Skip to main content
Glama

Linkup web search

linkup-search
Read-only

Search the web for fresh, cited results, answers, or structured data using keyword or agentic queries. Read LinkedIn profile, company, and post pages by passing their exact URLs.

Instructions

Search the web with Linkup (POST /v1/search, synchronous).

Cost per call: flash, fast or standard 0.005 USD (searchResults) or 0.006 (sourcedAnswer, structured); deep 0.05 or 0.055. Rate limit 10 requests per second per organisation. A query without results returns HTTP 400 and is not billed. LinkedIn profile, company and post pages can only be read through this endpoint (give the exact URL in the query with standard or deep), not through linkup-fetch.

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": "linkup-search"
  }
}

Input Schema

NameRequiredDescriptionDefault
depthNoflash: ranked snippets in under 200 ms, no LLM (alpha). fast: one-shot keyword retrieval in about 1 s, the recommended default. standard: one agentic pass, 1 to 3 s, can fan out into parallel sub-searches. deep: several iterations with sequential instructions, 5 to 30 s.fast
queryYesNatural-language query. flash and fast are keyword-only (write 'NVIDIA Q4 2024 revenue'); standard and deep follow instructions (name what to retrieve, then how to shape the answer; standard can scrape one URL given in the query, deep several, in order).
to_dateNoYYYY-MM-DD.
from_dateNoYYYY-MM-DD. Put date ranges here, not in the query.
max_charsNoCap on the size of the returned JSON; long strings are truncated and _truncated is set.
max_resultsNoUpper bound on the number of results (minimum 1).
output_typeNosearchResults: raw results (name, url, content, publishedAt) for you to reason over. sourcedAnswer: an answer plus sources. structured: JSON matching structured_output_schema.searchResults
include_imagesNoAlso return image results.
exclude_domainsNoDomains to exclude.
include_domainsNoRestrict to these domains (up to 100). Recommended when authoritative sources are known.
include_sourcesNostructured only: also return the sources; the response then has data and sources.
include_inline_citationsNosourcedAnswer only: add inline citations to the answer text.
structured_output_schemaNoRequired when output_type is structured. JSON Schema (object or string) with root type object. Keep it flat.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the annotations (readOnly, openWorld, non-idempotent, non-destructive), it discloses per-call cost by depth and output type, a 10 req/s per-organisation rate limit, synchronous execution, and the notable behavior that a query with no results returns HTTP 400 and is not billed. That is exactly the kind of operational context the annotations cannot carry.

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 core purpose and endpoint lead, followed by cost, rate limit, error semantics and the sibling exclusion — each sentence earns its place with no filler, and the pricing is compressed into a single tiered sentence.

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 no output schema, the description covers cost, throughput limits, failure semantics, execution mode and one hard routing constraint, while the schema fully documents parameters. Minor gap: no guidance on response size or how the fan-out sub-searches in standard/deep affect latency or billing beyond the flat per-call price.

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 100%, so baseline would be 3, but the description adds parameter-level meaning the schema does not: cost scales differently across depth and output_type (0.005/0.006 vs 0.05/0.055), and the LinkedIn case constrains which depth values are usable. It still leaves most per-parameter detail to the schema.

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 names a specific verb and resource (web search via POST /v1/search, synchronous) and explicitly distinguishes itself from the sibling linkup-fetch by stating that LinkedIn profile, company and post pages are reachable only through this endpoint.

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 concrete when/when-not rule for LinkedIn URLs (use this endpoint with standard or deep depth, not linkup-fetch), and the schema-backed depth discussion lets an agent pick a latency/cost tradeoff. It stops short of routing against other siblings such as the research or rewind tools, so it is clear context rather than a full selection rule set.

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