Skip to main content
Glama
Sign In
rison1337

x64dbg MCP

by rison1337
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

FindOEP

Locates the Original Entry Point of packed Windows executables using dynamic tracing, then optionally writes and verifies an unpacked dump for recovery.

Instructions

Find the Original Entry Point (OEP) of a packed executable and, optionally, produce a VERIFIED unpacked dump.

Engine: a packer-agnostic dynamic approach for the unpack-in-memory-then-jump class (UPX, ASPack, FSG, MPRESS, PECompact, Petite, simple crypters):

  1. ESP-anchor fast-forward -- a hardware breakpoint on the stub's saved register slot skips past the decompression loop and is immune to the page writes that defeat memory breakpoints.

  2. Section-hop conditional trace -- single-steps in the engine until execution enters a non-stub executable section (the OEP). Virtualizing protectors have no generic recoverable OEP contract here; they are reported honestly via isLikelyVirtualized rather than faked. The optional virtualization research backend is disabled in this build.

When dump_to_path is set, the dump is written via Scylla and VERIFIED before ok:true (entry moved out of the packer section to the OEP, IAT resolved, imports richer than the packed baseline). The raw memory dump is always kept, so a failed verification still leaves something for manual recovery.

timeline_to_path optionally writes a canonical unpack-workflow-v1 evidence artifact. Returns {ok, status, stages, artifacts, oepAddr, detectedVia, confidence, moduleBase, moduleSize, packerEntry, verified, reason, rawDumpPath, isLikelyVirtualized, ...}.

Input Schema

NameRequiredDescriptionDefault
timeout_msNo
dump_to_pathNo
packer_sectionNo
timeline_to_pathNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.9

TDQS

A4/5.0
Behavior4/5

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

Annotations (readOnlyHint=false, openWorldHint=true, destructiveHint=false, non-idempotent) are consistent, and the description adds substantial behavior beyond them: it writes a dump via Scylla only after verification, always retains the raw memory dump, writes an optional evidence artifact, and declines to fake results for virtualized targets. It omits prerequisites (debug session/process spawn) and timeout behavior, keeping it from a 5.

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

Conciseness4/5

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

Key purpose leads, followed by scoping, method, and output notes. The engine internals (ESP-anchor fast-forward, section-hop trace) are longer than an agent needs simply to select the tool, which costs a point, but nothing is redundant and the ordering is sensible.

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

Completeness4/5

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

For a complex, no-output-schema tool, the description compensates well by enumerating return fields (ok, status, stages, oepAddr, verified, rawDumpPath, isLikelyVirtualized, ...) and explaining the verification gate and artifact retention. The uncosted gaps are the untouched timeout_ms and packer_section parameters and unstated execution prerequisites.

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

Parameters2/5

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

Schema description coverage is 0%, so the description carries the full burden, yet it only addresses half the parameters. dump_to_path and timeline_to_path get real semantics (a Scylla-verified dump; a canonical unpack-workflow-v1 artifact), but timeout_ms and packer_section are never mentioned in the description or the schema.

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?

Opens with a specific verb, resource and scope: 'Find the Original Entry Point (OEP) of a packed executable and, optionally, produce a VERIFIED unpacked dump.' It also distinguishes itself from nearby siblings (DumpPeFromMemory, ValidateDump) by naming the target class and the verification contract.

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

Usage Guidelines4/5

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

Specifies the applicable target class (UPX, ASPack, FSG, MPRESS, PECompact, Petite, simple crypters) and an explicit when-not: virtualizing protectors have no generic recoverable OEP contract and are reported via isLikelyVirtualized instead of being unpacked. No sibling alternative is named directly, so it stops short of a 5.

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

Deploy Server

Other Tools