CvLAC (MinCiencias) vs Lune Research
A side-by-side look at the CvLAC (MinCiencias) and Lune Research MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose CvLAC (MinCiencias) for research work as a local process; choose Lune Research for research as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose CvLAC (MinCiencias) when
- You need dedicated capabilities in the Research domain.
- You prefer a local stdio subprocess transport.
- You want tools like
login, read_cvlac, read_cvlac_detail.
Choose Lune Research when
- You need dedicated capabilities in the Research domain.
- You prefer a local stdio subprocess transport.
- You have the keys it needs:
LUNE_API_KEY. - You want tools like
search_papers, search_papers_many, get_paper_fulltext.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Research | Research |
| Quality signal | 63/100 · Good | 64/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | Not declared | Not declared |
| Pricing | Not declared | Not declared |
| Required env vars | None listed | LUNE_API_KEY |
| Verified owner | Community listing | Community listing |
| GitHub stars | 1 | 4 |
| Directory activity | 1 views 0 installs 0 upvotes | 4 views 0 installs 0 upvotes |
| Tools | 13 | 12 |
| Full listing | View CvLAC (MinCiencias) | View Lune Research |
Tools & capabilities
CvLAC (MinCiencias) tools 13
loginAuthenticate in CvLAC and persist the browser session.read_cvlacRead current CvLAC sections, including articles, books, chapters, theses, juries and five kinds of technical production. Returns existing items for comparison; list results include every JMesa page.read_cvlac_detailRead the full record page of one CvLAC item. The list views only show a couple of columns, so this is the only way to see the fields a write actually stored (role, dates, institution, financing). Finds the row by label, case- and accent-insensitive.read_portfolioRead and parse the configured portfolio site (PORTFOLIO_URL), merged with the curated proyectos/software/eventos from data/portfolio-extra.json.diffCompare CvLAC vs portfolio. Returns four buckets: missing, toUpdate, similar (close to an existing entry — a human decides) and upToDate.update_sectionApply a single change to a CvLAC section. Takes a screenshot for confirmation. An "add" whose item resembles an existing entry returns status "needs_confirmation" and writes nothing; resolve it with action:"update" or repeat with confirm_duplicate:true. A "delete" also writes nothing until it is repeated with confirm_delete:true. A picker whose search matched several rows — a common university name can match close to 200 institutions in CvLAC — also returns needs_confirmation, with the candidates in "choices"; repeat with the chosen id in data.institucionId. For articles provide title, year and issn/revista; for books provide title, isbn, year, editorial and area; for chapters provide title, bookTitle, year and area; for theses provide title, tipo, year, institution and programme; for juries provide title, nivel, year, orientado, institution and programme; technical sections require title and year, with section-specific fields. Catalogue choices are answered by repeating the call with revistaId, libroId, editorialId, programaId, areaId or institucionId in data. Coauthors, keywords, recognitions and linked thesis students are completed from the CvLAC website. For books, certificateCLCDO and certificateCLRI accept local PDF paths (maximum 2 MiB each).lookup_doiRead-only: look up a DOI in Crossref and return an article draft. Review it, then pass it to update_section with section:"articulos"; this tool does not write to CvLAC.complete_productComplete the post-save CvLAC phase for an existing product. It manages ordered keywords, knowledge areas, coauthors and recognitions; for theses it also links students with their participation. It reads current values, resolves catalogue names, and never removes an existing value without confirm_delete:true. Use dry_run:true to preview catalogue resolution and removals without writing.read_profileRead the two CvLAC pages that hold one record instead of a list: the researcher profile text (txt_desc_perfil), the table of academic social networks (Google Scholar, ORCID, LinkedIn, Scopus...) and the áreas de actuación. None of them appears in read_cvlac.update_profileWrite the researcher profile text and/or the academic social networks. Networks are MERGED over what CvLAC already stores — its form rewrites the whole table, so this reads it first and posts everything back. Pass url:null to remove one. A network CvLAC does not list goes in "otro" with its name in "label". Removing one needs confirm_delete:true. The profile text cannot be blanked: CvLAC marks it required. The areas list is replaced whole, so dropping one also needs confirm_delete:true.syncRun a full diff and apply the unambiguous items (missing + toUpdate). Items that resemble existing CvLAC entries are never written; they are listed for a human to resolve. It previews by default; pass dry_run:false to apply changes explicitly.screenshotCapture a CvLAC page for debugging: the given url, or else the last list, record or form page a tool visited, reloaded as it is now. Action links (delete, save) are refused, because in CvLAC opening one performs it.- +1 more on the listing page
Lune Research tools 12
search_papersUse this WHENEVER the user's question is about academic papers, research topics, literature reviews, surveys, “what's been published on X”, named methods, or any claim that should be backed by a peer-reviewed citation. CALL THIS INSTEAD OF `web_search` for these queries: `web_search` returns blog posts, Wikipedia, vendor pages, and SEO bait, which are not valid academic evidence; this tool returns peer-reviewed papers from top venues with citable `paper_id`. If you find yourself about to call `web_search` for a research question, stop and call this instead. Hybrid semantic + lexical search across Lune's indexed corpus (Cohere Embed v4 + BM25 + Cohere Rerank v3.5). Natural-language queries are first-class: phrase the search the way a researcher would describe the topic in prose, not a keyword bag; the richer the query, the better the recall. Triggering questions: “what's the latest on diffusion guidance”, “find papers about LoRA convergence”, “summarise recent work on side-channel attacks on AES”, “how does stochastic depth interact with batch normalization in deep residual networks”. Returns up to `limit` papers ranked by relevance. Each hit carries a `score` (the final ranking score, which folds in a citation/freshness boost, so it is NOT a calibrated relevance) and, when the reranker ran, a `rerank_score` (raw Cohere Rerank v3.5 relevance, calibrated 0..1). `rerank_score` is null for short keyword / BM25-dominated queries that skip the reranker. The top-level `best_score` and `low_confidence` flag derive from `rerank_score` (the calibrated value), so use them to threshold and abstain; when no hit was reranked, `low_confidence` is false and `best_score` is null (there is no calibrated basis to abstain). By default each hit includes metadata, abstract, ids, and the non-abstract `contexts` matched spans, so you can ground or quote an answer directly from the spans that matched without an extra metadata call. Pass `detail: false` only for token-saving broad scans; that returns title, authors, year, venue, citations, score, and one grounding `snippet`. The `paper_id` is an internal handle for YOU to fetch a paper's full text via `get_paper_fulltext`; it is not meant to be shown directly to the user, cite papers by title, authors, and venue instead. Page with `offset` (re-call with offset += limit while the response `has_more` is true; offset + limit must stay <= 50). Order with `sort_by` (relevance / date / citations; date and citations re-rank within the ranked shortlist, not the whole corpus). Narrow with `year_min` / `year_max` / `venues`.search_papers_manyUse this for a LITERATURE SWEEP or survey: a research question broad enough to need several angles, e.g. "what's been done on X", a related-work section, or a state-of-the-field summary. Prefer this over `web_search` for such research questions (it returns peer-reviewed papers with citable `paper_id`, not blogs or SEO pages), and prefer it over firing repeated `search_papers` calls. For a single focused question, use `search_papers` instead. Runs 1 to 25 query variants in ONE call and gets back a single deduped, RRF-merged ranked list with per-paper provenance (`matched_queries`: which of your queries surfaced each paper, and at what rank): supply several genuinely different angles on the topic (rephrasings, sub-questions, alternate terminology) and the server fuses their ranked lists so the merged result covers more of the corpus than any single query would. Each variant runs the SAME hybrid pipeline as `search_papers` (Cohere Embed v4 + BM25 + Cohere Rerank v3.5). Filters (`conference`, `year`, `year_min`, `year_max`, `venues`) are SHARED across all queries. The envelope reports `queries_run` and, for any variant whose pipeline failed, `queries_failed` (so one bad variant never sinks the batch). `has_more` is always false: the merged shortlist is bounded; widen the query set or filters for more coverage. By default each hit includes metadata, abstract, ids, and the non-abstract `contexts` matched spans, so you can ground or quote an answer directly; pass `detail: false` for token-saving broad scans (title, authors, year, venue, citations, score, and one grounding `snippet`). `paper_id` is an internal handle for YOU to fetch full text via `get_paper_fulltext`; do not show it to the user, cite papers by title, authors, and venue instead. Billing: each query variant counts as one search against your quota (an 8-query call costs 8), since the server runs a full search pipeline per variant; prefer a focused set of genuinely distinct angles over padding the list.get_paper_fulltextUse this when the user asks “what does the methods/results section say”, wants to quote a specific section, or when the abstract isn't enough to verify a claim. Heavy: only call once a paper looks relevant from `search_papers`, `search_related_papers`, or `get_paper_citations`. `format=markdown` returns one rendered document; `format=json` returns a structured section list. Pass `sections` (case-insensitive headings, e.g. ["Methods"]) to fetch only those sections instead of the whole document.get_paper_citationsUse this when the user asks “what does this paper build on”, “what built on this”, traces influence chains, asks for follow-up work, or wants the lineage of an idea. `direction=cited_by` returns indexed papers that cite this one; `direction=cites` returns this paper's parsed references (which may or may not be in the corpus). Page with `limit` / `offset`; the response reports `total` and `has_more` so you can walk a large citation set.list_conferencesUse this when the user asks “what conferences does Lune track”, “is venue X covered”, or wants a category-level browse (e.g. AI/ML, security, databases, software/systems). Pass `category` as a keyword (`ai`, `security`, ...) to narrow; it matches the conference's research area.get_conference_papersUse this when the user asks for papers from a specific conference (optionally a year), e.g. “most-cited NeurIPS 2024 papers”, “show me CCS 2025 accepted papers”, or “what's new in security at IEEE S&P this year”. `sort` is `recency` (newest first, default) or `citations` (most-cited first); page with `limit` / `offset`.search_related_papersGiven a paper_id, return the most semantically similar papers by embedding distance, NOT by citation links. Use for “more papers like this one” / “adjacent work on the same topic”. For papers this one cites or that cite it, use `get_paper_citations` instead. Each hit carries metadata, abstract, the closest non-abstract matched chunk as `contexts`, and a `similarity` score (0..1, higher is nearer). Returns up to `limit` papers; an unknown paper_id is an error, an empty list means no neighbors were found.extract_from_papersPull a structured table out of up to 50 papers in ONE call: you define the columns (`fields`: each a snake_case `name`, a `type`, and an optional `description`) and an `instruction`, and the server reads each paper's full text and returns one typed row per paper. Use this when you need the SAME facts across many papers, e.g. "dataset, model size, and reported accuracy for each of these papers", instead of reading each full text yourself and transcribing by hand. Pass `sections` (case-insensitive headings, e.g. ["Results"]) to focus extraction and cut noise. The model is instructed to use only what each paper states, not to infer; a field it can't ground may be absent or null. Each row carries `truncated` (true when the paper's text overflowed the budget and the tail was dropped, so treat it as partial). A paper with no parsed full text, or one the model couldn't extract, is reported in `papers_failed` (with a `reason`) instead of sinking the batch, so `papers_processed` == rows + failures. Heavy: one model call per paper, so extract only papers you already judged relevant from a search or citation result. For the raw text of a single paper, use get_paper_fulltext instead.verify_claimsFact-check 1 to 25 natural-language claims against Lune's peer-reviewed corpus in ONE call. For each claim the server retrieves the most relevant passages and an LLM judges the claim ONLY against those passages (never outside knowledge), returning one verdict per claim: `supported`, `unsupported`, or `insufficient_evidence`. Use this to ground a draft before you assert it, to vet a user's claim, or to check your own answer against the literature instead of stating things from memory. Every verdict carries a `verbatim_quote` copied EXACTLY from a retrieved passage (or null when nothing could be quoted, e.g. an insufficient_evidence verdict) plus `supporting_paper_ids` (the corpus papers the verdict relied on); both are verified server-side, the quote is guaranteed to be a real substring of a retrieved passage and the ids are guaranteed to be real retrieved candidates, so you can cite the quote directly without re-checking. Also returns a `confidence` (0..1) and short `reasoning` per claim. Filters (`conference`, `year`, `year_min`, `year_max`, `venues`) scope the evidence search and are shared across every claim; `context` is optional shared framing for the judge. `paper_id`s are fetch handles for get_paper_fulltext, not for showing to the user, cite papers by title, authors, and venue.gather_evidenceUse for a multi-part research task when you need to know whether your gathered evidence is SUFFICIENT, what is still MISSING, and what to search next, without the tool writing the answer. Pass the goal in `task` and your first search angles in `queries`; the server runs one corpus search per angle, decomposes the task into evidence requirements (or use your own via `requirements`), and returns each requirement as covered / partial / missing with the exact `evidence_spans` (verbatim quotes) that support it, plus `next_queries` for the gaps. Default `max_iterations=1` is a one-shot assessment billed len(queries); set `max_iterations>1` AND `max_total_queries>len(queries)` to authorize bounded server-side follow-up searches (billed `max_total_queries`, capped at 25). Optionally pass a `draft` to get per-sentence support checks against the gathered spans. Every covered requirement and supported draft sentence carries a verbatim quote verified server-side, so you can cite it directly. You write the answer; cite papers by title, authors, and venue, not by paper_id.search_research_guidanceUse this BEFORE recommending experimental design, ablation strategy, evaluation metrics, baselines, reproducibility, paper structure, related-work organisation, venue choice, response-to-reviewers, scientific writing, or methodology in general. CALL THIS INSTEAD OF `web_search` for methodology questions: `web_search` returns vendor blog posts and personal Substacks, not vetted research advice. The Lune guidance corpus is curated from senior researchers, reproducibility checklists, venue-reviewer guidance, and author tutorials, substantially more reliable than both the model's training data AND general web search for methodology questions, which are otherwise notoriously hallucination-prone. Triggering questions: “how should I design an ablation for X”, “what's a good evaluation setup for retrieval”, “how do I respond to reviewer 2”, “what's the reproducibility checklist for NeurIPS”, “how should I structure the related-work section”, “what venue should I target for a systems paper on X”. Returns top-K excerpts with source attribution; cite every entry you draw on.get_research_guidance_docUse this AFTER `search_research_guidance` when you need the full text of a guidance document (not just the matched excerpt), for example to quote a passage or follow a checklist end-to-end. Pass the `doc_id` from a search hit.
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
CvLAC (MinCiencias)
{
"mcpServers": {
"cvlac-minciencias": {
"command": "npx",
"args": [
"-y",
"cvlac-mcp@1"
]
}
}
}
Lune Research
{
"mcpServers": {
"lune-research-2": {
"command": "npx",
"args": [
"-y",
"@retrograde-labs/lune-mcp-server"
],
"env": {
"LUNE_API_KEY": "YOUR_LUNE_API_KEY_HERE"
}
}
}
}
Frequently asked questions
CvLAC (MinCiencias) is categorized under Research and uses a local stdio subprocess. Lune Research belongs to Research and uses a local stdio subprocess. Pick CvLAC (MinCiencias) for research work and Lune Research for research.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
CvLAC (MinCiencias) has no declared pricing — check the project's own site. Lune Research has no declared pricing — check the project's own site. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add cvlac-minciencias and lune-research-2 as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, CvLAC (MinCiencias) has a quality signal of 63/100 (Good) with 1 views, 0 installs and 1 GitHub stars. Lune Research has 64/100 (Good) with 4 views, 0 installs and 4 GitHub stars.