{"id":"sekora-opensearch-mcp-server","name":"sekora-opensearch-mcp-server","homepage":"https://pypi.org/project/sekora-opensearch-mcp-server/","repo_url":"https://github.com/opensearch-project/sekora-opensearch-mcp-server.git","category":"search","subcategories":[],"tags":["mcp","opensearch","search","retrieval","ai-agents","sekora"],"what_it_does":"A MCP server that exposes Sekora-backed OpenSearch capabilities to AI agents via the Model Context Protocol, allowing the agent to run searches and related operations against an OpenSearch index using MCP tool calls.","use_cases":["Agent-assisted search over OpenSearch-backed content","Retrieval of documents/records from OpenSearch for downstream reasoning","Automating common OpenSearch workflows from an LLM agent via MCP"],"not_for":["High-sensitivity deployments without careful network/access controls","Use cases requiring a fully managed hosted API or turnkey authentication/hosting","Replacing a native OpenSearch client for advanced cluster administration"],"best_when":"You want a local/controlled MCP integration that lets an agent query an OpenSearch index through a tool interface.","avoid_when":"You need guaranteed production-grade operational assurances (SLA, published uptime) without additional engineering and monitoring, or you require strong built-in auth controls beyond what you provide at runtime.","alternatives":["OpenSearch REST API via direct HTTP calls from the agent (with API keys)","OpenSearch official client libraries (for application-side integrations)","Other MCP servers that provide search/RAG utilities over OpenSearch or Elasticsearch"],"af_score":42.5,"security_score":48.0,"reliability_score":31.2,"package_type":"mcp_server","discovery_source":["pypi"],"priority":"low","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-04-04T21:44:59.040494+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":["OpenSearch credentials (e.g., API key/basic auth) likely required at runtime, but not confirmed from provided content"],"oauth":false,"scopes":false,"notes":"Authentication and authorization details are not provided in the prompt content. MCP servers typically rely on underlying connection credentials you supply (e.g., OpenSearch API key). Verify whether tool-level authorization/scopes are implemented."},"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 was provided; as an MCP server it is likely a self-hosted/open-source integration, but this is not confirmed."},"requirements":{"requires_signup":false,"requires_credit_card":false,"domain_verification":false,"data_residency":[],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":42.5,"security_score":48.0,"reliability_score":31.2,"mcp_server_quality":55.0,"documentation_accuracy":45.0,"error_message_quality":0.0,"error_message_notes":null,"auth_complexity":50.0,"rate_limit_clarity":20.0,"tls_enforcement":60.0,"auth_strength":50.0,"scope_granularity":30.0,"dependency_hygiene":50.0,"secret_handling":50.0,"security_notes":"Security posture cannot be confirmed from the provided content. For MCP integrations with OpenSearch, ensure TLS is enforced end-to-end, restrict network access, use least-privilege OpenSearch credentials, and verify whether the server logs tool inputs/outputs (to avoid leaking queries or secrets).","uptime_documented":0.0,"version_stability":45.0,"breaking_changes_history":40.0,"error_recovery":40.0,"idempotency_support":"false","idempotency_notes":null,"pagination_style":"unknown","retry_guidance_documented":false,"known_agent_gotchas":["Search endpoints may have defaults (size/from, timeouts) that can cause large responses or slow queries if the agent does not constrain parameters.","If the MCP tools map directly to OpenSearch queries, the agent may produce expensive queries (e.g., broad match queries) unless guardrails/limits are enforced."]}}