Skip to main content
Glama
ethanhan2014

SAP ADT MCP Server

by ethanhan2014

set_debugger_breakpoint

Set a breakpoint at a specific ABAP source line in the SAP debugger. Provide the object URI, line number, and optionally user and system ID to halt execution for inspection.

Instructions

Set a breakpoint at a specific source location in the debugger

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
uriYesObject source URI (e.g. /sap/bc/adt/programs/programs/ztest/source/main)
lineYesLine number for breakpoint
userNoSAP username (default: current user)
system_idNoSAP system ID (e.g. DEV). Omit to use default system.

Implementation Reference

  • The handler for the set_debugger_breakpoint MCP tool. Parses input via DebuggerBreakpointSchema, then calls client.debuggerSetBreakpoints(uri, line, user).
    case "set_debugger_breakpoint": {
      const { uri, line, user } = DebuggerBreakpointSchema.parse(args);
      const result = await client.debuggerSetBreakpoints(uri, line, user);
      return { content: [{ type: "text", text: result }] };
    }
  • Registration of the 'set_debugger_breakpoint' tool in the ListToolsRequestSchema handler, defining its name, description, and input schema with uri, line, and optional user parameters.
    {
      name: "set_debugger_breakpoint",
      description: "Set a breakpoint at a specific source location in the debugger",
      inputSchema: {
        type: "object" as const,
        properties: {
          uri: { type: "string", description: "Object source URI (e.g. /sap/bc/adt/programs/programs/ztest/source/main)" },
          line: { type: "number", description: "Line number for breakpoint" },
          user: { type: "string", description: "SAP username (default: current user)" },
          ...SYSTEM_ID_PROP,
        },
        required: ["uri", "line"],
      },
    },
  • Zod schema 'DebuggerBreakpointSchema' used to validate the input arguments (uri, line, user) for the set_debugger_breakpoint tool.
    const DebuggerBreakpointSchema = z.object({
      uri: z.string(),
      line: z.number(),
      user: z.string().optional(),
    });
  • The actual implementation method 'debuggerSetBreakpoints' in AdtClient. Ensures an active debug session exists, then POSTs an XML breakpoint definition to the SAP ADT debugger breakpoints endpoint.
      async debuggerSetBreakpoints(uri: string, line: number, user?: string): Promise<string> {
        this.ensureDebugSession();
        const u = (user ?? this.config.username).toUpperCase();
        const xml = `<?xml version="1.0" encoding="UTF-8"?>
    <dbg:breakpoints xmlns:dbg="http://www.sap.com/adt/debugger">
      <dbg:breakpoint dbg:kind="line" dbg:uri="${this.escapeXml(uri)}" dbg:line="${line}" dbg:user="${this.escapeXml(u)}"/>
    </dbg:breakpoints>`;
        const resp = await this.http.post("/sap/bc/adt/debugger/breakpoints", xml, {
          headers: this.statefulHeaders({
            "Content-Type": "application/xml",
            Accept: "application/xml",
          }),
          responseType: "text",
        });
        return resp.data as string;
      }
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, and the description is minimal. It does not disclose side effects, permissions, or that a debugger must be active. For a state-modifying tool, more behavioral context is needed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

One sentence, no fluff, directly states the action. Efficient and front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 4 parameters and no output schema or annotations, the description is too brief. It lacks context about the debugger environment, format of URI, or how breakpoints interact with sessions.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the description adds no extra meaning. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool sets a breakpoint at a specific source location, using a specific verb and resource. It distinguishes from sibling tools like delete_debugger_breakpoint and debugger_step.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives like attach_debugger or debugger_step. No prerequisites or context (e.g., need a debugger session) are mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/ethanhan2014/sap-adt-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server