Connect AI clients to the Operations1 MCP server for report search, analytics, full report details, and glossary resources.
The operations1 MCP server enables AI-powered code editors like Cursor and Windsurf, plus general-purpose tools like Claude Desktop, to interact directly with your operations1 report data. It provides AI agents with:
- Report search & filtering across states, date ranges, and orders
- Full report detail including steps, interaction values, documents, and operators
- Aggregate analytics such as completion rates, pass yield, cycle time, and top documents
- Domain glossary so the AI understands operations1-specific terminology and can explain results in plain language
Tools
- search_reports: Searches Operations1 reports using filters like report name, state, updated date range, archived status, and order IDs.
- analyze_reports: Aggregates filtered Operations1 reports into summary metrics such as completion rate, pass status breakdowns, and cycle time statistics.
- get_full_report: Returns the complete detailed content of a specific Operations1 report, including steps, interactions, values, comments, and metadata.
Resources
ops1://glossary/overview:Provides a high-level index of the glossary resources and explains the main Operations1 concepts.ops1://glossary/report-states:Describes the possible report workflow states such as not-started, in-progress, paused, problem, and done.ops1://glossary/passed-statuses:Explains the meaning of pass-status values like pass, unclear, no-pass, and no-pass-critical.ops1://glossary/interaction-types:Lists the supported interaction types and briefly explains what each type represents.ops1://glossary/document-states:Describes the lifecycle states used for documents, such as new, active, archived, and review-related states.ops1://glossary/passed-propagation:Explains how pass and fail results roll up from interactions to steps and then to the overall report.
Operations1 MCP Server Setup
Operations1 hosts a remote MCP server at https://mcp.operations1.app/mcp. Configure your AI development tools to connect to this server. If your APIs require authentication, you can pass in headers via query parameters or however headers are configured in your MCP client.
Run this command in your terminal:
claude mcp add -s user -t http operations1-mcp https://mcp.operations1.app/mcp \
-H "Authorization: Bearer <token>" \
-H "Tenant-Id: <tenant>"OR
Add toclaude_desktop_config.json:
{
"mcpServers": {
"operations1-mcp": {
"type": "http",
"url": "https://mcp.operations1.app/mcp",
"headers": {
"Authorization": "Bearer <token>",
"Tenant-Id": "<tenant>"
}
}
}
}
