// SCAN REPORT

Dump Analyzer

7 tools. 5 can modify or destroy data without limits.

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

Last updated: 29 Jun 2026

5 can modify or destroy data

2 read-only

7 tools total

Community server · catalogue entry verified 29/06/2026

How to control Dump Analyzer ↓

TOOL MAP

What Dump Analyzer exposes to your agents

Read (2) Write / Execute (4) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Dump Analyzer tools

Destructive · High close_analysis_session The tool explicitly deletes temporary files and releases all resources associated with an analysis session. Execute · High execute_windbg_command This tool runs debugger commands with unrestricted scope ('any CDB command'). Execute · High start_analysis_session Loading and analyzing crash dumps via CDB commands constitutes executing external operations whose effects depend on arguments (which dump file, what symbols). Execute · High start_async_windbg_command This tool executes external debugger commands (CDB) whose effects depend on the command arguments provided by the AI agent.

5 of Dump Analyzer's 7 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Dump Analyzer

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

Deny destructive operations

{
  "close_analysis_session": {
    "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

{
  "prepare_dump_upload": {
    "limits": [
      {
        "counter": "prepare_dump_upload_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_async_windbg_command_result": {
    "limits": [
      {
        "counter": "get_async_windbg_command_result_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

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

Create a free account and register Dump Analyzer — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON DUMP ANALYZER →

Instant setup, no code required.

FULL CATALOGUE

All 7 Dump Analyzer tools

DESTRUCTIVE 1 tools

Destructive close_analysis_session Close the analysis session, release all resources, and delete temporary files.

EXECUTE 3 tools

Execute execute_windbg_command Execute any CDB command in an analysis session and stream the raw output. Execute start_analysis_session Start a crash dump analysis session and load the dump file and symbols. Execute start_async_windbg_command Start a CDB command asynchronously and return a command_id.

WRITE 1 tools

Write prepare_dump_upload Prepare a crash dump upload and return a pre-signed upload URL.

READ 2 tools

Read get_async_windbg_command_result Get the result of an asynchronously running CDB command, optionally waiting a short time. Read get_async_windbg_command_status Get the current status of an asynchronously running CDB command.

EXPLORE

Related servers

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

FAQ

Questions about Dump Analyzer

Can an AI agent delete data through the Dump Analyzer MCP server? +

Yes. The Dump Analyzer server exposes 1 destructive tools including close_analysis_session. 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 Dump Analyzer? +

The Dump Analyzer server has 1 write tools including prepare_dump_upload. 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 Dump Analyzer.

How many tools does the Dump Analyzer MCP server expose? +

7 tools across 3 categories: Execute, Read, Write. 2 are read-only. 5 can modify, create, or delete data.

How do I enforce a policy on Dump Analyzer? +

Register the Dump Analyzer 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 Dump Analyzer tool call.

Deterministic rules across all 7 Dump Analyzer tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON DUMP ANALYZER →

Instant setup, no code required.

7 Dump Analyzer tools catalogued and risk-classified — across an index of 43,000+ MCP servers.