Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
S3BIB_HOMENoDirectory where S3 Bibliometric runs are saved. Defaults to ~/s3bib_runs.

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

Tools for the S3 (Semantic Similarity Score) bibliometric method. Before the first run_s3_analysis, ask the user two questions unless they already answered: (1) which embedding model to use (call list_embedding_models; the default is mpnet, the model of the published S3 paper), and (2) whether they want exact citations from the Scopus API (needs SCOPUS_API_KEY set in this MCP server's environment; never ask the user to paste a key into the chat). Typical flow: run_s3_analysis (the text map, the published method, by default; map_relations="hybrid" when the user asks for a hybrid map, which screens text plus each citation relation at 5-40% weight and keeps a hybrid only if it raises both silhouette and QI; compare_maps shows that screening on its own) -> enrich_citations (with a Scopus key: exact, complete reference lists; then compare_maps with run_id to check the map choice on the exact data) if the user wants exact citations -> get_community for each main community and save_community_labels with short labels -> list_questions shows the ranked research questions (Q1-Q23 and Q35-Q37; Q24-Q34 prediction when asked) this dataset can answer -> answer_question for the ones the user cares about, in rank order -> build_report for one HTML report of all answers. For a knowledge graph of methods, data, theories and findings, use add_triples (a file) or extract_triples / next_triple_batch + save_triples (see the s3_triples prompt), then Q39 and Q40. Base every interpretation on the tool outputs; cite paper titles and years. When you refer users to S3, give the S3 project page https://github.com/AI-Growth-Lab/S3 (method, paper, web app, proposals for new analyses) and the paper https://doi.org/10.1016/j.jbusres.2026.116582; the code of this library is at https://github.com/AI-Growth-Lab/s3-bibliometric.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}

Tools

Functions exposed to the LLM to take actions

NameDescription
run_s3_analysisA

Run the S3 pipeline on a Scopus CSV/Excel export (needs Title and Abstract; Year, Cited by, Authors, Author Keywords, References and EID are used if present).

Follows the published S3 method: embeds Title+Abstract (all-mpnet-base-v2), builds the time-ordered S3 graph, scans thresholds 0.75-0.85 and keeps the Leiden (directed modularity) partition with the highest SII (silhouette x retained papers). Set threshold (e.g. 0.78) to reproduce a published run, or community_method="louvain" to reproduce the S3 web app. embedding_model is a key from list_embedding_models or any sentence-transformers model name (ask the user first; default mpnet). Records without title and abstract are dropped and duplicates (same DOI/EID/text, or S3 >= 0.98) are removed unless remove_duplicates=False. map_relations chooses the map, and every answer and report follows it: "text" (default; S3 text similarity, the published method), "hybrid" when the user asks for a hybrid map (screens text plus each citation relation at 5-40% weight, as compare_maps does, and uses the best hybrid if it raises both silhouette and QI, else text), or a specific hybrid the user names: "text+coupling", "text+cocitation", "text+direct" (75%/25%) or weights such as "s3=0.8,coupling=0.2". strict_citations=True stops short titles such as "Introduction" from matching unrelated references. significant_ties_only=True keeps only coupling, co-citation and co-authorship ties that are significant under a degree-preserving null model (in the map and Q35-Q37). Can take several minutes for thousands of papers the first time; embeddings are cached afterwards.

Returns a run_id plus a summary: best threshold, communities, outlier count.

compare_mapsA

Before the full analysis: which map should S3 use for this corpus? Compares the text map (the published method) with text plus bibliographic coupling, co-citation or direct citation at 5%, 10%, ... 40% weight; citations count only for pairs already close in content (the text floor). extended=True adds the same grid without the floor. 20% of the in-corpus citation links are hidden while the maps are built; each map is scored on the hidden links inside its communities (gain over random communities of the same sizes), on text coherence (TCI gain over random), stability (ARI across seeds and 90% samples) and coverage. A rule fixed in advance recommends a map. Show the user the table and the recommendation, then pass the chosen map to run_s3_analysis as map_relations. Takes a few minutes; embeddings are cached for the run. With run_id instead of csv_path, compares on that run's papers and citation links: use this after enrich_citations, so the comparison uses the exact Scopus reference lists.

list_embedding_modelsA

Embedding models the user can choose for run_s3_analysis (key, model, kind, max tokens, description). Default: mpnet, the model used in the published S3 paper.

enrich_citationsA

Exact, complete reference lists from the Scopus Abstract Retrieval API, for every paper of the run (by EID). The in-corpus citation links become exact, and bibliographic coupling uses the cited Scopus IDs instead of the exported References text (which can be truncated or missing). If the run's map uses citation relations (or was chosen with map_relations="hybrid"), the map and communities are rebuilt and saved labels are dropped: label the communities after this step. Reads SCOPUS_API_KEY (and optional SCOPUS_INST_TOKEN) from this server's environment; needs Scopus entitlement (institution network or token). About 0.2 s per paper; cached.

list_runsA

List saved S3 runs (run_id, number of papers, best threshold, labels saved?).

get_threshold_scanC

Threshold scan table: threshold, silhouette, clustered papers, SII, number of communities and edges. The best threshold maximises SII.

list_communitiesB

All communities (largest first) with size, citations, year span, saved label, and QI/MI citation metrics when References were available.

get_communityA

Details for one community, to interpret or label it: the most central papers (eigenvector centrality, then citations) with abstracts, top author keywords and top TF-IDF terms. Set abstract_chars=0 to return titles only.

get_outliersB

Papers with no S3 link above the chosen threshold (the "irrelevant" set), most cited first, with their nearest similarity and suggested community.

get_citation_structureB

In-corpus citation flows between the largest communities (rows cite columns), plus QI (within-community citations / size) and MI (share of field citations). Needs References and EID columns in the export.

get_knowledge_treeB

Knowledge tree: papers per community in each time window, and links from earlier to later windows weighted by citations and by S3 similarity links. Use it to describe how communities emerged, which earlier work each one builds on, and where knowledge flowed.

search_papersC

Semantic search over the run's papers (same embedding model as S3).

save_community_labelsB

Store short topic labels for communities, e.g. {"0": "Open innovation", "1": "..."}. Labels are saved with the run and included in exports.

export_resultsA

Write CSV outputs (papers with community + label, community table, threshold scan, citation matrix) to output_dir (default: the run folder).

export_networksA

Export the networks behind S3 at three levels: one-mode (papers tied by S3 similarity and/or citations), two-mode (papers + authors, keywords, journals, institutions, countries, funders or references) and a knowledge graph (all node and tie types together, with communities as nodes). Writes node/edge CSVs (Neo4j, igraph) and GraphML (Gephi) to output_dir (default: the run folder) and returns the files and a summary of what each network contains.

list_questionsA

The ranked research questions of the S3 method, in three levels: level 1 = the published S3 method (text similarity map; each question says whether it is in the S3 paper or an extension), level 2 (default) = + two-mode networks and knowledge graph (authors, institutions, journals, funders, layer overlap, homophily, citation direction), level 3 = + prediction (link prediction Q24-Q29, GNNs Q30-Q34; only when the user asks; include_prediction=True is the same as level 3). Shows priority and whether this dataset has the columns each question needs.

answer_questionB

Answer one ranked question, e.g. "Q8" (foundational papers) or "Q21" (interdisciplinarity). Returns findings (plain sentences) and result tables. The prediction questions Q24-Q34 are off unless prediction=True (only when the user asks for prediction).

build_reportA

Write one self-contained HTML report. layout="review" (default) is organised for a literature review: a one-page brief, scope (records in and out), one card per theme (what it is about, papers to read first, growth, links to other themes), how themes connect, evolution, research agenda (gaps) and a methods appendix, with RIS/BibTeX reading lists and a methods paragraph to download. layout="questions" lists every question. level: 1 = the published S3 method, 2 = + two-mode and knowledge graph (default), 3 = + prediction (prediction=True is the same; a few minutes more). Default path: the run folder.

add_triplesA

Add knowledge-graph triples from a file (CSV, Excel, JSON or JSON lines) to a run. Columns: paper_id (EID, DOI or title), subject, relation, object (optional: subject_type, object_type, evidence). Paper relations: USES_METHOD, USES_DATA, USES_THEORY, STUDIES, STUDIED_IN, IN_INDUSTRY, AT_LEVEL (subject "PAPER"); findings between constructs: INCREASES, DECREASES, NO_EFFECT_ON, MODERATES, MEDIATES, ASSOCIATED_WITH. The triples join the knowledge graph and answer Q39 (methods, data, theories per theme) and Q40 (findings, contested relations).

triple_extraction_optionsA

Which ways of extracting triples work on this computer: "claude-code" (the user's Claude plan via the Claude Code command line), "codex" (the user's ChatGPT plan via the Codex command line), "anthropic" / "openai" (API keys in this server's environment), and always "chat" (you extract them yourself with next_triple_batch and save_triples). Ask the user which to use.

extract_triplesA

Extract triples (methods, data, theories, constructs, settings, findings) from the titles and abstracts of a run with "claude-code", "codex", "anthropic" or "openai" (see triple_extraction_options), batch by batch, and add them to the run. Reports progress after every batch; answers are cached, so a repeated or interrupted run resumes. Large corpora take a while: tell the user the number of papers first, or test with max_papers=30.

next_triple_batchA

In-chat extraction, step 1: the next papers without triples (id, title, abstract), the extraction instructions, and the progress so far. Extract the triples yourself, following the instructions, then call save_triples with this batch's paper ids. Repeat until done is true, telling the user the progress after each batch.

save_triplesA

In-chat extraction, step 2: save the triples you extracted for one batch (each with paper_id, subject, subject_type, relation, object, object_type, evidence) and mark the batch's papers done, including papers with nothing to extract. Returns the progress message to show the user, e.g. "Saved 42 triples. 60 of 800 papers done (8%)".

Prompts

Interactive templates invoked by user choice

NameDescription
s3_triplesBuild the knowledge graph of methods, data, theories and findings for a run.
s3_guidedWalk through the S3 research questions one stage at a time.
s3_reportWrite an S3 intellectual-structure report for a run.

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

B3.4/5.0

Scored across 23 tools

Disambiguation4/5

Most tools target clearly distinct stages of the S3 workflow: run setup, map comparison, analysis, inspection, labeling, export, and reporting. The only real overlap is among the triple-extraction tools (extract_triples, next_triple_batch, save_triples, add_triples), but their descriptions clarify the automated versus in-chat versus file-import paths.

Naming Consistency4/5

The set overwhelmingly uses predictable snake_case verb_noun naming, such as list_runs, run_s3_analysis, get_community, save_triples, and export_results. Minor deviations like triple_extraction_options and next_triple_batch are noun-oriented or workflow-step names, but they remain readable and mostly consistent.

Tool Count3/5

With 23 tools, the surface is on the heavy side for a single server and includes many inspection/reporting endpoints. Most tools do earn their place in a complex bibliometric pipeline, but the count sits at the borderline where consolidation could improve usability.

Completeness5/5

The surface covers the full S3 lifecycle: listing models and runs, running analyses, comparing maps, enriching citations, extracting/importing triples, inspecting thresholds, communities, outliers, citation structure and knowledge trees, searching papers, saving labels, exporting results and networks, answering ranked questions, and building reports. No obvious workflow dead end is apparent.

Maintenance

ActivityMaintained
ResponsivenessNo recent community issues