neubird
Official Model Context Protocol server for NeuBird AI (The Production Operations Agent). Lets AI assistants like Claude Code, Cursor, and GitHub Copilot drive NeuBird's autonomous incident investigation, root-cause analysis, and remediation capabilities. Runs locally (stdio via npx) or as a remote HTTP server; calls the NeuBird API at https://api.neubird.ai using the caller's credentials.
One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.
Documentation
Documentation link · transport
Tools
neubird_list_projects— Retrieve all available projects with optional inactive filtering.neubird_create_project— Establish a new project with name and description.neubird_get_project_details— Obtain comprehensive project information.neubird_update_project— Modify a project name or description.neubird_delete_project— Remove a project (requires confirmation).neubird_list_connections— Show all configured connections with sync status.neubird_create_aws_connection— Establish an AWS integration using an IAM role ARN.neubird_create_datadog_connection— Set up a Datadog connection via API/app keys.neubird_wait_for_connection_sync— Poll a connection until synchronization completes.neubird_add_connection_to_project— Link one or more connections to a project.neubird_list_project_connections— Display connections assigned to a specific project.neubird_list_sessions— Retrieve investigation sessions with filtering and search.neubird_investigate_alert— Initiate an investigation using an alert ID.neubird_continue_investigation— Submit follow-up questions to a completed investigation.neubird_get_investigation_status— Monitor real-time investigation progress and steps.neubird_get_rca— Extract the complete root cause analysis with remediation steps.neubird_get_chain_of_thought— Display reasoning steps and investigation logic.neubird_get_investigation_queries— List queries executed during an investigation.neubird_get_investigation_sources— Show data sources consulted during analysis.neubird_get_follow_up_suggestions— Recommend additional investigative questions.neubird_get_rca_score— Provide quality-assessment metrics for an investigation.neubird_list_project_instructions— List instructions by type and status.neubird_create_project_instruction— Create FILTER, SYSTEM, GROUPING, or RCA instructions.neubird_validate_instruction— Verify instruction syntax before application.neubird_apply_session_instruction— Test an instruction against a specific investigation.neubird_rerun_session— Re-execute an investigation with updated instructions.neubird_inspect_session— Retrieve session metadata and configuration.neubird_get_session_report— Generate summary reports for multiple sessions.neubird_get_session_summary— Provide detailed analysis and performance scoring.neubird_get_incident_report— Aggregate organization-wide MTTR and metrics.neubird_discover_project_resources— Aggregate all resources across a project's connections.neubird_list_connection_resource_types— Enumerate available resource types by connection and telemetry.neubird_get_guidance— Interactive assistance across connections, projects, and troubleshooting.
About MCP
The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.
Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.
Work with this as data
Every MCP server here is available over the APIs.io API and to AI agents over MCP.