servicenow-mcp
Related Servers
Alternatives to servicenow-mcp
- AlicenseCqualityAmaintenanceEnables AI to interact with ServiceNow instances via MCP, providing 400+ tools across all modules for automation, development, and management.50018Elastic 2.0
Related Servers
- AlicenseAqualityBmaintenanceThe most comprehensive ServiceNow MCP server. 17 tools for full CRUD, CMDB graph traversal, background scripts, ATF testing, and more.242,047 npm13MIT
- AlicenseNot gradedqualityDmaintenanceA comprehensive MCP server for ServiceNow that provides over 60 pre-built tools for ITSM, ITOM, and App Dev operations, enabling AI agents to manage incidents, changes, users, service catalog, and projects through a unified interface.6MIT
- AlicenseNot gradedqualityAmaintenanceA metadata-driven MCP server that auto-generates 480+ tools across 160+ ServiceNow tables, with multi-instance support, natural language search, and local script development.336 npm55Apache 2.0
- AlicenseBqualityBmaintenanceEnables natural language control of ServiceNow from AI clients like Claude and Cursor. Provides 400+ tools for incidents, changes, CMDB, and scripts via MCP protocol.500183 npm2MIT
- AlicenseNot gradedqualityDmaintenanceEnterprise-grade MCP server providing 102 production-ready tools for Jira, Confluence, and Bitbucket, enabling AI agents to manage issues, pages, repositories, and more via natural language.MIT
- AlicenseAqualityBmaintenanceAn MCP server that enables AI assistants to interact with ServiceNow instances, allowing script execution, data querying, ATF tests, and log tailing through natural language commands.135147 npm16MIT
TDQS
Scored across 581 tools
The set contains many large clusters of tools that do nearly the same thing: query_records vs fluent_query vs fluent_sdk_query vs nlq_query vs natural_language_search vs ai_search, or aggregate_report vs run_aggregate_query vs aggregate_report vs trend_query vs visualize_trend. Other overlapping pairs exist (list_update_sets vs list_changesets, get_changeset vs get_current_update_set, execute_script vs run_fix_script vs execute_background_script vs fluent_exec, mcp_health_check vs sn_mcp_status), plus dozens of AI/Otto inventory tools whose boundaries are only visible after reading long descriptions. Individual descriptions are unusually detailed, which helps, but at 581 tools an agent cannot reliably pick the right one.
Most tools follow snake_case verb_noun with recognizable family prefixes (sn_mcp_, sn_a2a_, fluent_, ml_, cmdb_, pa_, uib_, atf_, va_). However a substantial minority break the pattern with noun-only or noun-phrase names (change_readiness, service_health, aggregate_report, ml_similar_incidents, ai_search, nlq_query, fluent_version), and the many separate prefix families make the convention feel layered rather than single and predictable.
581 tools is an extreme mismatch for a single MCP server — far beyond what an agent can load, reason over, or select from reliably, even with search_tools and lean-discovery mitigations. The surface spans a dozen unrelated product domains (ITSM, CSM, HRSD, GRC, SecOps, CMDB, DevOps, Flow, PA, UI Builder, Fluent SDK, MCP/A2A administration), which should be separate servers.
Coverage is extraordinarily broad: most domains have create/read/update/delete or lifecycle operations (incident, change, problem, CSM case, HR case, catalog, GRC, vulnerability, CMDB, flows, scripting, attachments), plus read-only diagnostics and governance reports. Some gaps remain (e.g. no generic delete for several record types, thin coverage of some write paths), but agents would rarely hit a hard dead end.