{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:A6S2DVCOVTLBMMS4ERBHROVYZ6","short_pith_number":"pith:A6S2DVCO","schema_version":"1.0","canonical_sha256":"07a5a1d44eacd616325c244278bab8cf9c9273c7bcc92a5acdfe13fc2b3631e3","source":{"kind":"arxiv","id":"2506.05364","version":2},"attestation_state":"computed","paper":{"title":"Survey of LLM Agent Communication with MCP: A Software Design Pattern Centric Review","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Anjana Sarkar, Soumyendu Sarkar","submitted_at":"2025-05-26T09:11:17Z","abstract_excerpt":"This survey investigates how classical software design patterns can enhance the reliability and scalability of communication in Large Language Model (LLM)-driven agentic AI systems, focusing particularly on the Model Context Protocol (MCP). It examines the foundational architectures of LLM-based agents and their evolution from isolated operation to sophisticated, multi-agent collaboration, addressing key communication hurdles that arise in this transition. The study revisits well-established patterns, including Mediator, Observer, Publish-Subscribe, and Broker, and analyzes their relevance in "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.05364","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-05-26T09:11:17Z","cross_cats_sorted":[],"title_canon_sha256":"5ba739dceb5df39f6ec94d81796e5c6f94549b4338e374b74032808ccfe33c1a","abstract_canon_sha256":"9561bbd814d52d84ee3b6ce0f3df537813f1716bcf8b8499d195e2c70fb3f5ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:04.743449Z","signature_b64":"P2nvU/vSfuH2waMuRO9FyqRv3tkZ150etdIryzboZARYYkYeuF1enypuR3H4eb21wGlJcwrq+eyLk0WgioSXCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07a5a1d44eacd616325c244278bab8cf9c9273c7bcc92a5acdfe13fc2b3631e3","last_reissued_at":"2026-05-25T02:01:04.742810Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:04.742810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Survey of LLM Agent Communication with MCP: A Software Design Pattern Centric Review","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Anjana Sarkar, Soumyendu Sarkar","submitted_at":"2025-05-26T09:11:17Z","abstract_excerpt":"This survey investigates how classical software design patterns can enhance the reliability and scalability of communication in Large Language Model (LLM)-driven agentic AI systems, focusing particularly on the Model Context Protocol (MCP). It examines the foundational architectures of LLM-based agents and their evolution from isolated operation to sophisticated, multi-agent collaboration, addressing key communication hurdles that arise in this transition. The study revisits well-established patterns, including Mediator, Observer, Publish-Subscribe, and Broker, and analyzes their relevance in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05364","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.05364/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.05364","created_at":"2026-05-25T02:01:04.742895+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.05364v2","created_at":"2026-05-25T02:01:04.742895+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05364","created_at":"2026-05-25T02:01:04.742895+00:00"},{"alias_kind":"pith_short_12","alias_value":"A6S2DVCOVTLB","created_at":"2026-05-25T02:01:04.742895+00:00"},{"alias_kind":"pith_short_16","alias_value":"A6S2DVCOVTLBMMS4","created_at":"2026-05-25T02:01:04.742895+00:00"},{"alias_kind":"pith_short_8","alias_value":"A6S2DVCO","created_at":"2026-05-25T02:01:04.742895+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2512.06556","citing_title":"Semantic Attacks on Tool-Augmented LLMs: Securing the Model Context Protocol Against Descriptor-Level Manipulation","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19369","citing_title":"When to Answer and When to Defer: A Decision Framework for Reliable Code Predictions","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2508.07407","citing_title":"A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems","ref_index":83,"is_internal_anchor":true},{"citing_arxiv_id":"2604.13064","citing_title":"Red Skills or Blue Skills? A Dive Into Skills Published on ClawHub","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A6S2DVCOVTLBMMS4ERBHROVYZ6","json":"https://pith.science/pith/A6S2DVCOVTLBMMS4ERBHROVYZ6.json","graph_json":"https://pith.science/api/pith-number/A6S2DVCOVTLBMMS4ERBHROVYZ6/graph.json","events_json":"https://pith.science/api/pith-number/A6S2DVCOVTLBMMS4ERBHROVYZ6/events.json","paper":"https://pith.science/paper/A6S2DVCO"},"agent_actions":{"view_html":"https://pith.science/pith/A6S2DVCOVTLBMMS4ERBHROVYZ6","download_json":"https://pith.science/pith/A6S2DVCOVTLBMMS4ERBHROVYZ6.json","view_paper":"https://pith.science/paper/A6S2DVCO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.05364&json=true","fetch_graph":"https://pith.science/api/pith-number/A6S2DVCOVTLBMMS4ERBHROVYZ6/graph.json","fetch_events":"https://pith.science/api/pith-number/A6S2DVCOVTLBMMS4ERBHROVYZ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A6S2DVCOVTLBMMS4ERBHROVYZ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A6S2DVCOVTLBMMS4ERBHROVYZ6/action/storage_attestation","attest_author":"https://pith.science/pith/A6S2DVCOVTLBMMS4ERBHROVYZ6/action/author_attestation","sign_citation":"https://pith.science/pith/A6S2DVCOVTLBMMS4ERBHROVYZ6/action/citation_signature","submit_replication":"https://pith.science/pith/A6S2DVCOVTLBMMS4ERBHROVYZ6/action/replication_record"}},"created_at":"2026-05-25T02:01:04.742895+00:00","updated_at":"2026-05-25T02:01:04.742895+00:00"}