mcpField
D
Dimensions Analytics

Dimensions Analytics

Local
github.comSearch6Updated 3d ago
RepositoryVisit website

About Dimensions Analytics

Dimensions Analytics is an MCP server for Dimensions DSL research data. Its README names publications, grants, researchers, patents, and trials, and points to documentation for installation and usage.

Key features

  1. 01Search research data
  2. 02Analyze publications and grants
  3. 03Query researchers and patents
  4. 04Query clinical trials

Use cases

  1. 01Find Dimensions research data
  2. 02Analyze grants and publications
  3. 03Look up patents or clinical trials

MCP support

It is an MCP server for Dimensions DSL. The README does not specify its individual MCP tools.

#research#publications#grants#patents#clinical-trials#bibliometrics#analytics

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "ai-dimensions-analytics": {
      "command": "npx",
      "args": [
        "-y",
        "@digital-science-dsl/dimensions-analytics-mcp"
      ],
      "env": {
        "DIMENSIONS_API_KEY": "<DIMENSIONS_API_KEY>",
        "DIMENSIONS_BASE_URL": "<DIMENSIONS_BASE_URL>"
      }
    }
  }
}
Run commandnpx -y @digital-science-dsl/dimensions-analytics-mcp
Environment variables to set
DIMENSIONS_API_KEYSecretDimensions API key (same key as the Dimensions DSL API)
DIMENSIONS_BASE_URLDimensions API base URL. Required for custom instances, e.g. https://your-instance.dimensions.ai

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@digital-science-dsl/dimensions-analytics-mcp1.4.2

Tools

27

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
pageintegerNoPage index (0-based). Equivalent to skip = page × limit. Max page 49.
skipintegerNoRecords to skip (0-based). Mutually exclusive with page. Max window: 50000 total records.
typeenumNoFilter by publication typearticle | chapter | proceeding | monograph | preprint | book
limitintegerNoMaximum results to return (max 1000, default 100)
querystringNoFree-text search terms. Optional — omit for a filters-only search that relies solely on `filters` and/or the entity-specific convenience filters (e.g. yearFrom/yearTo).
fieldsarrayNoFields to return. Accepts aliases or DSL names. id is always included; publications also always include doi. Use dimensions://fields/{entity} for the full list.
sortByenumNoSort results by this field (total_citations = times_cited, citation_ratio = field_citation_ratio, altmetric_score = altmetric)times_cited | total_citations | recent_citations | relative_citation_ratio | field_citation_ratio | citation_ratio | altmetric | altmetric_score | year | date
yearTointegerNoFilter publications up to this year (inclusive)
filtersarrayNoAdditional where-clause filters. Each item needs field, operator, and (except for is_empty/is_not_empty) value, e.g. {"field": "researchers.id", "operator": "=", "value": "ur.01343614074.49"}. Supported operators: =, !=, >, <, >=, <=, in, is_empty, is_not_empty.
yearFromintegerNoFilter publications from this year (inclusive)
confirmLargeFetchbooleanNoRequired when skip≥5000, page≥5, or limit=1000 with skip>0. Acknowledges Dimensions reasonable-use policy (dimensions://schema/policy).

Details

From the project README

@digital-science-dsl/dimensions-analytics-mcp

Dimensions Analytics MCP server for the Dimensions DSL.

Documentation: github.com/digital-science/dimensions-analytics-mcp — Installation, Usage, Reference. Custom Dimensions instances must set DIMENSIONS_BASE_URL (see Installation).

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.