Skip to main content
Glama
webdata-tools-mcp

webdata-tools-mcp

Search papers, preprints and patents

search_research
Read-onlyIdempotent

Search papers, preprints, and patents from OpenAlex, arXiv, PubMed, Europe PMC, and patent offices in one deduplicated list, with filters for recency, open access, and citation impact.

Instructions

Papers, preprints and patents from OpenAlex, arXiv, PubMed, Europe PMC and the European Patent Office (worldwide patents: EP, WO, US, CN, JP, KR...) in one deduplicated list, newest first or most influential first: title, abstract, authors and affiliations, venue, DOI, PDF link, citations, citations per year, field-normalized impact (top 1% / 10%), open-access status, and for patents the number, applicants, inventors, IPC classes and family id. Retracted papers are left out. Runs the Apify Actor tacps126/research-radar on your Apify account (about $0.003 per result; spend per call is capped at $0.5).

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": {
      "queries": "<queries>"
    },
    "name": "search_research"
  }
}

Input Schema

NameRequiredDescriptionDefault
queriesYesTopics, keywords or phrases, e.g. "solid state battery".
sort_byNonewest first, most cited, or highest field-normalized impact (influential work).newest
sourcesNoWhich sources to search. Default: openalex, arxiv, pubmed, europepmc, patents.
max_itemsNoMaximum results to return (default 30, max 500). Cost scales with this.
extra_inputNoAdvanced: extra Actor input fields, merged over the defaults.
open_access_onlyNoOnly papers that are free to read.
posted_within_daysNoOnly results published in the last N days.

Output Schema

NameRequiredDescriptionDefault
toolYesName of the tool that produced the result.
countYesNumber of records the Actor returned.
itemsYesThe records. Long text fields are shortened to 600 characters.
shownYesNumber of records included in `items` (can be lower than count when the result is long).
truncatedYesTrue when records were left out to keep the result short; ask for fewer items.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.10.1

TDQS

A4/5.0
Behavior5/5

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

Goes well beyond the readOnly/openWorld/idempotent annotations by disclosing that it runs a named third-party Apify Actor on the caller's account, the per-result cost (~$0.003) and a hard $0.5 per-call spend cap. It also documents deduplication across sources and silent exclusion of retracted papers — exactly the non-obvious behaviors an agent would otherwise have to discover empirically.

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 purpose is front-loaded and the cost/retraction caveats earn their place, but a large middle span enumerates return fields (title, abstract, affiliations, DOI, citations per year, IPC classes, family id) that the output schema already defines. That list inflates a single run-on sentence without adding decision value, hurting scannability.

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?

Cost model, spend cap, deduplication, retraction filtering and actor provenance cover the risky parts of an open-world, paid call, and the output schema plus full param coverage handles the rest. The only real omission is guidance on how query phrasing interacts with results or what happens on zero hits, which is minor here.

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 all seven parameters are already documented, and the description largely restates them (source list, sort orders, cost scaling with volume). It adds only a marginal gloss — 'influential work' for the impact sort and worldwide patent coverage for the patents source — so baseline 3 applies.

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 specific verb+resource with exhaustive scope: papers, preprints and patents from five named providers plus the EPO, deduplicated, with an explicit ordering rule. No sibling tool covers scholarly literature or patents, so the agent can route to it unambiguously from the name and first clause alone.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied by the description of content and sorting: nothing states when to prefer this over a general news search or when a query is out of scope (e.g. non-literature questions). The 'newest first or most influential first' phrasing hints at the sort_by choice but never frames it as a decision rule. Absent alternatives among siblings for academic sources, this is adequate but not directive.

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