mcp-server

Search the Web

alterlab_search

Read-onlyIdempotent

Search the web and read the top results in one call: a vendor-neutral list of URLs, titles and snippets, with each result page as concise markdown. Use when you have a question or topic but no URL yet; for one known URL use alterlab_scrape. Cost: $0.001 per query; only fetched result pages are billed on top, and scrape_results=false returns the result list alone (cheapest). Each result has a content_status (ok, partial, blocked, timeout, dead_origin, pending). concise=false returns full-length content; mode trades latency for coverage; domain restricts to one site and time_range filters by recency. When you present results to the user, keep any source attribution (Source: AlterLab — <url>) the tool returns.

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": "alterlab_search"
  }
}

Input Schema

Name	Required	Description
`mode`	No	Latency tier for page content: fast (5 s), standard (15 s), deep (60 s). Default: standard.
`page`	No	Results page number. Default: 1.
`query`	Yes
`domain`	No
`concise`	No	With scrape_results=true: concise agent output, markdown with size caps. Default: true. false returns full-length content.
`country`	No
`formats`	No
`language`	No
`time_range`	No
`num_results`	No	Number of results to return. Default: 10.
`safe_search`	No
`scrape_results`	No	Return the content of each result page (billed per fetched page). Default: true. false returns the unified result list only.
`extraction_schema`	No	JSON schema for structured extraction. Fields matching this schema are extracted from the page. Example: { "title": "string", "price": "number" }. LLM extraction needs your own LLM API key (OpenAI, Anthropic, OpenRouter, etc.) added in the dashboard BYOK settings; without one the request is rejected with byok_key_required and not charged.

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedNov 6, 2026

addedInput schema / properties / concise

Added value: +{
+  "default": true,
+  "description": "With scrape_results=true: concise agent output, markdown with size caps. Default: true. false returns full-length content.",
+  "type": "boolean"
+}

addedInput schema / properties / mode

Added value: +{
+  "description": "Latency tier for page content: fast (5 s), standard (15 s), deep (60 s). Default: standard.",
+  "enum": [
+    "fast",
+    "standard",
+    "deep"
+  ],
+  "type": "string"
+}

changedInput schema / properties / scrape_results / default
```
Previous value: -falseNew value: +true
```

changedInput schema / properties / scrape_results / description

Previous value: -"Also scrape each result page. Default: false."New value: +"Return the content of each result page (billed per fetched page). Default: true. false returns the unified result list only."

First observedNov 3, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Annotations already cover safety (readOnly, idempotent, non-destructive, openWorld), yet the description still adds substantial non-obvious behavior: per-query pricing of $0.001, per-fetched-page billing, the content_status enumeration (ok, partial, blocked, timeout, dead_origin, pending), and a source-attribution obligation when presenting results. The latency/coverage tradeoff for mode and the concise-vs-full content switch are also disclosed.

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-loaded with the core action and the sibling contrast, then cost, then options — a sensible order with no filler. It is dense and somewhat run-on in the later clauses, but nearly every sentence carries operational information.

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 13-parameter tool with a nested object and no output schema, the description does the important work: it sketches the return shape (URLs/titles/snippets plus markdown pages), explains content_status, and warns about billing and attribution. The remaining gap is mainly the localization/format/safe-search options, which no structured field documents.

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 only 46% across 13 parameters, so the description carries real weight. It explains scrape_results, concise, mode (as a latency/coverage tradeoff), domain, and time_range, but says nothing about country, language, formats, safe_search, or pagination (page), leaving several undocumented parameters unaddressed in both places.

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?

States a concrete compound verb and resource: search the web AND read the top results, returning 'a vendor-neutral list of URLs, titles and snippets, with each result page as concise markdown'. It explicitly contrasts with alterlab_scrape, so an agent can distinguish the two without opening either schema.

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?

Gives an explicit selection rule: 'Use when you have a question or topic but no URL yet; for one known URL use alterlab_scrape.' It also names a cost-driven variant ('scrape_results=false returns the result list alone (cheapest)'), which is actionable when-to-use guidance rather than vague context.

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

All mcp-server tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.