{"id":"acuvity-mcp-server-aws-bedrock-kb-retrieval","name":"mcp-server-aws-bedrock-kb-retrieval","homepage":"https://hub.docker.com/r/acuvity/mcp-server-aws-bedrock-kb-retrieval","repo_url":"https://hub.docker.com/r/acuvity/mcp-server-aws-bedrock-kb-retrieval","category":"ai-ml","subcategories":[],"tags":["mcp","aws","bedrock","retrieval","rag","knowledge-base","ai-agents","tooling"],"what_it_does":"An MCP server package that enables AI agents to retrieve relevant knowledge from AWS Bedrock Knowledge Bases (KB retrieval) and return it as context for downstream model responses.","use_cases":["Agent-assisted Q&A over an organization’s Bedrock Knowledge Base content","Retrieval-augmented generation (RAG) workflows using MCP tool calls","Customer support assistants grounded in enterprise KB documents","Document search and citation-style retrieval for agent responses"],"not_for":["Direct database/file access beyond the intended KB retrieval capability","Replacing robust search/analytics pipelines where custom ranking and filtering are required","Use cases that need strict compliance tooling not described by the package"],"best_when":"You want an LLM agent to use a standardized MCP tool to fetch Bedrock KB context during conversational flows.","avoid_when":"You cannot securely manage AWS credentials/permissions or need advanced retrieval controls not documented by the server.","alternatives":["AWS Bedrock Knowledge Bases Retrieve API (direct integration)","Other MCP RAG/retrieval servers (e.g., generic vector DB retrieval MCP servers)","Direct RAG implementations using Bedrock + your own middleware"],"af_score":44.2,"security_score":53.8,"reliability_score":25.0,"package_type":"mcp_server","discovery_source":["docker_mcp"],"priority":"low","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-04-04T21:34:38.636276+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":["AWS credentials (IAM access keys or environment/instance credentials)"],"oauth":false,"scopes":false,"notes":"Authentication is not described here; MCP servers interacting with AWS Bedrock KB retrieval typically rely on AWS IAM permissions. Exact auth mechanism and required IAM actions/scopes should be confirmed from the repo/README."},"pricing":{"model":null,"free_tier_exists":false,"free_tier_limits":null,"paid_tiers":[],"requires_credit_card":false,"estimated_workload_costs":null,"notes":"Pricing depends on AWS Bedrock + Knowledge Base retrieval usage and any hosting/runtime cost of the MCP server; no package-specific pricing information was provided."},"requirements":{"requires_signup":false,"requires_credit_card":false,"domain_verification":false,"data_residency":[],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":44.2,"security_score":53.8,"reliability_score":25.0,"mcp_server_quality":70.0,"documentation_accuracy":50.0,"error_message_quality":0.0,"error_message_notes":null,"auth_complexity":45.0,"rate_limit_clarity":20.0,"tls_enforcement":70.0,"auth_strength":60.0,"scope_granularity":45.0,"dependency_hygiene":45.0,"secret_handling":45.0,"security_notes":"Assumes use of AWS IAM credentials. Security posture depends on how the MCP server is configured (credential source, logging practices, TLS for MCP transport, least-privilege IAM). No repository evidence provided here for dependency scanning, secret redaction, or explicit TLS requirements.","uptime_documented":0.0,"version_stability":30.0,"breaking_changes_history":30.0,"error_recovery":40.0,"idempotency_support":"false","idempotency_notes":null,"pagination_style":"none","retry_guidance_documented":false,"known_agent_gotchas":["Agents may request retrieval repeatedly in a loop; without explicit retry/rate-limit handling guidance this can amplify cost/latency.","AWS permission misconfiguration commonly causes tool failures; agents need clear mapping from IAM errors to remediation steps.","If pagination or result limits are not exposed, agents may miss relevant long contexts."]}}