title": "Usage" + }, + "warnings": { + "anyOf": [ + { + "items": { + "$ref": "#/$defs/Warning" + }, + "type": "array" + }, + { + "type": "null" + } + ], + "default": null, + "description": "Warnings for the search request, if any.", + "title": "Warnings" + } + }, + "required": [ + "search_id", + "results" + ], + "title": "SearchResponse", + "type": "object" +}
1 tool update
- Changed
web_search_preview1 field changed- changed
Input schema / properties / search_queries / descriptionPrevious value: -"(optional) List of keyword search queries of 1-6\n words, which may include search operators. The search queries should be related to the\n objective. Limited to 5 entries of 200 characters each."New value: +"List of keyword search queries of 3-6\n words, which may include search operators. The search queries should be related to the\n objective. Limited to 3 entries of 100 characters each."
2 tool updates
- First observed
web_fetch - First observed
web_search_preview
Related MCP Connectors
Agent-native search engine with live web research optimized for AI agents.
Web search for AI agents — one tool across 6 engines, routed to the cheapest + cached.
Web search, browser automation, scraping, crawling and CAPTCHA solving for AI agents.
LLM-ready web search + instant answers + URL-to-clean-text fetch for agents and RAG.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceProvides web search and content extraction for AI agents.MIT
- AlicenseNot gradedqualityDmaintenanceWeb search, clean page reading & one-call research dossiers for AI agents. No API key — your agent does the synthesis.38 npmMIT
- AlicenseNot gradedqualityAmaintenanceEnables AI agents to perform live web searches with ranked results and extracted page passages, plus clean markdown extraction of any URL.MIT
- AlicenseAqualityDmaintenanceWeb search for AI agents across 6 engines (Serper, Brave, Exa, Tavily, Firecrawl, Perplexity) through one search tool. Routes each query to the cheapest engine that clears a quality bar and caches repeats. Hosted, streamable-HTTP, BYOK supported.11MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.