servicenow

servicenow

MCP server that gives Claude Code tools to read, write, and configure a ServiceNow instance, enabling hands-off flow design and management via basic auth.

Category
Visit Server

README

ServiceNow MCP Server

MCP server that gives Claude Code tools to read, write, and configure a ServiceNow instance.

šŸ”§ Flow Designer — hands-off flow build

This server can build, compile, and publish Flow Designer flows programmatically — no browser, no UI "Activate", any scope — via the undocumented processflow API plus the CSRF g_ck header (the missing piece that makes basic auth work). Tools: flow_designer_get / flow_designer_save / flow_designer_compile (only basic-auth admin creds needed — no Script Runner).

āž”ļø See docs/flow-designer/ for the full kit: the recipe, the bundled servicenow-flow-creator skill, the gotchas, and a worked catalog-item example.

Setup

1. Install and build

npm install
npm run build

2. Configure credentials

Credentials are passed to the server through the MCP config env block (step 4). The code reads process.env only — there is no .env loading, so a .env file is ignored. You need three values:

  • SN_INSTANCE — your instance subdomain only (e.g. dev12345, not the full https://… URL)
  • SN_USERNAME — an admin user
  • SN_PASSWORD — that user's password

The flow-designer kit (flow_designer_*) and every table_* tool need only these basic-auth admin creds — no Script Runner (step 3 is optional).

3. (Optional) Deploy Script Runner — only for the run_script tool

Flow-designer users can skip this entirely. flow_designer_get/save/compile and every table_* tool work with just the basic-auth admin creds from step 2. Script Runner is required only if you want the run_script tool (arbitrary server-side GlideScript).

To enable run_script, deploy a Scripted REST API app to your PDI:

  1. Open ServiceNow Studio on your PDI
  2. Create a new scoped app: scope = x_mcp_snc, name = "MCP Script Runner"
  3. Create a Scripted REST API: name = script_runner
  4. Add a POST resource at /execute with this script:
(function process(/*RESTAPIRequest*/ request, /*RESTAPIResponse*/ response) {
    var body = request.body.data;
    var script = '' + body.script;

    var evaluator = new GlideScopedEvaluator();
    evaluator.putVariable('request', request);
    evaluator.putVariable('response', response);

    var result;
    try {
        var gr = new GlideRecord('sys_script_include');
        gr.initialize();
        gr.setValue('script', script);
        result = evaluator.evaluateScript(gr, 'script', null);

        if (result !== null && result !== undefined) {
            response.setBody({ result: '' + result });
        }
    } catch (e) {
        response.setStatus(500);
        response.setBody({ error: '' + e });
        return;
    }
})(request, response);

Note: GlideScopedEvaluator allows injecting request and response into the script scope, so scripts CAN use response.setBody() directly for complex output. For simple scripts, the last expression value is auto-returned.

  1. Set the resource to require admin role

4. Add to Claude Code

Add to your Claude Code MCP config (~/.claude/settings.json or project settings):

{
  "mcpServers": {
    "servicenow": {
      "command": "node",
      "args": ["/absolute/path/to/servicenow-mcp-server/dist/index.js"],
      "env": {
        "SN_INSTANCE": "your-instance-name",
        "SN_USERNAME": "admin",
        "SN_PASSWORD": "your-password"
      }
    }
  }
}

Available Tools

Tool Description
table_read Query any ServiceNow table with filtering and pagination
table_create Insert a record into any table
table_update Update a record (tracks before/after state)
table_delete Delete a record
get_table_schema Get field definitions for a table
get_choices Get choice list values for a field
get_instance_info Get instance version and active plugins
run_script Execute server-side GlideScript
get_sys_properties Read system properties
set_sys_property Set a system property value
flow_designer_get Fetch a flow's editable processflow JSON
flow_designer_save Build/save a flow (PUT the raw processflow object)
flow_designer_compile Compile + publish a flow — hands-off "Activate" via /snapshot

Plus more tool groups not listed above: catalog, change, CMDB, knowledge, import-set, batch, aggregate, and attachments. See src/index.ts for the full registration.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured