Opencitations

io.github.pipeworx-iov0.1.2Updated Oct 1, 2026

OpenCitations MCP — citation index (COCI + general Index API).

VerifiedStreamable HTTPWeb executableData & AnalyticsKnowledge & Memory

Overview

AI-generated overview

Lets an assistant look up citation data for scholarly DOIs — who cites a paper, what it cites, and its bibliographic metadata.

What it does
Wraps the OpenCitations index (COCI and generic Index APIs) as MCP tools. Tools include references(doi) for works cited by a DOI, citations(doi) for works citing it, citation_count(doi) and references_count(doi) for totals, metadata(dois) for bibliographic records of up to 50 comma-separated DOIs, and citation(oci) for a single citation by Open Citation Identifier. It is keyless and returns open-license citation data.
When to use it
Useful for literature reviews, citation-graph exploration, impact checks, and verifying bibliographic details of DOIs. Worth adding when an assistant needs citation counts or reference lists without a paid bibliographic database subscription.
Requirements
Runs as a remote streamable HTTP endpoint at the Pipeworx gateway; no account, API key, or environment variable is declared. A local stdio variant is also offered via npx, which needs Node.js. Network access to the gateway or to opencitations.net is required.
Before you install
The pack endpoint also exposes shared Pipeworx meta-tools such as ask_pipeworx, discover_tools, search_within, and remember/recall, so the listed tool count is larger than the pack's own tools and consumes extra context. Queries are sent to a third-party gateway and to OpenCitations. No credentials are requested, and the tools described only read citation data.

Installation

In SourceWeft

  1. Open Opencitations in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "opencitations": {
      "type": "http",
      "url": "https://gateway.pipeworx.io/opencitations/mcp"
    }
  }
}

README

@pipeworx/opencitations

OpenCitations MCP — open-license citation index (COCI + Index APIs). Keyless.

Part of Pipeworx — an MCP gateway connecting AI agents to 1683+ live data sources.

Tools

  • references(doi) — DOIs cited BY the given DOI
  • citations(doi) — DOIs that cite the given DOI
  • citation_count(doi) — number of incoming citations for a DOI
  • references_count(doi) — number of outgoing references for a DOI
  • metadata(dois) — bibliographic metadata for one or more DOIs (comma-sep list, max 50)
  • citation(oci) — a single citation by Open Citation Identifier

Data source

https://opencitations.net/index/coci/api/v1/ (COCI) and https://opencitations.net/index/api/v1/ (generic Index endpoints).

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

json
{  "mcpServers": {    "opencitations": {      "url": "https://gateway.pipeworx.io/opencitations/mcp"    }  }}

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/opencitations/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — ask_pipeworx, discover_tools, search_within, remember/recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools are what let a scoped connection answer a question this pack does not cover — via ask_pipeworx, which routes across the whole catalog — without you adding a second MCP server. There is currently no way to mount a pack endpoint without them; if the extra schemas cost you more context than the routing is worth, connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:

json
{  "mcpServers": {    "pipeworx": {      "url": "https://gateway.pipeworx.io/mcp"    }  }}

Both URLs reach the same gateway and the same 1683+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

No MCP client? Call it over HTTP

bash
curl -X POST https://gateway.pipeworx.io/v1/tools/opencitations_references \  -H 'Content-Type: application/json' \  -d '{"doi":"10.1371/journal.pone.0123456"}'

No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/opencitations_references. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.

Standalone (no gateway account)

This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:

json
{  "mcpServers": {    "opencitations": {      "command": "npx",      "args": ["-y", "@pipeworx/mcp-opencitations"]    }  }}

Or run it directly to confirm it starts:

bash
npx -y @pipeworx/mcp-opencitations

It speaks MCP over stdin/stdout and answers initialize/tools/list/tools/call for only this pack's tools — none of the shared meta-tools the gateway connection above adds. Same source, same tools, no ask_pipeworx routing.

Using with ask_pipeworx

Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:

ask_pipeworx({ question: "your question about Opencitations data" })

The gateway picks the right tool and fills the arguments automatically.

More

License

MIT

Source: README.md at commit 7cfcb12

Tools

0
Tool metadata has not been indexed yet.

Version history

3
  1. v0.1.2LatestSep 27, 2026
  2. v0.1.1Sep 25, 2026
  3. v0.1.0Sep 16, 2026