@onlyflows/servicenow-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SN_USER | Yes | ServiceNow username | |
| SN_INSTANCE | Yes | Instance URL (e.g. https://yourinstance.service-now.com) | |
| SN_PASSWORD | Yes | ServiceNow password | |
| SN_REL_DEPTH | No | Default CMDB relationship traversal depth | 3 |
| SN_DISPLAY_VALUE | No | Default display value mode (true, false, all) | true |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| sn_queryA | Query a policy-approved ServiceNow table. Returns records with pagination metadata (record_count, has_more, next_offset; no table total, which would cost a COUNT query: page with next_offset until has_more is false). Field verbosity: an explicit fields list always wins; otherwise response_format="concise" (default) uses the table's safe default field set and response_format="detailed" returns all policy-approved readable fields (same as fields="all"). Responses larger than max_response_bytes are truncated by dropping whole records from the tail, with a hint for fetching the rest. Filter example (a list means AND): structured_query={filter:[{type:"equality",field:"active",operator:"eq",value:true},{type:"text",field:"name",operator:"contains",value:"fleet"}]}. OR: {type:"group",operator:"or",conditions:[...]}. |
| sn_getA | Get exactly one record from a policy-approved ServiceNow table by a strict 32-hex sys_id or an approved table-specific human-readable identifier. Identifier resolution is exact and bounded: no match returns not_found and multiple matches return conflict. Explicit fields win; otherwise concise uses safe defaults and detailed returns all policy-approved readable fields. |
| sn_createA | Create one record on any table the configured policy grants for writes. Fields are bounded by the field policy; incident additionally requires a short_description. Journal fields (comments, work_notes) add an entry. |
| sn_updateA | Update fields on exactly one record selected by canonical sys_id, on any table the configured policy grants for writes. At least one bounded approved field is required; journal fields (comments, work_notes) add an entry. |
| sn_incident_add_commentA | Append one bounded customer-visible comment to an authorized incident. |
| sn_incident_add_work_noteB | Append one bounded internal work note to an authorized incident. |
| sn_deleteA | Delete a ServiceNow record by sys_id. Requires the confirm flag set to true as a safety measure. |
| sn_batchA | Bulk update or delete records matching policy-authorized structured filters. Runs in dry-run mode by default — set confirm to true to execute. Raw encoded queries are prohibited. Safety cap at 10,000 records. |
| sn_aggregateA | Run aggregate queries (COUNT, AVG, MIN, MAX, SUM) on a ServiceNow table with optional grouping. |
| sn_schemaB | Get the schema (field definitions) for a ServiceNow table. Returns field names, types, max lengths, mandatory flags, and reference targets. |
| sn_healthB | Check ServiceNow instance health: version, cluster nodes, stuck jobs, semaphores, and key stats (active incidents, P1s, changes, problems). |
| sn_attachA | Manage attachments on ServiceNow records. List, download, or upload attachments. Bytes are exchanged inline as base64; this tool never reads or writes the host filesystem, so it behaves identically for local, containerized, and remote servers. |
| sn_relationshipsA | Traverse CMDB CI relationships (graph walk). Supports upstream, downstream, or both directions with configurable depth. Use for impact analysis and dependency mapping. |
| sn_syslogA | Query ServiceNow system logs (syslog table) with severity, source, and time-based filters. Results ordered newest first, with pagination metadata (record_count, total, has_more, next_offset). To tail: tail=true, then after_cursor=cursor for newer entries, oldest first. |
| sn_codesearchA | Search across ServiceNow code artifacts — business rules, script includes, UI scripts, client scripts, scripted REST operations, ES modules and ATF step scripts. Returns matches with a snippet around the first hit; with no table, tables take turns so each is on page 1. |
| sn_discoverC | Discover tables, applications, and plugins installed on the ServiceNow instance. |
| sn_flow_viewA | View a Flow Designer flow or subflow (by sys_id or exact name) as a graph: trigger, steps, branches, loops and called subflows (depth 2-3), with input values under field policy. Returns a Mermaid diagram and an outline as text, and the full graph with the diagram as structuredContent. A name that matches more than one flow fails with a conflict; pass the sys_id instead. Reads only through the Table API; never calls Flow Designer's internal API, so it changes nothing on the instance. Flow text is untrusted instance data. |
| sn_atf_authorA | Create ATF tests and suites, or add tests to a suite. Requires explicit table write grants. Rolls back confirmed inserts on failure; reports incomplete or uncertain writes. Supports a runtime-verified step catalog; script steps require atf.allowScriptSteps. A step that names a table needs read (forms: write) access to it; conditions use plain readable fields with literal-comparison operators; record_query and record_validation always enforce ACLs. Does not execute tests. |
| sn_atf_runA | Run an ATF suite using ServiceNow Cloud Runner only (no local browser or manual-runner fallback), through CI/CD with explicit atf.execute permission. Returns progress/result IDs, readable failures and cached comparison. Use sn_atf_readiness first. |
| sn_atf_resultsA | Get paginated ATF suite results, retrieve complete step summary/output in chunks, or inspect cached history/comparisons. History and compare need no ServiceNow network requests. Results may include untrusted failure text. |
| sn_atf_readinessA | Check ATF plugins, properties, runner availability and profile grants. Unreadable or unverified checks are reported explicitly. Optionally inspect a suite and its child suites for active tests and UI steps. |
| sn_atfA | Automated Test Framework — list tests/suites and read legacy results. Run actions return migration guidance for sn_atf_run. |
| sn_nlB | Natural language interface for ServiceNow. Translates plain English into ServiceNow API calls. Supports queries, aggregates, schema lookups, creates, updates, and batch operations. Read operations execute immediately; write operations require execute=true. |
| sn_profileA | Inspect non-secret metadata and the effective policy card (tables, tools, fields, batch limits) for an explicitly selected ServiceNow profile. Profiles are created, modified, and selected out of band by the operator; this tool never changes profile configuration or reveals credentials. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| servicenow-mcp.add-profile | Guide creation of an explicit, default-deny ServiceNow profile without putting secrets in chat or argv. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 24 tools
The core CRUD set (sn_query/sn_get/sn_create/sn_update/sn_delete) is cleanly separated, and each specialty tool (sn_syslog, sn_relationships, sn_codesearch, sn_flow_view) targets a distinct artifact. The main ambiguity is sn_nl, a general natural-language interface that overlaps with sn_query, sn_aggregate, sn_schema, sn_create, sn_update, and sn_batch, and to a lesser degree sn_atf vs sn_atf_results both exposing ATF result reads — descriptions mitigate but do not eliminate this.
All 24 tools use a consistent `sn_` prefix with snake_case segments, giving a predictable namespace. Minor structural deviations exist between flat verb tools (sn_query), grouped families (sn_atf_readiness / sn_atf_author / sn_atf_run / sn_atf_results alongside a bare sn_atf), and resource-scoped names (sn_incident_add_comment), but none are confusing.
24 tools sits at the high end of the comfortable range, but ServiceNow is a genuinely broad platform (records, CMDB, ATF, flows, logs, attachments, discovery, profiles), so each tool maps to a real capability area rather than filler. A couple of niches (sn_incident_add_comment / sn_incident_add_work_note) could arguably fold into sn_update, but the surface is defensible.
Full record lifecycle is covered (query, get, create, update, delete, bulk batch, aggregates, schema), plus strong coverage of CMDB relationships, ATF authoring/running/results, code search, flow viewing, attachments, syslog, and instance health. Remaining gaps are modest: sn_attach cannot delete attachments, Flow Designer is read-only, and there is no explicit journal/history retrieval tool (only field-level comment appends).