Integration

CORE integration

CORE (core.ac.uk) aggregates open access research papers from thousands of repositories and journals worldwide. Search works (deduplicated papers), outputs (repository copies), data providers and journals with CORE's query language, count matches grouped by field, and get a work, output, data provider or journal with its key dates and volumes, a work's outputs, its parsed TEI full text and an output's raw XML record. Not exposed: PDF downloads (they redirect to core.ac.uk; use downloadUrl), the output history, the full-text discovery and recommender endpoints and the data provider statistics with options. An API key is optional: without one, calls are limited to 100 tokens a day and 10 a minute (a simple query costs one token) and full text is withheld; a free key from the CORE API registration form raises the limits. The key is sent as a Bearer token in the Authorization header.

Connect CORE How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in CORE.Built from the 14 CORE tools below, on the connection you add once.

What you can do with CORE

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Stat, 4 operations

get_data_provider_statsGet data provider statsGETGets a data provider's volume in CORE: number of metadata records and of records with full text, plus harvest information.
get_journal_statsGet journal statsGETGets a journal's volume in CORE: number of metadata records, of records with full text, and of DOIs.
get_output_statsGet output statsGETGets the key dates of an output: deposited, published, updated, accepted and created in CORE.
get_work_statsGet work statsGETGets the key dates of a work: deposited, accepted, published and last updated.

Output, 3 operations

get_outputGet outputGETGets one output (a repository copy of a paper) by its CORE ID: title, authors, abstract, dates, DOI and OAI id, types, license, data provider, links, full-text status and download URL.
list_work_outputsList work outputsGETLists the outputs of a work: each copy of the paper harvested from a repository, journal or other data provider, with its own metadata, links and data provider.
search_data_provider_outputsSearch data provider outputsGETSearches the outputs harvested from one data provider with CORE's query language (an empty q lists them all), sorted by relevance or recency, up to 100 per call.

Aggregate, 1 operation

aggregate_searchAggregate searchPOSTCounts the records matching a query, grouped by the values of the given fields (for example works per yearPublished), instead of returning the records.

Data provider, 1 operation

get_data_providerGet data providerGETGets one data provider (a repository or journal CORE harvests) by its CORE id or opendoar:<id>: name, institution, type, ROR and OpenDOAR ids, OAI-PMH URL, software, location.

Journal, 1 operation

get_journalGet journalGETGets one journal by ISSN (issn:<ISSN>) or CORE id: title, identifiers, publisher, language, subjects and the matching data provider.

Raw, 1 operation

get_output_raw_recordGet output raw recordGETGets the raw XML metadata record CORE harvested for an output, as one text field.

Search, 1 operation

searchSearchGETSearches CORE's open access research collection: works (deduplicated papers), outputs (repository copies), data-providers or journals, with CORE's query language. At most 10,000 results reachable through offset and limit.

Tei, 1 operation

get_work_teiGet work teiGETGets the TEI XML parsed from the full text of a work, as one text field. Empty when CORE holds no parsed full text the caller may access.

Work, 1 operation

get_workGet workGETGets one work (a deduplicated research paper) by its CORE id: title, authors, abstract, dates, DOI and other identifiers, type, publisher, language, journals, data providers, links and its outputs.

Use CORE from Claude Code, Cursor or Codex

Connect CORE in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its CORE operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect CORE

Create your workspace
Sign up free. Nothing to install.
Connect CORE once
Add your CORE connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.