{"id":"https://openalex.org/W4415309747","doi":"https://doi.org/10.48550/arxiv.2507.12806","title":"MCPEval: Automatic MCP-based Deep Evaluation for AI Agent Models","display_name":"MCPEval: Automatic MCP-based Deep Evaluation for AI Agent Models","publication_year":2025,"publication_date":"2025-07-17","ids":{"openalex":"https://openalex.org/W4415309747","doi":"https://doi.org/10.48550/arxiv.2507.12806"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2507.12806","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.12806","pdf_url":"https://arxiv.org/pdf/2507.12806","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.12806","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100321254","display_name":"Zhiwei Liu","orcid":"https://orcid.org/0000-0003-4241-0326"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Liu, Zhiwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058194829","display_name":"Jielin Qiu","orcid":"https://orcid.org/0000-0002-7384-1324"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiu, Jielin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100437641","display_name":"Shiyu Wang","orcid":"https://orcid.org/0009-0005-2275-0712"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Shiyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100461787","display_name":"Jianguo Zhang","orcid":"https://orcid.org/0000-0002-0009-0574"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jianguo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037613999","display_name":"Zuxin Liu","orcid":"https://orcid.org/0000-0001-7412-5074"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Zuxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111227899","display_name":"Roshan Ram","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ram, Roshan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101905561","display_name":"Haolin Chen","orcid":"https://orcid.org/0000-0003-1791-6560"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Haolin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026898193","display_name":"Weiran Yao","orcid":"https://orcid.org/0000-0002-6570-3888"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao, Weiran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063103006","display_name":"Shelby Heinecke","orcid":"https://orcid.org/0000-0002-8831-0753"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heinecke, Shelby","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042646536","display_name":"Silvio Savarese","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Savarese, Silvio","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100751566","display_name":"Huan Wang","orcid":"https://orcid.org/0000-0002-1403-5314"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Huan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5032046813","display_name":"Caiming Xiong","orcid":"https://orcid.org/0000-0003-0349-8628"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiong, Caiming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5100321254"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12205","display_name":"Time Series Analysis and Forecasting","score":0.3644999861717224,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12205","display_name":"Time Series Analysis and Forecasting","score":0.3644999861717224,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10820","display_name":"Fuzzy Logic and Control Systems","score":0.3643999993801117,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.3605000078678131,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6061999797821045},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6050999760627747},{"id":"https://openalex.org/keywords/protocol","display_name":"Protocol (science)","score":0.6031000018119812},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5676000118255615},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.565500020980835},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4058000147342682},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3693999946117401}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8026999831199646},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6061999797821045},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6050999760627747},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.6031000018119812},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5676000118255615},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.565500020980835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5641000270843506},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4251999855041504},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4058000147342682},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3693999946117401},{"id":"https://openalex.org/C74072328","wikidata":"https://www.wikidata.org/wiki/Q1142726","display_name":"Intelligent agent","level":2,"score":0.3547999858856201},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3125999867916107},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.3107999861240387},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29030001163482666},{"id":"https://openalex.org/C3018395757","wikidata":"https://www.wikidata.org/wiki/Q1379672","display_name":"Evaluation methods","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2791999876499176},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.26019999384880066},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2507.12806","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.12806","pdf_url":"https://arxiv.org/pdf/2507.12806","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.12806","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.12806","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.12806","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.12806","pdf_url":"https://arxiv.org/pdf/2507.12806","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"rapid":[1],"rise":[2],"of":[3,49],"Large":[4],"Language":[5],"Models":[6],"(LLMs)-based":[7],"intelligent":[8],"agents":[9,51],"underscores":[10],"the":[11],"need":[12],"for":[13],"robust,":[14],"scalable":[15],"evaluation":[16,48,70],"frameworks.":[17],"Existing":[18],"methods":[19],"rely":[20],"on":[21],"static":[22],"benchmarks":[23],"and":[24,46,64,94],"labor-intensive":[25],"data":[26],"collection,":[27],"limiting":[28],"practical":[29],"assessment.":[30],"We":[31,86],"introduce":[32],"MCPEval,":[33],"an":[34],"open-source":[35],"Model":[36],"Context":[37],"Protocol":[38],"(MCP)-based":[39],"framework":[40],"that":[41],"automates":[42],"end-to-end":[43],"task":[44],"generation":[45],"deep":[47],"LLM":[50,96],"across":[52,74],"diverse":[53],"domains.":[54],"MCPEval":[55,89],"standardizes":[56],"metrics,":[57],"seamlessly":[58],"integrates":[59],"with":[60],"native":[61],"agent":[62,97],"tools,":[63],"eliminates":[65],"manual":[66],"effort":[67],"in":[68,81],"building":[69],"pipelines.":[71],"Empirical":[72],"results":[73],"five":[75],"real-world":[76],"domains":[77],"show":[78],"its":[79],"effectiveness":[80],"revealing":[82],"nuanced,":[83],"domain-specific":[84],"performance.":[85],"publicly":[87],"release":[88],"https://github.com/SalesforceAIResearch/MCPEval":[90],"to":[91],"promote":[92],"reproducible":[93],"standardized":[95],"evaluation.":[98]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-05-01T08:36:08.643496","created_date":"2025-10-18T00:00:00"}