CiteNexus MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPENAI_MODEL | No | Optional override for OpenAI model (e.g., llama3) | |
| SERP_API_KEY | Yes | Your SerpAPI key to query Google Scholar | |
| OPENAI_API_KEY | No | Optional OpenAI API key for fallback formatting | |
| OPENAI_API_BASE | No | Optional override for OpenAI API base URL (e.g., for local models) |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| batch-citationsA | Resolve and export up to 20 identifiers, preserving order and per-item failures. Reports progress; no durable background task is created. |
| enhance-citationA | Normalize BibTeX formatting while preserving supplied metadata. Does not invent authors, awards or keywords. Use verify-citation to check facts. |
| find-open-accessA | Find source-reported open-access locations, with optional Unpaywall enrichment. Returns links and licenses without downloading full texts. |
| find-scholar-idA | Legacy Google Scholar discovery via paid SerpAPI or SearchApi. Returns candidates with namespaced cluster IDs; the first result is not identity proof. Requires SERPAPI_API_KEY or SEARCHAPI_API_KEY. |
| get-citationA | Resolve a DOI or namespaced ID and export deterministic BibTeX, RIS or CSL-JSON with provenance and missing-field warnings. Legacy scholar_id remains accepted. |
| list-providersA | List sources, access tiers, configured availability, supported operations and setup variables. Does not call vendors or expose secrets. |
| paper-metricsB | Retrieve observed citation counts by provider and index, never an estimated impact factor or sample length. Select multiple providers to compare coverage. |
| related-papersA | Page through citing papers or references in one provider's graph. Supports Semantic Scholar, Europe PMC, OpenAlex, SerpAPI, and SearchApi citations. Offset must be a multiple of limit. |
| resolve-paperA | Resolve a DOI, arXiv ID, PMID, PMCID, OpenAlex, Semantic Scholar, Scholar, Scopus or WOS ID. Validates returned identifiers; use search-papers for titles. |
| search-papersA | Search scholarly sources concurrently (defaults: Crossref, DataCite, Europe PMC). Limit is per provider. Page one source at a time using next_offsets, or next_cursors as cursor for Europe PMC, with the same query and limit. Filters apply to fetched pages. Partial failures remain visible. detail=compact omits per-field field_sources; use full or resolve-paper for them. |
| verify-citationA | Verify an identifier or single BibTeX entry against sources and compare supplied title/year. Title-only input returns ambiguous candidates. Provider outages are distinct from missing records. Does not validate scientific claims. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| literature-review | Plan a traceable literature search with explicit scope and evidence boundaries. |
| bibliography-audit | Audit supplied references without replacing uncertain matches silently. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| provider_resource | Provider catalog and credential configuration status, without secret values. |
| methodology_resource | Evidence, provenance, deduplication and citation integrity policy. |
| workflows_resource | Discovery, bibliography auditing, evidence tables and open-access workflows. |
TDQS
Scored across 11 tools
Most tools target clearly distinct actions such as searching, resolving, exporting, verifying, and enriching citations. Overlaps exist between get-citation and resolve-paper for identifier resolution, and between find-scholar-id and search-papers for discovery, but the descriptions provide enough distinction to guide selection.
All names use kebab-case consistently, which is the dominant convention here. Most follow a verb_noun pattern (find-open-access, resolve-paper, verify-citation), while a few are noun phrases (paper-metrics, related-papers), creating minor deviation but still readable and predictable.
With 11 tools, the set is well-scoped for a scholarly citation and metadata server. Each tool covers a meaningful operation such as search, resolve, export, verify, metrics, or provider listing, without excessive surface area.
The surface covers discovery, identifier resolution, citation export, verification, open-access lookup, metrics, and related-paper traversal. Minor gaps remain, such as no dedicated full-text retrieval or citation-style configuration beyond BibTeX, RIS, and CSL-JSON, but core workflows are well supported.