Claude For Abap

45 tools. 20 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated:

20 can modify or destroy data
25 read-only
45 tools total

Community server · catalogue entry verified 12/06/2026

How to control Claude For Abap ↓

What Claude For Abap exposes to your agents

Read (25) Write / Execute (19) Destructive / Financial (1)
Critical Risk

The most dangerous Claude For Abap tools

20 of Claude For Abap's 45 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control Claude For Abap

PolicyLayer is an MCP gateway — it sits between your AI agents and Claude For Abap, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations
{
  "adt_delete_object": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations
{
  "adt_create_object": {
    "limits": [
      {
        "counter": "adt_create_object_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "adt_browse_package": {
    "limits": [
      {
        "counter": "adt_browse_package_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

  1. Create a free account and register Claude For Abap — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON CLAUDE FOR ABAP →

Free to start. No card required.

All 45 Claude For Abap tools

READ 25 tools
Read adt_browse_package List the immediate contents (one level) of an ABAP package. Use adt_list_packages for recursive walks. Read adt_cds_data_preview Preview the data exposed by a CDS view (DDL source) via the ADT CDS Data Preview endpoint. Read-only. Returns Read adt_cds_dependencies Return the dependency graph of a CDS view — the entities it consumes (and, where the system exposes it, relate Read adt_check_note_status Report the implementation status of a SAP Note in the system (e.g. can be implemented / obsolete / fully imple Read adt_compare_source Compare the source of the same object across two systems. Returns a unified-diff plus added/removed line count Read adt_compare_versions Diff two versions of the SAME object Read adt_get_dump Fetch the full detail of one ABAP short dump by id. Performs two requests: a metadata XML lookup (runtime erro Read adt_get_note Fetch SAP Note metadata (title, component, version, type, implementation prerequisites) via the Note Assistant Read adt_get_source Fetch the ABAP source of an object (program, class, interface, function module, include, CDS, table). Returns Read adt_get_transport Fetch detail of a single transport request (header + included objects). Read adt_grep_source Full-text regex search across ABAP source. Complements adt_search_objects (which only matches names). Scope th Read adt_list_dumps List ABAP short dumps (ST22) from the runtime-dumps Atom feed. Each entry exposes id, runtime error name, term Read adt_list_inactive_objects List the inactive objects worklist for the connected user (the ADT Read adt_list_locks List runtime enqueue locks (the SM12 analog). NOTE: most ABAP systems do NOT expose SM12 runtime enqueues over Read adt_list_packages Recursively walk subpackages from a root package. Returns a flattened map of package → contents (counts and en Read adt_list_released_apis List the API release-state contracts the system defines — the catalog used to classify released objects (e.g. Read adt_list_systems List configured SAP systems available for ADT calls, the default system, and read-only flags. Read adt_list_transports List transport requests visible to the configured user. Filter by user (requestor) and / or status (modifiable Read adt_list_versions List the version history of an object via the ADT versions sub-resource ({objectUri}/versions). NOTE: many on- Read adt_ping Ping a configured SAP system by calling the ADT discovery endpoint. Use to verify credentials and network reac Read adt_read_spool Read the output (spool list) of a background job / spool request (SP01 analog). EXPERIMENTAL — see adt_schedul Read adt_read_table Execute an OpenSQL SELECT against the SAP database via the ADT Data Preview endpoint. Read-only by design (SEL Read adt_search_objects Quick-search the ABAP repository for objects whose name matches a pattern. Use Read adt_transport_diff Diff every object listed in a transport between two systems. Capped at maxObjects (default 50). Read adt_where_used Where-used list for an object. Returns the references that point to it.

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

Questions about Claude For Abap

Can an AI agent delete data through the Claude For Abap MCP server? +

Yes. The Claude For Abap server exposes 1 destructive tools including adt_delete_object. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Claude For Abap? +

The Claude For Abap server has 9 write tools including adt_create_object, adt_create_transport, adt_implement_note. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Claude For Abap.

How many tools does the Claude For Abap MCP server expose? +

45 tools across 4 categories: Destructive, Execute, Read, Write. 25 are read-only. 20 can modify, create, or delete data.

How do I enforce a policy on Claude For Abap? +

Register the Claude For Abap MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Claude For Abap tool call.

Deterministic rules across all 45 Claude For Abap tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

45 Claude For Abap tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.