Search MCP Server

web_search

Search the web for real-time data, current events, documentation, and up-to-date factual information. Use live search to verify technical specifics and avoid relying on outdated training data.

Instructions

Search the web for real-time data, current events, documentation, and up-to-date factual information. NEVER rely on training data for technical specifics — always search first. See server instructions for full protocol.

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": "web_search"
  }
}

Input Schema

Name	Required	Description	Default
`query`	Yes	Keywords only — strip filler. Use exact quotes for error messages or code signatures. Prepend site:domain to narrow to a specific source. Never hardcode a year — if temporal context matters, state the need naturally (e.g. "latest api", "current version", "recent changes"). Search engines handle freshness.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.10.16Aug 1, 2026

TDQS

A3.8/5.0

Behavior2/5

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

There are no annotations, so the description must convey behavioral traits. It conveys that the tool returns current/realtime information and implies a read-only operation, but it does not disclose output format, pagination, rate limits, or any side effects. The reference to 'server instructions' offloads detail rather than providing it.

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

Conciseness5/5

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

The description is two sentences, front-loaded with the core purpose, and every word earns its place. The imperative instruction adds practical value without unnecessary verbosity.

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?

Given the simple single-parameter schema and no output schema, the description covers the tool's purpose, topical scope, and a clear usage rule. It could be more complete by stating return value expectations, but the combination of the schema and the pointer to server instructions makes it adequate for invocation.

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 coverage is 100% and the query parameter description is very detailed (keyword style, quotes, site: operator, date handling). The tool description adds general guidance on when to search but no additional parameter-level detail, so a baseline of 3 is appropriate.

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?

The description clearly identifies the tool's action ('Search the web') and its scope ('real-time data, current events, documentation, and up-to-date factual information'). It distinguishes itself from the sibling 'github_search' by targeting general web content rather than code repositories.

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?

It gives a strong usage directive: always search first for technical specifics rather than relying on training data. It also lists the types of information this tool is meant for, though it does not explicitly mention when to prefer alternative tools like 'github_search'.

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

Deploy Server