// SCAN REPORT

ABAP-ADT-API MCP-Server

127 tools. 38 can modify or destroy data without limits.

7 destructive tools with no built-in limits. Policy required.

Last updated:

38 can modify or destroy data
89 read-only
127 tools total
// TOOL MAP
Read (89) Write / Execute (31) Destructive / Financial (7)
// WHAT CAN GO WRONG
✕

Destructive tools (debuggerDeleteBreakpoints, debuggerDeleteListener, deleteObject) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.

✕

Write operations (activateByName, activateObjects, createAtcRun) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.

✕

Execute tools (runClass, runQuery) trigger processes with side effects. Builds, notifications, workflows — all fired without throttling.

One command. Full control.

Intercept sits between your agent and ABAP-ADT-API MCP-Server. Every tool call checked against your policy before it executes — so your agent can do its job without breaking things.

npx -y @policylayer/intercept scan -- npx -y @mario-andreschak/mcp-abap-abap-adt-api
Scans every tool. Generates a policy. Starts enforcing.
Works with Claude Code · Cursor · Claude Desktop · Windsurf · any MCP client
// RECOMMENDED RULES
Deny destructive operations
debuggerDeleteBreakpoints:
  rules:
    - action: deny

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

Rate limit write operations
activateByName:
  rules:
    - rate_limit: 30/hour

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
abapDocumentation:
  rules:
    - rate_limit: 60/minute

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

// ALL 127 ABAP-ADT-API MCP-SERVER TOOLS
DESTRUCTIVE 7 tools
Destructive debuggerDeleteBreakpoints Destructive debuggerDeleteListener Destructive deleteObject Destructive dropSession Destructive tracesDelete Destructive tracesDeleteConfiguration Destructive transportDelete
EXECUTE 2 tools
Execute runClass Execute runQuery
WRITE 29 tools
Write activateByName Write activateObjects Write createAtcRun Write createObject Write createTestInclude Write createTransport Write createTransportsConfig Write debuggerAttach Write debuggerSaveSettings Write debuggerSetBreakpoints Write debuggerSetVariableValue Write gitCreateRepo Write lock Write login Write publishServiceBinding Write pushRepo Write renameEvaluate Write renameExecute Write renamePreview Write setObjectSource Write setPrettyPrinterSetting Write setTransportsConfig Write switchRepoBranch Write tracesCreateConfiguration Write tracesSetParameters Write transportAddUser Write transportSetOwner Write unLock Write unPublishServiceBinding
READ 89 tools
Read abapDocumentation Read adtCompatibiliyGraph Read adtCoreDiscovery Read adtDiscovery Read annotationDefinitions Read atcChangeContact Read atcCheckVariant Read atcContactUri Read atcCustomizing Read atcExemptProposal Read atcRequestExemption Read atcUsers Read atcWorklists Read bindingDetails Read checkRepo Read classComponents Read classIncludes Read codeCompletion Read codeCompletionElement Read codeCompletionFull Read collectionFeatureDetails Read ddicElement Read ddicRepositoryAccess Read debuggerChildVariables Read debuggerGoToStack Read debuggerListen Read debuggerListeners Read debuggerStackTrace Read debuggerStep Read debuggerVariables Read dumps Read extractMethodEvaluate Read extractMethodExecute Read extractMethodPreview Read featureDetails Read feeds Read findCollectionByUrl Read findDefinition Read findObjectPath Read fixEdits Read fixProposals Read fragmentMappings Read getObjectSource Read getTransportConfiguration Read gitExternalRepoInfo Read gitPullRepo Read gitRepos Read gitUnlinkRepo Read hasTransportConfig Read healthcheck Read inactiveObjects Read isProposalMessage Read loadTypes Read logout Read mainPrograms Read nodeContents Read objectRegistrationInfo Read objectStructure Read objectTypes Read packageSearchHelp Read prettyPrinter Read prettyPrinterSetting Read reentranceTicket Read remoteRepoInfo Read revisions Read searchObject Read stageRepo Read syntaxCheckCdsUrl Read syntaxCheckCode Read syntaxCheckTypes Read systemUsers Read tableContents Read tracesDbAccess Read tracesHitList Read tracesList Read tracesListRequests Read tracesStatements Read transportConfigurations Read transportInfo Read transportReference Read transportRelease Read transportsByConfig Read unitTestEvaluation Read unitTestOccurrenceMarkers Read unitTestRun Read usageReferences Read usageReferenceSnippets Read userTransports Read validateNewObject
// FAQ
Can an AI agent delete data through the ABAP-ADT-API MCP-Server MCP server? +

Yes. The ABAP-ADT-API MCP-Server server exposes 7 destructive tools including debuggerDeleteBreakpoints, debuggerDeleteListener, deleteObject. These permanently remove resources with no undo. Intercept blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through ABAP-ADT-API MCP-Server? +

The ABAP-ADT-API MCP-Server server has 29 write tools including activateByName, activateObjects, createAtcRun. Set rate limits in your policy file -- for example, rate_limit: 10/hour prevents an agent from making more than 10 modifications per hour. Intercept enforces this at the transport layer.

How many tools does the ABAP-ADT-API MCP-Server MCP server expose? +

127 tools across 4 categories: Destructive, Execute, Read, Write. 89 are read-only. 38 can modify, create, or delete data.

How do I add Intercept to my ABAP-ADT-API MCP-Server setup? +

One line change. Instead of running the ABAP-ADT-API MCP-Server server directly, prefix it with Intercept: intercept -c mario-andreschak-mcp-abap-abap-adt-api.yaml -- npx -y @mario-andreschak/mcp-abap-abap-adt-api. Download a pre-built policy from policylayer.com/policies/mario-andreschak-mcp-abap-abap-adt-api and adjust the limits to match your use case.

// RELATED SERVERS

Other MCP servers with similar tools.

Starter policies available for each. Same risk classification, same one-command setup.

Mcp Api 310 tools
adminautomation
Aibtc 288 tools
adminautomation
Google Super 200 tools
adminautomation
Propresenter 177 tools
adminautomation
Leaper Vision Toolkit 169 tools
adminautomation
Mcp Sitecore 153 tools
adminautomation
SmartBear MCP 147 tools
adminautomation
Slack 143 tools
adminautomation
policylayer/intercept

Control every MCP tool call
your agent makes.

Set budgets, approvals, and hard limits across MCP servers.

npx -y @policylayer/intercept init
Protect your agent in 30 seconds. Scans your MCP config and generates enforcement policies for every server.
// GET IN TOUCH

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

Message sent.

We'll get back to you soon.