Skip to main content
mcpSource-backed

WinDbg MCP Server

MCP server that connects Claude to Windows CDB/WinDbg for crash dump discovery, dump triage, remote debugging targets, custom debugger commands, debugger cleanup, and CTRL+BREAK interrupts.

by svnscha · submitted by oktofeesh1·added 2026-06-06·
Review first review before installing

Open the source and read safety notes before installing.

Citation facts

Source-backed facts for citing this resource, derived directly from the registry — also available as plain text for AI assistants.

Source URLs
https://raw.githubusercontent.com/svnscha/mcp-windbg/main/README.md, https://github.com/svnscha/mcp-windbg
Brand
MCP Server for WinDbg
Brand domain
github.com
Safety notes
WinDbg MCP starts CDB processes and can run arbitrary WinDbg commands supplied through the MCP tool call., Remote debugging tools can attach to live targets, inspect process state, send CTRL+BREAK, and interrupt execution., Crash dump analyses and remote connections remain active until closed or the CDB process is terminated., Symbol paths can fetch symbols from network symbol servers and can disclose module names, versions, and debugging context., Do not expose streamable HTTP mode beyond a trusted host without transport security, authentication, and network controls.
Privacy notes
Crash dumps can contain memory, stack values, command lines, environment variables, file paths, registry data, sensitive values, PII, customer data, and proprietary code or symbols., WinDbg output, dump paths, remote connection strings, symbol paths, module lists, thread stacks, exception records, and debugger command output may be visible to the MCP client and model provider., Verbose logs, command transcripts, dump triage prompts, and saved analysis results can retain sensitive crash data after use., Redact dump paths, remote endpoints, symbols, process details, and command output before sharing logs, screenshots, or PR comments.
Author
svnscha
Submitted by
oktofeesh1
Claim status
unclaimed
Last verified
2026-06-06

Decision playbook

Review trust signals before you adopt

Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.

Compare context
Selected

0

Current score

63

Baseline

Delta

No baseline selected

No major trust-signal divergence detected in the current selection.

Source and provenance checks

Needs review

Confirm ownership and provenance before trusting install instructions.

  • Source link availableRequired

    Open the canonical repository and verify ownership.

    Done
  • Source provenance statusRequired

    Marked as source-backed.

    Done
  • Metadata reviewed

    No reviewed flag detected in metadata.

    Pending

Safety and privacy checks

Complete

Validate risk disclosures before installation or API wiring.

  • Safety notes presentRequired

    Review the listed safety guidance before running commands.

    Done
  • Privacy notes presentRequired

    Review data handling notes before connecting accounts or secrets.

    Done
  • Trust level risk gateRequired

    Trust level does not block evaluation.

    Done

Package and install checks

Needs review

Check package metadata and artifact integrity signals.

  • Install payload available

    Install or copy payload is available for review.

    Done
  • Package verification flag

    No package verification flag provided.

    Pending
  • Checksum metadata

    No checksum provided for downloaded artifact.

    Pending

Compare-driven decision checks

Needs review

Use compare context to validate trade-offs before adoption.

  • Compare tray has multiple entries

    Add at least one more entry to compare trust differences.

    Pending
  • Baseline comparison available

    No baseline peer selected yet.

    Pending
  • Diverging trust signals identified

    No major trust-signal divergence found.

    Pending

Setup at a glance

CLI install

Copy-ready — paste the snippet to get started.

15 minutes

Adoption plan

Balanced adoption plan

Current risk score 24/100. Use staged verification before broader rollout.

Risk 24

Pre-adoption checks

Validate source and review signals before any execution.

  • Confirm source provenanceRequired

    Source URL/provenance metadata is present.

    Done
  • Confirm metadata review state

    No review metadata found; increase manual validation.

    Pending
  • Verify install payload

    Install/config payload exists and can be inspected.

    Done

Security checks

Confirm safety, privacy, and package integrity signals.

  • Review safety notesRequired

    Safety notes are present.

    Done
  • Review privacy notesRequired

    Privacy notes are present.

    Done
  • Verify package integrity metadata

    No package verification/checksum metadata.

    Pending

Rollout

Adopt in controlled steps based on the selected plan.

  • Run in isolated sandbox firstRequired

    Use a constrained sandbox and observe behavior across multiple tasks.

    Pending
  • Roll out graduallyRequired

    Roll out to a small cohort before wider usage.

    Pending
  • Set monitoring and fallback

    Define rollback path and monitor errors after adoption.

    Pending

Evidence readiness

Evidence readiness matrix · balanced

Missing required evidence: Metadata review. Risk score 31.

Risk 31

Source provenance

Present

Source repository/provenance is listed.

Required in this preset

Metadata review

Missing

Review metadata is missing.

Required in this preset

Safety notes

Present

Safety notes are present.

Required in this preset

Privacy notes

Present

Privacy notes are present.

Optional in this preset

Package integrity

Missing

Package integrity metadata is missing.

Optional in this preset

Install payload

Present

Install payload is available.

Required in this preset

Required gaps: Metadata review

Decision timeline

Decision timeline · balanced

Blocking gaps: Check metadata review status. Risk 28.

Risk 28

triage

Confirm source provenanceRequired

Source/provenance metadata is available.

Done

triage

Check metadata review statusRequired

Review metadata is missing.

Pending

verify

Review safety notesRequired

Safety notes are available.

Done

verify

Review privacy notes

Privacy notes are available.

Done

verify

Validate package integrity metadata

Package integrity metadata is missing.

Pending

rollout

Verify install payload and commandsRequired

Install payload is available.

Done

Blockers: Check metadata review status

Prerequisite readiness

Prerequisite readiness

5 prerequisites to line up before setup. Includes a review or approval gate.

0/5 ready
Install & runtime2Permissions & scopes1Review & approval215 minutes

Safety & privacy surface

Safety & privacy surface

5 safety and 4 privacy notes across 3 risk areas. Review closely: network access.

3 areas
  • SafetyExecution & processesWinDbg MCP starts CDB processes and can run arbitrary WinDbg commands supplied through the MCP tool call.
  • SafetyNetwork accessRemote debugging tools can attach to live targets, inspect process state, send CTRL+BREAK, and interrupt execution.
  • SafetyNetwork accessCrash dump analyses and remote connections remain active until closed or the CDB process is terminated.
  • SafetyNetwork accessSymbol paths can fetch symbols from network symbol servers and can disclose module names, versions, and debugging context.
  • SafetyNetwork accessDo not expose streamable HTTP mode beyond a trusted host without transport security, authentication, and network controls.
  • PrivacyLocal filesCrash dumps can contain memory, stack values, command lines, environment variables, file paths, registry data, sensitive values, PII, customer data, and proprietary code or symbols.
  • PrivacyNetwork accessWinDbg output, dump paths, remote connection strings, symbol paths, module lists, thread stacks, exception records, and debugger command output may be visible to the MCP client and model provider.
  • PrivacyExecution & processesVerbose logs, command transcripts, dump triage prompts, and saved analysis results can retain sensitive crash data after use.
  • PrivacyNetwork accessRedact dump paths, remote endpoints, symbols, process details, and command output before sharing logs, screenshots, or PR comments.

Disclosure: MIT-licensed open-source MCP server for Windows debugging. It is a wrapper around CDB/WinDbg, so users remain responsible for debugger permissions, target authorization, and crash-dump handling.

Safety notes

  • WinDbg MCP starts CDB processes and can run arbitrary WinDbg commands supplied through the MCP tool call.
  • Remote debugging tools can attach to live targets, inspect process state, send CTRL+BREAK, and interrupt execution.
  • Crash dump analyses and remote connections remain active until closed or the CDB process is terminated.
  • Symbol paths can fetch symbols from network symbol servers and can disclose module names, versions, and debugging context.
  • Do not expose streamable HTTP mode beyond a trusted host without transport security, authentication, and network controls.

Privacy notes

  • Crash dumps can contain memory, stack values, command lines, environment variables, file paths, registry data, sensitive values, PII, customer data, and proprietary code or symbols.
  • WinDbg output, dump paths, remote connection strings, symbol paths, module lists, thread stacks, exception records, and debugger command output may be visible to the MCP client and model provider.
  • Verbose logs, command transcripts, dump triage prompts, and saved analysis results can retain sensitive crash data after use.
  • Redact dump paths, remote endpoints, symbols, process details, and command output before sharing logs, screenshots, or PR comments.

Prerequisites

  • Windows environment with Debugging Tools for Windows, CDB, or WinDbg installed.
  • Python 3.10 or newer.
  • MCP client configuration access for stdio or reviewed streamable HTTP transport.
  • Crash dumps, dump directories, or remote debugging targets you are authorized to inspect.
  • Reviewed symbol path, CDB path, command timeout, and remote debugging policy.

Schema details

Install type
cli
Troubleshooting
No
Source repository stats
Scope
Source repo
Collection metadata
Estimated setup
15 minutes
Difficulty
advanced
Tool listing metadata
Disclosure
MIT-licensed open-source MCP server for Windows debugging. It is a wrapper around CDB/WinDbg, so users remain responsible for debugger permissions, target authorization, and crash-dump handling.
Full copyable content
{
  "mcpServers": {
    "mcp_windbg": {
      "command": "mcp-windbg",
      "env": {
        "_NT_SYMBOL_PATH": "<reviewed-symbol-path>"
      }
    }
  }
}

About this resource

Content

MCP Server for WinDbg connects Claude to Windows crash dump analysis and remote debugging through CDB/WinDbg. It can discover dump files, open crash dumps, run common triage commands, connect to remote debugging targets, execute reviewed WinDbg commands, send CTRL+BREAK, and close debugger processes when analysis is complete.

Use it for Windows crash triage, dump comparison, and debugging workflows where an engineer wants Claude to help interpret debugger output. It is not an auto-fix tool; it launches CDB and sends debugger commands on behalf of the MCP client.

Source Review

These sources were reviewed on 2026-06-06. Prefer the live repository, README, PyPI metadata, license, package metadata, server manifest, MCP server source, CDB process wrapper, CLI entry point, and triage prompt for current setup and behavior.

Features

  • Run a stdio MCP server with mcp-windbg or python -m mcp_windbg.
  • Use optional streamable HTTP transport for reviewed local or controlled deployments.
  • List Windows crash dump files from a configured or selected directory.
  • Open a crash dump and run common analysis commands.
  • Connect to remote debugging targets with CDB.
  • Execute custom WinDbg commands against a dump or remote connection.
  • Send CTRL+BREAK to an active remote debugging target.
  • Close crash dump and remote debugging targets to release resources.
  • Configure CDB executable path, symbol path, command timeout, and verbose mode.

Installation

Install from PyPI:

pip install mcp-windbg

Configure a stdio MCP client:

{
  "mcpServers": {
    "mcp_windbg": {
      "command": "mcp-windbg",
      "env": {
        "_NT_SYMBOL_PATH": "<reviewed-symbol-path>"
      }
    }
  }
}

If the CDB executable is not auto-detected, pass a reviewed CDB_PATH or use the documented command-line flag for a custom CDB path.

Use Cases

  • Ask Claude to list available crash dumps in an approved dump directory.
  • Open a dump and summarize exception, thread, stack, and module output.
  • Run reviewed commands such as stack inspection, module listing, or heap analysis.
  • Compare multiple dumps for repeated failure patterns.
  • Connect to a remote debugging target when live debugging is authorized.
  • Interrupt a hanging remote target with CTRL+BREAK and inspect thread state.

Safety and Privacy

Debugger access is powerful. Use WinDbg MCP only on dumps, directories, and remote targets you are authorized to inspect. Review every command before it is sent to CDB, especially commands that modify debugger state, interrupt live targets, load extensions, or disclose broad memory and environment details.

Crash dumps often contain sensitive memory and diagnostic context. Treat dump files, debugger output, symbol paths, remote connection strings, module names, stack traces, command logs, and analysis summaries as confidential unless they have been sanitized for sharing.

Duplicate Check

No svnscha/mcp-windbg, WinDbg MCP Server, CDB MCP server, mcp-windbg, or matching source URL entry was found in content/mcp or README.md.

Source citations

Add this badge to your README

Show that WinDbg MCP Server is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.

Listed on HeyClaude
[![Listed on HeyClaude](https://heyclau.de/badge/mcp/windbg-mcp-server.svg)](https://heyclau.de/entry/mcp/windbg-mcp-server)

How it compares

WinDbg MCP Server side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.

Field

MCP server that connects Claude to Windows CDB/WinDbg for crash dump discovery, dump triage, remote debugging targets, custom debugger commands, debugger cleanup, and CTRL+BREAK interrupts.

Open dossier

Official Agentset MCP server that lets Claude retrieve cited knowledge-base results from an Agentset namespace through the `knowledge-base-retrieve` tool, with optional tenant scoping and custom tool descriptions.

Open dossier

PortSwigger's Burp Suite MCP Server extension connects Burp Suite to MCP clients through an SSE server or packaged stdio proxy for request, Repeater, Intruder, history, scanner, Collaborator, and configuration workflows.

Open dossier

Local-first codebase intelligence MCP server that indexes repositories with tree-sitter, stores searchable chunks in DuckDB, and gives Claude semantic search, regex search, daemon status, and deep code research tools.

Open dossier
Next steps
Trust
Review statusNot reviewedNot reviewedNot reviewedNot reviewed
Package trustPackage not verifiedPackage not verifiedPackage not verifiedPackage not verified
Source provenanceSource-backedSource-backedSource-backedSource-backed
Submitteroktofeesh1oktofeesh1oktofeesh1oktofeesh1
Install riskReview firstReview firstReview firstReview first
Notes Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓
BrandAgentset logoAgentsetBurp Suite MCP Server logoBurp Suite MCP ServerChunkHound logoChunkHound
Categorymcpmcpmcpmcp
SourceSource-backedSource-backedSource-backedSource-backed
AuthorsvnschaAgentsetPortSwiggerChunkHound
Added2026-06-062026-06-062026-06-062026-06-06
Platforms
Harness
Source repo
Safety notesWinDbg MCP starts CDB processes and can run arbitrary WinDbg commands supplied through the MCP tool call. Remote debugging tools can attach to live targets, inspect process state, send CTRL+BREAK, and interrupt execution. Crash dump analyses and remote connections remain active until closed or the CDB process is terminated. Symbol paths can fetch symbols from network symbol servers and can disclose module names, versions, and debugging context. Do not expose streamable HTTP mode beyond a trusted host without transport security, authentication, and network controls.The MCP server sends Claude's retrieval queries to the Agentset API using the configured API key and namespace. The `knowledge-base-retrieve` tool can return up to 100 results per call and can rerank results by relevance. Namespace and tenant selection control which indexed documents are searchable; review them before connecting a shared agent. API keys should be scoped, rotated, and stored only in the MCP server environment or a secret manager. Custom tool descriptions can influence when the model calls the retrieval tool, so review them before use in production workflows.Burp Suite MCP Server can send HTTP/1.1 and HTTP/2 requests, create Repeater tabs, send requests to Intruder, toggle Proxy Intercept, pause or resume Burp's task execution engine, and update the active message editor. In Burp Suite Professional it can also expose scanner issues and generate or poll Collaborator payloads for out-of-band testing. The extension includes approval flows for outbound HTTP requests and sensitive data access, but users can configure always-allow targets and disable some approval requirements. Configuration editing tools can import project-level or user-level Burp options when enabled in the extension, which can change proxy, scanner, target, and other Burp behavior. Use only on systems and applications where testing is authorized; active requests, Intruder traffic, scanner workflows, and Collaborator payloads can affect third-party services. Keep the MCP server bound to trusted local interfaces and avoid exposing the SSE server to untrusted networks.ChunkHound reads source files, Markdown, text, PDFs, and supported config files under the target directory and stores indexed chunks in a local database. Realtime indexing and daemon mode can continue watching project files after the initial MCP connection. Code research and web search tools require embedding, reranking, and LLM configuration and may invoke local CLIs or external model APIs depending on settings. Exclude generated files, vendored dependencies, secrets, large artifacts, and unrelated repositories before indexing broad workspace roots. Review MCP client configuration carefully when using an absolute project path in a global Claude Desktop config.
Privacy notesCrash dumps can contain memory, stack values, command lines, environment variables, file paths, registry data, sensitive values, PII, customer data, and proprietary code or symbols. WinDbg output, dump paths, remote connection strings, symbol paths, module lists, thread stacks, exception records, and debugger command output may be visible to the MCP client and model provider. Verbose logs, command transcripts, dump triage prompts, and saved analysis results can retain sensitive crash data after use. Redact dump paths, remote endpoints, symbols, process details, and command output before sharing logs, screenshots, or PR comments.Retrieved chunks can include private documents, product specs, policies, support content, internal procedures, historical project information, or customer-specific data. Retrieval queries, namespace IDs, tenant IDs, document chunks, citations, and tool outputs may be visible to the MCP client, model provider, Agentset logs, and application telemetry. Tenant IDs are useful for data segregation, but incorrect tenant or namespace configuration can expose the wrong knowledge base. Do not paste API keys, namespace IDs, tenant IDs, or retrieved private chunks into shared issue reports, screenshots, or repository files.Proxy HTTP history, WebSocket history, Organizer items, scanner issues, request and response bodies, headers, cookies, tokens, session identifiers, and Collaborator interaction data may be returned to the MCP client. The extension can read project-level and user-level Burp configuration; upstream code filters some configuration credentials when configured, but users should still treat exported options as sensitive. MCP prompts, responses, Burp logs, and client transcripts can retain target URLs, credentials, payloads, vulnerability details, and proprietary application behavior. The stdio proxy and SSE server bridge Burp traffic into the MCP client process; keep client configs, proxy paths, and Burp project files protected.Indexed chunks, file paths, symbols, comments, Markdown, PDFs, configuration values, database files, daemon state, and search results can reveal proprietary source code and internal architecture. Embedding, reranking, LLM, and web search providers may receive code-derived queries or snippets if configured. Local ChunkHound database files, logs, daemon state, and MCP transcripts may retain code-derived context after the session ends. Avoid sharing ChunkHound databases, config files with API keys, verbose logs, research outputs, and screenshots from private repositories.
Prerequisites
  • Windows environment with Debugging Tools for Windows, CDB, or WinDbg installed.
  • Python 3.10 or newer.
  • MCP client configuration access for stdio or reviewed streamable HTTP transport.
  • Crash dumps, dump directories, or remote debugging targets you are authorized to inspect.
  • Agentset account or self-hosted Agentset deployment with a populated namespace.
  • Agentset API key with access to the namespace Claude should query.
  • Node.js 18.17 or newer for running the `@agentset/mcp` package.
  • Namespace ID selected with `--ns` or `AGENTSET_NAMESPACE_ID`.
  • Burp Suite Community or Professional with Java extension support.
  • Java and the `jar` command available for building and loading the extension.
  • Gradle wrapper execution allowed for building `build/libs/burp-mcp-all.jar` from source.
  • An MCP client that can connect to the Burp SSE server or run the packaged stdio proxy.
  • Python 3.10 or newer and the `uv` package manager.
  • A local repository or workspace you are authorized to index.
  • ChunkHound JSON config reviewed for database path, excludes, embeddings, and LLM provider settings.
  • Optional embedding provider credentials for semantic search, or regex-only usage when no embedding key is configured.
Install
pip install mcp-windbg
Run `npx @agentset/mcp --ns <namespace-id>` with `AGENTSET_API_KEY` set in the MCP server environment.
./gradlew embedProxyJar
uv tool install chunkhound
Config
{
  "mcpServers": {
    "mcp_windbg": {
      "command": "python",
      "args": ["-m", "mcp_windbg"],
      "env": {
        "CDB_PATH": "<optional-cdb-executable-path>",
        "_NT_SYMBOL_PATH": "<reviewed-symbol-path>"
      }
    }
  }
}
{
  "mcpServers": {
    "agentset": {
      "command": "npx",
      "args": ["-y", "@agentset/mcp@latest", "--ns", "ns_xxx"],
      "env": {
        "AGENTSET_API_KEY": "agentset_xxx"
      }
    }
  }
}
Manual-only setup:
./gradlew embedProxyJar
{
  "mcpServers": {
    "chunkhound": {
      "command": "chunkhound",
      "args": ["mcp", "/path/to/approved/project"]
    }
  }
}
Citations
ClaimUnclaimedUnclaimedUnclaimedUnclaimed
Open 4 picks in the interactive comparison tool

Related guides

Signals

Loading live community signals…

More like this, weekly

A short, calm digest of reviewed Claude resources. Unsubscribe any time.