{"id":"darkroaster-pubmearch","name":"pubmearch","homepage":null,"repo_url":"https://github.com/Darkroaster/pubmearch","category":"ai-ml","subcategories":[],"tags":["mcp","pubmed","ncbi","literature-analysis","biomedical","python","research-analytics"],"what_it_does":"Provides an MCP server (Python) that queries PubMed using NCBI advanced search, saves result files, and performs analyses such as keyword hotspot frequency, keyword trends over time, publication count over time windows, and generates comprehensive reports.","use_cases":["PubMed literature retrieval with date ranges and max result limits","Identifying research hotspots by keyword frequency","Tracking changes in keyword usage over time to infer research trends","Analyzing publication volume changes across customizable time periods","Generating one-shot analytical reports from prior search results"],"not_for":["Production-grade enterprise deployments without reviewing the server’s security and error-handling behavior","Use cases requiring strict, documented rate-limit handling or guaranteed pagination semantics","Workflows that require a formal REST/GraphQL/OpenAPI contract or official SDKs"],"best_when":"You want an AI-agent-accessible MCP tool to explore PubMed research dynamics (hotspots/trends/publication counts) using NCBI advanced search syntax.","avoid_when":"You need strong guarantees around reliability (SLA, documented retries/idempotency) or you cannot provide/secure NCBI credentials and want strict credential-less operation.","alternatives":["NCBI E-utilities / ESearch+EFetch directly","Other PubMed analytics tools/libraries (e.g., bibliometrics packages)","Custom scripts using Biopython/Entrez with your own data storage and reporting"],"af_score":51.0,"security_score":50.5,"reliability_score":22.5,"package_type":"mcp_server","discovery_source":["github"],"priority":"high","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-03-30T13:42:02.993224+00:00","interface":{"has_rest_api":false,"has_graphql":false,"has_grpc":false,"has_mcp_server":true,"mcp_server_url":null,"has_sdk":false,"sdk_languages":[],"openapi_spec_url":null,"webhooks":false},"auth":{"methods":["Environment variables: NCBI_USER_EMAIL","Environment variables: NCBI_USER_API_KEY"],"oauth":false,"scopes":false,"notes":"Authentication is for NCBI usage (email + API key) via environment variables, not for an externally secured API/auth scheme."},"pricing":{"model":null,"free_tier_exists":false,"free_tier_limits":null,"paid_tiers":[],"requires_credit_card":false,"estimated_workload_costs":null,"notes":"No pricing information provided; likely incurs NCBI/compute costs depending on usage."},"requirements":{"requires_signup":false,"requires_credit_card":false,"domain_verification":false,"data_residency":[],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":51.0,"security_score":50.5,"reliability_score":22.5,"mcp_server_quality":70.0,"documentation_accuracy":55.0,"error_message_quality":0.0,"error_message_notes":null,"auth_complexity":80.0,"rate_limit_clarity":20.0,"tls_enforcement":60.0,"auth_strength":55.0,"scope_granularity":20.0,"dependency_hygiene":45.0,"secret_handling":70.0,"security_notes":"Uses NCBI email/API key via environment variables, which is generally better than hard-coding. However, TLS, logging/redaction behavior, and detailed threat model are not documented. Scope granularity is not applicable to NCBI tokens in the described interface, and no server-side auth is described, implying local/agent access control is unspecified. No information is provided about dependency pinning or vulnerability management.","uptime_documented":0.0,"version_stability":50.0,"breaking_changes_history":20.0,"error_recovery":20.0,"idempotency_support":"false","idempotency_notes":null,"pagination_style":"none","retry_guidance_documented":false,"known_agent_gotchas":["Tool inputs rely on correctly formatted PubMed advanced search syntax; malformed queries may fail or return unexpected results.","Result files are saved to a local directory (pubmearch/results); agents may need to manage filesystem state and avoid reusing/overwriting prior runs.","No explicit documentation provided for pagination semantics beyond max_results; large queries may be truncated.","No explicit retry/idempotency guidance documented for long-running or partial failures."]}}