MCP-DBLP
A Model Context Protocol (MCP) server that gives Large Language Models access to the DBLP computer science bibliography (accompanying paper published at ).
Potencialize seu agente
Instalação do publicador. Não é um endpoint do PlugMCP.
Host a copy with our keys and logs.
Ainda não há uma versão empacotada no registro. Siga o README do repositório.
URL remota ou um comando na sua máquina? Como as duas instalações diferem
Rodar no PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
AbrirDo publicador
A Model Context Protocol (MCP) server that gives Large Language Models access to the DBLP computer science bibliography (accompanying paper published at ).
A Model Context Protocol (MCP) server that provides access to the DBLP computer science bibliography database for Large Language Models.
MCP-DBLP lets an LLM search DBLP through the Model Context Protocol and build a BibTeX file from the results. The model chooses the papers and the citation keys; the server writes the entries from DBLP's data, so the model never rewrites bibliographic fields.
Since version 2.0, MCP-DBLP works from a local copy of DBLP instead of the dblp.org web API, which now blocks automated clients. On first start the server downloads the local index, a prebuilt SQLite index of the monthly DBLP dump (about 1.3 GB, see The local DBLP index). After that, all searches run locally, without rate limits.
and and or (no parentheses), filtered by year and venue.bib export on dblp.org except for the time of day in the timestamp field, and titles also brace words with inner capitals ({CaDiCaL}, {DRUP}-based) so that bibliography styles do not lowercase them.bib file, written by the servermcp-dblp-index updateProvide feedback to the author via this form.
Run:
claude mcp add mcp-dblp -- uvx mcp-dblp
Add to your Claude Desktop configuration file:
~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.json{
"mcpServers": {
"mcp-dblp": {
"command": "uvx",
"args": ["mcp-dblp"]
}
}
}
git clone https://github.com/szeider/mcp-dblp.git
cd mcp-dblp
uv venv && source .venv/bin/activate
uv pip install -e .
Then configure Claude Desktop with:
{
"mcpServers": {
"mcp-dblp": {
"command": "uv",
"args": ["--directory", "/path/to/mcp-dblp/", "run", "mcp-dblp"]
}
}
}
DBLP publishes all of its data as a monthly XML dump under the CC0 license. The companion repository mcp-dblp-index builds the local index from each dump and publishes it as a GitHub release.
First start. If no local index is installed, the server downloads the current release in the background (about 1.3 GB, unpacked to 4.2 GB). This takes about 2 minutes at 100 Mbit/s and about 9 minutes at 20 Mbit/s. Meanwhile, each tool call waits up to 40 seconds for the index and then answers with the download progress, so the first search takes longer than usual. An interrupted download resumes where it stopped.
Updates. A new local index is released every month. The installed one changes only when you update it:
uvx --from mcp-dblp mcp-dblp-index update
The old index keeps serving until the new one is installed. Papers added to DBLP after the release date are not in the index until the next release.
Command line. mcp-dblp-index manages the index:
Environment variables. Set them in the server's environment; in Claude Desktop, use the env field of the server entry:
{
"mcpServers": {
"mcp-dblp": {
"command": "uvx",
"args": ["mcp-dblp"],
"env": { "MCP_DBLP_HOME": "/Volumes/Data/mcp-dblp" }
}
}
}
Usage instructions are delivered to the model with the first answer of each session. See instructions_prompt.md.
Search DBLP for publications. All query words must occur in the title, the author names or the venue (case and accents do not matter). Each result shows its DBLP key and a Matched: line that says where each query word was found, for example szeider = author 2 of 3.
Parameters:
query (string, required): The search words. or separates alternatives (no parentheses), "quoted phrases" match adjacent words, the field prefixes author:, title:, venue: and year: apply to the next word or phrase, and a 4-digit year restricts the results to that year. Example: author:Vaswani title:attention 2017max_results (integer, optional): Maximum number of publications to return. Default is 10year_from (integer, optional): Lower bound for publication yearyear_to (integer, optional): Upper bound for publication yearvenue_filter (string, optional): Case-insensitive substring filter for publication venues (e.g., 'iclr')include_bibtex (boolean, optional): Whether to include BibTeX entries in the results. Default is falseFind publications by title, also when the title is misspelled or only its beginning is known. Results are ranked by title similarity and labelled "same title", "title contains the query" or "similar title".
Parameters:
title (string, required): Full or partial title of the publication (case-insensitive)similarity_threshold (number, required): A float between 0 and 1 where 1.0 means an exact matchmax_results (integer, optional): Maximum number of publications to return. Default is 10year_from (integer, optional): Lower bound for publication yearyear_to (integer, optional): Upper bound for publication yearvenue_filter (string, optional): Case-insensitive substring filter for publication venuesinclude_bibtex (boolean, optional): Whether to include BibTeX entries in the results. Default is falseList an author's publications, newest first. The name is matched fuzzily. DBLP tells namesakes apart by a number ("Wei Wang 0010"); the answer names the DBLP person listed and the other persons with a matching name.
Parameters:
author_name (string, required): Full author name, optionally with DBLP's number (case and accents do not matter)similarity_threshold (number, required): A float between 0 and 1 where 1.0 means an exact matchmax_results (integer, optional): Maximum number of publications to return. Default is 20include_bibtex (boolean, optional): Whether to include BibTeX entries in the results. Default is falseyear_from (integer, optional): Only publications from this year onyear_to (integer, optional): Only publications up to this yearLook up a venue: its name, acronym, type (conference or journal), DBLP page, number of publications, and year range.
Parameters:
venue_name (string, required): A conference acronym ('IJCAI'), DBLP's journal abbreviation ('J. ACM') or a journal's full name ('Journal of the ACM')Add a BibTeX entry to the collection for later export.
Parameters:
dblp_key (string, required): The DBLP key from search results (e.g., "conf/nips/VaswaniSPUJGKP17"); DBLP:KEY and the biburl of a DBLP entry (https://dblp.org/rec/KEY.bib) work toocitation_key (string, required): The citation key to use in the .bib file (e.g., "Vaswani2017")Behavior:
The server renders every entry from DBLP's data; the model chooses only the citation key and never edits the entry. A key missing from the local index is looked up on dblp.org, which currently blocks automated clients, so such a call returns an error and leaves the collection unchanged.
Export all collected BibTeX entries to a .bib file.
Parameters:
path (string, required): Absolute path for the .bib file (e.g., "/path/to/refs.bib"); a leading ~ is expanded. Relative paths are rejected.Behavior:
add_bibtex_entry to the specified pathChoose which dblp.org host the web fallback uses: keys missing from the local index, or all requests with MCP_DBLP_INDEX=http. Searches with the local index never contact dblp.org, and dblp.org currently blocks automated clients, so this tool is rarely useful.
Parameters:
host (string, required): dblp.org, dblp.uni-trier.de, or dblp.dagstuhl.de; other hosts are rejectedOur exploration focuses on two types of explanation problems, abductive and contrastive, in local and global contexts (Marques-Silva 2023). Abductive explanations (Ignatiev, Narodytska, and Marques-Silva 2019), corresponding to prime-implicant explanations (Shih, Choi, and Darwiche 2018) and sufficient reason explanations (Darwiche and Ji 2022), clarify specific decision-making instances, while contrastive explanations (Miller 2019; Ignatiev et al. 2020), corresponding to necessary reason explanations (Darwiche and Ji 2022), make explicit the reasons behind the non-selection of alternatives. Conversely, global explanations (Ribeiro, Singh, and Guestrin 2016; Ignatiev, Narodytska, and Marques-Silva 2019) aim to unravel models' decision patterns across various inputs.
Our exploration focuses on two types of explanation problems, abductive and contrastive, in local and global contexts \cite{MarquesSilvaI23}. Abductive explanations \cite{IgnatievNM19}, corresponding to prime-implicant explanations \cite{ShihCD18} and sufficient reason explanations \cite{DarwicheJ22}, clarify specific decision-making instances, while contrastive explanations \cite{Miller19,IgnatievNA020}, corresponding to necessary reason explanations \cite{DarwicheJ22}, make explicit the reasons behind the non-selection of alternatives. Conversely, global explanations \cite{Ribeiro0G16,IgnatievNM19} aim to unravel models' decision patterns across various inputs.
export_bibtex answers Exported 7 references to /path/to/refs.bib and writes:
@article{MarquesSilvaI23,
author = {Jo{\~{a}}o Marques{-}Silva and
Alexey Ignatiev},
title = {No silver bullet: interpretable {ML} models must be explained},
journal = {Frontiers Artif. Intell.},
volume = {6},
year = {2023},
url = {https://doi.org/10.3389/frai.2023.1128212},
doi = {10.3389/FRAI.2023.1128212},
timestamp = {Tue, 07 May 2024 00:00:00 +0200},
biburl = {https://dblp.org/rec/journals/frai/MarquesSilvaI23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{IgnatievNM19,
author = {Alexey Ignatiev and
Nina Narodytska and
Jo{\~{a}}o Marques{-}Silva},
title = {Abduction-Based Explanations for Machine Learning Models},
booktitle = {The Thirty-Third {AAAI} Conference on Artificial Intelligence, {AAAI}
2019, The Thirty-First Innovative Applications of Artificial Intelligence
Conference, {IAAI} 2019, The Ninth {AAAI} Symposium on Educational
Advances in Artificial Intelligence, {EAAI} 2019, Honolulu, Hawaii,
USA, January 27 - February 1, 2019},
pages = {1511--1519},
publisher = {{AAAI} Press},
year = {2019},
url = {https://doi.org/10.1609/aaai.v33i01.33011511},
doi = {10.1609/AAAI.V33I01.33011511},
timestamp = {Mon, 04 Sep 2023 00:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/IgnatievNM19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{ShihCD18,
author = {Andy Shih and
Arthur Choi and
Adnan Darwiche},
editor = {J{\'{e}}r{\^{o}}me Lang},
title = {A Symbolic Approach to Explaining Bayesian Network Classifiers},
booktitle = {Proceedings of the Twenty-Seventh International Joint Conference on
Artificial Intelligence, {IJCAI} 2018, July 13-19, 2018, Stockholm,
Sweden},
pages = {5103--5111},
publisher = {ijcai.org},
year = {2018},
url = {https://doi.org/10.24963/ijcai.2018/708},
doi = {10.24963/IJCAI.2018/708},
timestamp = {Tue, 20 Aug 2019 00:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ijcai/ShihCD18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DarwicheJ22,
author = {Adnan Darwiche and
Chunxi Ji},
title = {On the Computation of Necessary and Sufficient Explanations},
booktitle = {Thirty-Sixth {AAAI} Conference on Artificial Intelligence, {AAAI}
2022, Thirty-Fourth Conference on Innovative Applications of Artificial
Intelligence, {IAAI} 2022, The Twelveth Symposium on Educational Advances
in Artificial Intelligence, {EAAI} 2022 Virtual Event, February 22
- March 1, 2022},
pages = {5582--5591},
publisher = {{AAAI} Press},
year = {2022},
url = {https://doi.org/10.1609/aaai.v36i5.20498},
doi = {10.1609/AAAI.V36I5.20498},
timestamp = {Wed, 18 Mar 2026 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/aaai/DarwicheJ22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{Miller19,
author = {Tim Miller},
title = {Explanation in artificial intelligence: Insights from the social sciences},
journal = {Artif. Intell.},
volume = {267},
pages = {1--38},
year = {2019},
url = {https://doi.org/10.1016/j.artint.2018.07.007},
doi = {10.1016/J.ARTINT.2018.07.007},
timestamp = {Sun, 07 Dec 2025 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/ai/Miller19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{IgnatievNA020,
author = {Alexey Ignatiev and
Nina Narodytska and
Nicholas Asher and
Jo{\~{a}}o Marques{-}Silva},
editor = {Matteo Baldoni and
Stefania Bandini},
title = {From Contrastive to Abductive Explanations and Back Again},
booktitle = {AIxIA 2020 - Advances in Artificial Intelligence - XIXth International
Conference of the Italian Association for Artificial Intelligence,
Virtual Event, November 25-27, 2020, Revised Selected Papers},
series = {Lecture Notes in Computer Science},
volume = {12414},
pages = {335--355},
publisher = {Springer},
year = {2020},
url = {https://doi.org/10.1007/978-3-030-77091-4\_21},
doi = {10.1007/978-3-030-77091-4\_21},
timestamp = {Tue, 15 Jun 2021 00:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aiia/IgnatievNA020.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{Ribeiro0G16,
author = {Marco T{\'{u}}lio Ribeiro and
Sameer Singh and
Carlos Guestrin},
editor = {Balaji Krishnapuram and
Mohak Shah and
Alexander J. Smola and
Charu C. Aggarwal and
Dou Shen and
Rajeev Rastogi},
title = {"Why Should {I} Trust You?": Explaining the Predictions of Any Classifier},
booktitle = {Proceedings of the 22nd {ACM} {SIGKDD} International Conference on
Knowledge Discovery and Data Mining, San Francisco, CA, USA, August
13-17, 2016},
pages = {1135--1144},
publisher = {{ACM}},
year = {2016},
url = {https://doi.org/10.1145/2939672.2939778},
doi = {10.1145/2939672.2939778},
timestamp = {Sun, 01 Feb 2026 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/kdd/Ribeiro0G16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
MCP-DBLP is a research prototype. Use it at your own risk.
This project is licensed under the MIT License. See the LICENSE file for details.
A Model Context Protocol (MCP) server that provides access to the DBLP computer science bibliography database for Large Language Models.
Ferramentas
Ainda não há lista de ferramentas. Servidores remotos recebem uma após a primeira verificação de saúde.
Perguntas frequentes
Copie nesta página a configuração stdio para Cursor, Claude Desktop, Claude Code ou VS Code. Ela usa a instalação do publicador, não um proxy do PlugMCP.
Este registro não lista nenhuma variável de ambiente obrigatória.
MCP Dblp roda localmente via stdio.
Última verificação: 2026-10-28. A Model Context Protocol (MCP) server that provides access to the DBLP computer science bibliography database for Large Language Models.