Data · Local MCP server
CiteNexus
Search scholarly sources, verify references, and export citations with traceable evidence.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.akougkas/cite-nexus-mcp- Version
- 0.2.2
- Status
- Active
- Category
- data
- Transport
- stdio (local process)
- Package
- PyPI
- Published
- 2026-09-17
- Updated
- 2026-09-17
- Publisher
- akougkas (GitHub) · 2 servers with pages here
- Namespace
- Namespace verified by the MCP Registry via GitHub (github.com/akougkas) · how
- Website
- github.com/akougkas/cite-nexus-mcp
- Repository
- github.com/akougkas/cite-nexus-mcp
- Source
- Registry API entry
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| PyPIruntime: uvx | cite-nexus-mcp | 0.2.2 | stdio |
How to connect CiteNexus
CiteNexus runs locally from a Python package published to PyPI: cite-nexus-mcp version 0.2.2. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Python; clients usually start it with uvx (from uv) or after pip install - the usual command is uvx cite-nexus-mcp. It reads these environment variables: CITE_NEXUS_CONTACT_EMAIL, SEMANTIC_SCHOLAR_API_KEY (secret), OPENALEX_API_KEY (secret), SERPAPI_API_KEY (secret), SCOPUS_API_KEY (secret), SCOPUS_INSTTOKEN (secret), WOS_API_KEY (secret) and UNPAYWALL_EMAIL; set them in the client's configuration for this server.
In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):
{
"mcpServers": {
"cite-nexus-mcp": {
"command": "uvx",
"args": [
"cite-nexus-mcp"
],
"env": {
"CITE_NEXUS_CONTACT_EMAIL": "<value>",
"SEMANTIC_SCHOLAR_API_KEY": "<secret>",
"OPENALEX_API_KEY": "<secret>",
"SERPAPI_API_KEY": "<secret>",
"SCOPUS_API_KEY": "<secret>",
"SCOPUS_INSTTOKEN": "<secret>",
"WOS_API_KEY": "<secret>",
"UNPAYWALL_EMAIL": "<value>"
}
}
}
}Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect
More from akougkas (GitHub)
| Server | Runs |
|---|---|
| ZulipChat MCP ServerZulipChat MCP: Connect AI to Zulip with 60+ tools for messaging, streams, events, and analytics. | Local · stdio |
More data servers
| Server | Runs |
|---|---|
| Citedy SEO AgentAI marketing: SEO articles, trend scouting, competitor analysis, social media, lead magnets. | Remote · HTTPLive check: sign-in required |
| CiteHawkAI-search visibility (GEO) analytics: brand scores, competitor rankings, recommendations, evidence. | Remote · HTTPLive check: sign-in required |
| CitelyRead-only GEO data: which AI assistants mention a brand and cite its domain. | Remote · HTTPLive check: sign-in required |
| CiteMeSearch papers, format citations in 60 styles, and verify bibliographies against scholarly sources. | Remote · HTTPLive check: ✓ handshake |
| Citevana AI visibility toolsFree MCP tools for AI-search visibility: crawler checks, page audits, and llms.txt generation. | Remote · HTTPLive check: ✓ handshake |
| CitlyzeRead-only access to your Citlyze workspace: AI search visibility, citations, and recommendations. | Remote · HTTPLive check: sign-in required |
| Cituna MCPTrack how 7 AI engines cite your brand, daily, with live Google Search Console. | Remote & Local · HTTP, stdioLive check: sign-in required |
| Civic Library MCPUS civic & property data: geocoding, census tracts, Opportunity Zones, FEMA flood zones. | Local · stdio |