Skip to main content
Glama
deenesjakoruzh
szeider

MCP-DBLP

by szeider
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

MCP-DBLP

MCP Compatible License: MIT Python Version

Un servidor del Protocolo de Contexto de Modelo (MCP) que proporciona acceso a la base de datos bibliográfica de informática DBLP para Modelos de Lenguaje Extensos (artículo complementario aceptado en AI4SC @ AAAI-26).

Descripción general

El MCP-DBLP integra la API de DBLP (Digital Bibliography & Library Project) con LLMs a través del Protocolo de Contexto de Modelo, permitiendo a los modelos de IA:

  • Buscar y recuperar publicaciones académicas de la base de datos DBLP

  • Procesar citas y generar entradas BibTeX

  • Realizar coincidencias difusas en títulos de publicaciones y nombres de autores

  • Extraer y formatear información bibliográfica

  • Procesar referencias incrustadas en documentos

  • Exportación directa a BibTeX que evita el procesamiento por LLM para una máxima precisión

Related MCP server: ArXiv-MCP

Características

  • Capacidades de búsqueda integral con consultas booleanas

  • Coincidencia difusa de títulos y nombres de autores

  • Recuperación de entradas BibTeX directamente desde DBLP

  • Filtrado de publicaciones por año y lugar de publicación

  • Análisis estadístico de datos de publicaciones

  • Capacidad de exportación directa a BibTeX que evita el procesamiento por LLM para una máxima precisión

Herramientas disponibles

Nombre de la herramienta

Descripción

get_instructions

Obtener instrucciones de uso y guía de flujo de trabajo

search

Buscar publicaciones en DBLP usando consultas booleanas

fuzzy_title_search

Buscar publicaciones con coincidencia difusa de títulos

get_author_publications

Recuperar publicaciones de un autor específico

get_venue_info

Obtener información detallada sobre un lugar de publicación

add_bibtex_entry

Añadir una entrada BibTeX a la colección mediante la clave DBLP

export_bibtex

Exportar todas las entradas BibTeX recopiladas a un archivo .bib

Comentarios

Envíe sus comentarios al autor a través de este formulario.

Requisitos del sistema

  • Python 3.11+

  • uv

Instalación

Claude Code

Simplemente ejecute:

claude mcp add mcp-dblp -- uvx mcp-dblp

Claude Desktop

Añada a su archivo de configuración de Claude Desktop:

  • macOS/Linux: ~/Library/Application Support/Claude/claude_desktop_config.json

  • Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "mcp-dblp": {
      "command": "uvx",
      "args": ["mcp-dblp"]
    }
  }
}

Desde el código fuente (Desarrollo)

git clone https://github.com/szeider/mcp-dblp.git
cd mcp-dblp
uv venv && source .venv/bin/activate
uv pip install -e .

Luego configure Claude Desktop con:

{
  "mcpServers": {
    "mcp-dblp": {
      "command": "uv",
      "args": ["--directory", "/path/to/mcp-dblp/", "run", "mcp-dblp"]
    }
  }
}

Instrucciones

Las instrucciones de uso están disponibles a través de la herramienta get_instructions. Los puntos clave del flujo de trabajo se muestran en la descripción de la herramienta; llame a la herramienta para obtener detalles completos. Consulte también instructions_prompt.md.

Detalles de las herramientas

search

Busca publicaciones en DBLP usando una cadena de consulta booleana.

Parámetros:

  • query (cadena, requerido): Una cadena de consulta que puede incluir operadores booleanos 'and' y 'or' (sin distinción entre mayúsculas y minúsculas)

  • max_results (número, opcional): Número máximo de publicaciones a devolver. El valor predeterminado es 10

  • year_from (número, opcional): Límite inferior para el año de publicación

  • year_to (número, opcional): Límite superior para el año de publicación

  • venue_filter (cadena, opcional): Filtro de subcadena sin distinción entre mayúsculas y minúsculas para lugares de publicación (ej., 'iclr')

  • include_bibtex (booleano, opcional): Si se deben incluir entradas BibTeX en los resultados. El valor predeterminado es falso

fuzzy_title_search

Busca publicaciones en DBLP con coincidencia difusa de títulos.

Parámetros:

  • title (cadena, requerido): Título completo o parcial de la publicación (sin distinción entre mayúsculas y minúsculas)

  • similarity_threshold (número, requerido): Un flotante entre 0 y 1 donde 1.0 significa una coincidencia exacta

  • max_results (número, opcional): Número máximo de publicaciones a devolver. El valor predeterminado es 10

  • year_from (número, opcional): Límite inferior para el año de publicación

  • year_to (número, opcional): Límite superior para el año de publicación

  • venue_filter (cadena, opcional): Filtro de subcadena sin distinción entre mayúsculas y minúsculas para lugares de publicación

  • include_bibtex (booleano, opcional): Si se deben incluir entradas BibTeX en los resultados. El valor predeterminado es falso

get_author_publications

Recupera detalles de publicaciones para un autor específico con coincidencia difusa.

Parámetros:

  • author_name (cadena, requerido): Nombre completo o parcial del autor (sin distinción entre mayúsculas y minúsculas)

  • similarity_threshold (número, requerido): Un flotante entre 0 y 1 donde 1.0 significa una coincidencia exacta

  • max_results (número, opcional): Número máximo de publicaciones a devolver. El valor predeterminado es 20

  • include_bibtex (booleano, opcional): Si se deben incluir entradas BibTeX en los resultados. El valor predeterminado es falso

get_venue_info

Recupera información detallada sobre un lugar de publicación.

Parámetros:

  • venue_name (cadena, requerido): Nombre del lugar o abreviatura (ej., 'ICLR' o nombre completo)

add_bibtex_entry

Añade una entrada BibTeX a la colección para su posterior exportación.

Parámetros:

  • dblp_key (cadena, requerido): La clave DBLP de los resultados de búsqueda (ej., "conf/nips/VaswaniSPUJGKP17")

  • citation_key (cadena, requerido): La clave de cita a usar en el archivo .bib (ej., "Vaswani2017")

Comportamiento:

  • Obtiene la entrada BibTeX directamente de DBLP usando la clave proporcionada

  • Reemplaza la clave de cita con su clave personalizada

  • Añade a la colección de la sesión (las claves duplicadas se sobrescriben)

  • Devuelve comentarios inmediatos de éxito/fallo con el recuento de la colección

  • Permite reintentar entradas individuales fallidas

export_bibtex

Exporta todas las entradas BibTeX recopiladas a un archivo .bib.

Parámetros:

  • path (cadena, requerido): Ruta absoluta para el archivo .bib (ej., "/ruta/a/refs.bib")

Comportamiento:

  • Guarda todas las entradas añadidas mediante add_bibtex_entry en la ruta especificada

  • La extensión .bib se añade automáticamente si falta

  • Los directorios principales se crean si es necesario

  • Borra la colección después de una exportación exitosa

  • Devuelve la ruta completa al archivo guardado

  • Devuelve un error si la colección está vacía

Nota importante: Las entradas BibTeX se obtienen directamente de DBLP con una protección de tiempo de espera de 10 segundos y no son procesadas, modificadas ni alucinadas por el LLM. Esto garantiza la máxima precisión y fiabilidad de los datos bibliográficos. Solo se modifican las claves de cita según lo especificado. Si una solicitud agota el tiempo de espera, se devuelve un mensaje de error y la entrada no se añade a la colección.

Ejemplo

Texto de entrada:

Nuestra exploración se centra en dos tipos de problemas de explicación, abductivos y contrastivos, en contextos locales y globales (Marques-Silva 2023). Las explicaciones abductivas (Ignatiev, Narodytska, y Marques-Silva 2019), correspondientes a explicaciones de implicante primo (Shih, Choi, y Darwiche 2018) y explicaciones de razón suficiente (Darwiche y Ji 2022), aclaran instancias específicas de toma de decisiones, mientras que las explicaciones contrastivas (Miller 2019; Ignatiev et al. 2020), correspondientes a explicaciones de razón necesaria (Darwiche y Ji 2022), hacen explícitas las razones detrás de la no selección de alternativas. Por el contrario, las explicaciones globales (Ribeiro, Singh, y Guestrin 2016; Ignatiev, Narodytska, y Marques-Silva 2019) tienen como objetivo desentrañar los patrones de decisión de los modelos a través de diversas entradas.

Texto de salida:

Nuestra exploración se centra en dos tipos de problemas de explicación, abductivos y contrastivos, en contextos locales y globales \cite{MarquesSilvaI23}. Las explicaciones abductivas \cite{IgnatievNM19}, correspondientes a explicaciones de implicante primo \cite{ShihCD18} y explicaciones de razón suficiente \cite{DarwicheJ22}, aclaran instancias específicas de toma de decisiones, mientras que las explicaciones contrastivas \cite{Miller19}; \cite{IgnatievNA020}, correspondientes a explicaciones de razón necesaria \cite{DarwicheJ22}, hacen explícitas las razones detrás de la no selección de alternativas. Por el contrario, las explicaciones globales \cite{Ribeiro0G16}; \cite{IgnatievNM19} tienen como objetivo desentrañar los patrones de decisión de los modelos a través de diversas entradas.

Bibtex de salida

Todas las referencias se han exportado correctamente a un archivo BibTeX en: /ruta/absoluta/a/bibtex/20250305_231431.bib

@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 20:23:47 +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 12:29:24 +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 16:19:08 +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    = {Mon, 04 Sep 2023 16:50:24 +0200},
 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    = {Thu, 25 May 2023 12:52:41 +0200},
 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 17:23:54 +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    = {Fri, 25 Dec 2020 01:14:16 +0100},
 biburl       = {https://dblp.org/rec/conf/kdd/Ribeiro0G16.bib},
 bibsource    = {dblp computer science bibliography, https://dblp.org}
}

Descargo de responsabilidad

Este MCP-DBLP se encuentra en su etapa de prototipo y debe usarse con precaución. Se anima a los usuarios a experimentar, pero cualquier uso en entornos críticos es bajo su propio riesgo.

Licencia

Este proyecto está bajo la Licencia MIT - consulte el archivo LICENSE para obtener más detalles.

Available Tools

6 tools
calculate_statisticsA

Calculate statistics from a list of publication results. Arguments:

  • results (array, required): An array of publication objects, each with at least 'title', 'authors', 'venue', and 'year'. Returns a dictionary with:

  • total_publications: Total count.

  • time_range: Dictionary with 'min' and 'max' publication years.

  • top_authors: List of tuples (author, count) sorted by count.

  • top_venues: List of tuples (venue, count) sorted by count (empty venue is treated as '(empty)').

ParametersJSON Schema
NameRequiredDescriptionDefault
resultsYes

TDQS

A3.6/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It discloses the return structure (a dictionary with specific keys) and behavioral details like how empty venues are treated. However, it doesn't mention error handling, performance aspects (e.g., for large arrays), or side effects. The description adds some context but isn't comprehensive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is appropriately sized and front-loaded with the purpose, followed by structured details on arguments and returns. Every sentence earns its place by clarifying inputs and outputs, though it could be slightly more concise by integrating the argument list into the flow rather than as a separate bullet.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 1 parameter with 0% schema coverage and no output schema, the description does well by fully explaining the parameter and return values. It covers the tool's complexity adequately, though it could improve by adding usage context or error scenarios. The lack of annotations and output schema is compensated by the detailed description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate fully. It provides detailed semantics for the single parameter 'results', specifying it as an array of publication objects with required fields ('title', 'authors', 'venue', 'year'). This adds significant meaning beyond the bare schema, fully documenting the parameter's structure and expectations.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Calculate statistics from a list of publication results.' It specifies the verb ('calculate') and resource ('statistics'), but doesn't explicitly differentiate from siblings like 'search' or 'get_author_publications' which have different functions. The purpose is clear but lacks sibling comparison.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. The description doesn't mention prerequisites (e.g., needing publication data first), exclusions, or compare to siblings like 'export_bibtex' or 'get_venue_info'. Usage is implied from the purpose but not explicitly stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

export_bibtexA

Export BibTeX entries from a collection of HTML hyperlinks. Arguments:

  • links (string, required): HTML string containing one or more key links. The href attribute should contain a URL to a BibTeX file, and the link text is used as the citation key. Example input with three links: "Smith2023 Jones2022 Brown2021" Process:

  • For each link, the tool fetches the BibTeX content from the URL

  • The citation key in each BibTeX entry is replaced with the key from the link text

  • All entries are combined and saved to a .bib file with a timestamp filename Returns:

  • A message with the full path to the saved .bib file

ParametersJSON Schema
NameRequiredDescriptionDefault
linksYes

TDQS

A4.2/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes the process: fetching BibTeX content from URLs, replacing citation keys, saving to a timestamped .bib file, and returning the file path. It covers key behaviors like network fetching and file creation, though it omits details like error handling or rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with sections for Arguments, Process, and Returns, making it easy to parse. It is appropriately sized, with each sentence adding value, though it could be slightly more concise by integrating the example more seamlessly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (network fetching, file creation) and lack of annotations or output schema, the description is largely complete. It explains the process, parameter usage, and return value. However, it could improve by mentioning potential errors (e.g., invalid URLs) or file format specifics.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must fully compensate. It provides detailed semantics for the single parameter 'links', including its type, requirement, format (HTML string with <a> tags), example, and how the href and link text are used. This adds significant meaning beyond the basic schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool exports BibTeX entries from HTML hyperlinks, specifying the exact verb ('export'), resource ('BibTeX entries'), and source ('collection of HTML hyperlinks'). It distinguishes from sibling tools like 'get_author_publications' or 'search' by focusing on BibTeX extraction from links rather than general searches or author-specific queries.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage when BibTeX entries need to be exported from HTML links, but it does not explicitly state when to use this tool versus alternatives like 'fuzzy_title_search' or 'get_author_publications'. It provides an example input, which helps clarify context, but lacks explicit guidance on exclusions or prerequisites.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_author_publicationsA

Retrieve publication details for a specific author with fuzzy matching. Arguments:

  • author_name (string, required): Full or partial author name (case-insensitive).

  • similarity_threshold (number, required): A float between 0 and 1 where 1.0 means an exact match.

  • max_results (number, optional): Maximum number of publications to return. Default is 20.

  • include_bibtex (boolean, optional): Whether to include BibTeX entries in the results. Default is false. Returns a dictionary with keys: name, publication_count, publications, and stats (which includes top venues, years, and types).

ParametersJSON Schema
NameRequiredDescriptionDefault
author_nameYes
include_bibtexNo
max_resultsNo
similarity_thresholdYes

TDQS

A3.6/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It describes key behaviors like fuzzy matching, case-insensitive search, and default values for optional parameters. However, it lacks details on error handling, rate limits, authentication needs, or what happens with low similarity thresholds. The description doesn't contradict annotations, but it's incomplete for a tool with fuzzy matching and multiple parameters.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured and appropriately sized. It starts with a clear purpose statement, then lists arguments with detailed explanations, and ends with return value information. Every sentence adds value, though the return details could be slightly more concise. It's front-loaded with the core functionality.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (fuzzy matching, 4 parameters) and lack of annotations/output schema, the description does a good job of covering key aspects. It explains parameters thoroughly and outlines the return structure. However, it could benefit from more behavioral context (e.g., performance implications, error cases) to be fully complete for an agent's use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description adds significant value beyond the input schema, which has 0% description coverage. It explains each parameter's purpose: 'author_name' for full/partial name matching, 'similarity_threshold' as a float between 0-1 for match precision, 'max_results' for limiting output with a default, and 'include_bibtex' for including BibTeX entries. This compensates fully for the schema's lack of descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Retrieve publication details for a specific author with fuzzy matching.' It specifies the verb ('retrieve'), resource ('publication details'), and key behavior ('fuzzy matching'). However, it doesn't explicitly differentiate from sibling tools like 'fuzzy_title_search' or 'search', which might have overlapping functionality.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention sibling tools like 'fuzzy_title_search' (for titles) or 'search' (which might be more general), nor does it specify prerequisites or exclusions. Usage is implied by the description but not explicitly stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_venue_infoA

Retrieve detailed information about a publication venue. Arguments:

  • venue_name (string, required): Venue name or abbreviation (e.g., 'ICLR' or full name). Returns a dictionary with fields: abbreviation, name, publisher, type, and category. Note: Some fields may be empty if DBLP does not provide the information.

ParametersJSON Schema
NameRequiredDescriptionDefault
venue_nameYes

TDQS

A3.8/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It discloses that the tool retrieves data from DBLP and notes that some fields may be empty, adding useful behavioral context about data source and completeness. However, it lacks details on error handling, rate limits, or authentication needs, which are important for a read operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with clear sections for arguments and returns, and every sentence adds value. It could be slightly more front-loaded by moving the note about DBLP earlier, but overall it's efficient with minimal waste.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's low complexity (1 parameter, no output schema, no annotations), the description is reasonably complete. It covers the purpose, parameter semantics, return fields, and data source limitations. However, it could improve by mentioning error cases or when to use alternatives, slightly reducing completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description adds significant meaning beyond the input schema, which has 0% coverage. It explains the 'venue_name' parameter as accepting names or abbreviations (e.g., 'ICLR'), clarifies it's required, and provides examples, fully compensating for the schema's lack of documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'retrieve' and resource 'detailed information about a publication venue,' making the purpose specific and unambiguous. It distinguishes this tool from siblings like 'get_uthor_publications' or 'search' by focusing on venue metadata rather than author data or broader searches.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives like 'search' or 'fuzzy_title_search.' The description implies usage for venue details but lacks explicit context, prerequisites, or exclusions, leaving the agent to infer based on tool names alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 6 tool updatesv1.0.0
    • First observedcalculate_statistics
    • First observedexport_bibtex
    • First observedfuzzy_title_search
    • First observedget_author_publications
    • First observedget_venue_info
    • First observedsearch
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.1/5.0

Scored across 6 tools

Disambiguation5/5

Each tool has a clearly distinct purpose with no ambiguity: calculate_statistics processes existing results, export_bibtex handles BibTeX export, fuzzy_title_search and search provide different search methods, get_author_publications focuses on authors, and get_venue_info targets venues. The tools cover different aspects of the DBLP domain without overlap.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern with snake_case: calculate_statistics, export_bibtex, fuzzy_title_search, get_author_publications, get_venue_info, and search. The naming is predictable and readable throughout the set.

Tool Count5/5

With 6 tools, the count is well-scoped for a DBLP server, covering key operations like search, author/venue info, statistics, and BibTeX export. Each tool earns its place without feeling thin or bloated, suitable for typical academic workflows.

Completeness4/5

The tool set provides strong coverage for core DBLP operations including search, author/venue retrieval, and data export, with minor gaps such as no direct tool for updating or deleting data (though this may be intentional for a read-heavy domain). Agents can effectively navigate publication workflows with these tools.

Maintenance

ActivityMaintained
ResponsivenessUnresponsive

Resources

Related MCP Connectors

Related MCP Servers

  • Crossref MCP Server

    botanicastudios
    A
    license
    B
    quality
    D
    maintenance
    A Model Context Protocol server that enables querying the Crossref API to search for academic publications by title, author, or DOI, returning structured metadata about scholarly works.
    3
    27 npm
    4
    MIT

  • ArXiv-MCP

    kelvingao
    A
    license
    Not graded
    quality
    D
    maintenance
    A Model Context Protocol server that enables AI agents to search, retrieve, and analyze academic papers from arXiv, supporting features like keyword search, paper details retrieval, content extraction, and paper analysis.
    5
    MIT

  • Semantic Scholar MCP Server

    alperenkocyigit
    F
    license
    Not graded
    quality
    D
    maintenance
    A comprehensive Model Context Protocol server that provides AI assistants with direct access to Semantic Scholar's academic database, enabling advanced paper discovery, citation analysis, author research, and AI-powered recommendations.
    16
    -

  • harcx-mcp

    Vashistht
    A
    license
    Not graded
    quality
    D
    maintenance
    An MCP server that enables AI assistants to verify BibTeX citations and URLs against academic databases like Semantic Scholar and DBLP. It allows users to ensure bibliography accuracy and link accessibility directly within their research workflows.
    1
    MIT

Appeared in Searches