Skip to content
Agentmart
Submit a tool

Reversecore MCP

Security-first MCP server for reverse engineering, malware analysis, forensics, and SAST.

Connector by sjkim1127 · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)★ 212
Write a review

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/sjkim1127-reversecore-mcp

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Security-first MCP server for reverse engineering, malware analysis, forensics, and SAST.

Use cases: security-scanning, debugging

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools
29 read · 13 write · 1 delete · 8 not yet classified
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Tools by what they do 51

Read from the source code; the running server may list different tools.

Read 29 · Look things up without changing anything.

  • audit_source_code
  • find_similar_patterns
  • get_job_result
  • get_memory_session_detail
  • get_relevant_context
  • get_server_health
  • get_tool_metrics
  • list_memory_sessions
  • Radare2_calculate
  • Radare2_decompile_function
  • Radare2_disassemble_function
  • Radare2_get_current_address
Show 17 more tools
  • Radare2_get_function_prototype
  • Radare2_list_all_strings
  • Radare2_list_classes
  • Radare2_list_decompilers
  • Radare2_list_entrypoints
  • Radare2_list_functions
  • Radare2_list_functions_tree
  • Radare2_list_imports
  • Radare2_list_libraries
  • Radare2_list_methods
  • Radare2_list_sections
  • Radare2_list_strings
  • Radare2_list_symbols
  • Radare2_show_function_details
  • Radare2_show_headers
  • Radare2_xrefs_to
  • recall_memory_item

Write 13 · Create, change, send or run things.

  • complete_memory_session
  • create_memory_session
  • cve_fuzz_target
  • hunt_cve_vulnerabilities
  • Radare2_close_file
  • Radare2_rename_flag
  • Radare2_rename_function
  • Radare2_set_comment
  • Radare2_set_function_prototype
  • Radare2_use_decompiler
  • save_memory_item
  • save_pattern
Show 1 more tools
  • update_memory_session_time

Delete 1 · Delete, drop, revoke or wipe things.

  • Radare2_run_command

Not yet classified 8 · We could not tell from the name and description.

  • cve_minimize_poc
  • cve_synthesize_harness
  • cve_triage_crash
  • Radare2_analyze
  • Radare2_disassemble
  • Radare2_open_file
  • resume_memory_session
  • verify_path_and_get_args

Files it touches

  • Any path the agent passes to its tools

Tools (51)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • audit_source_code

    Perform a security audit on a source code file (SAST). This tool analyzes source code (C, C++, Python, Go, etc.) to identify potential security vulnerabilities such as buffer overflows, injection flaws, and weak cryptography. It provides a structured breakdown of dangerous patterns found in the code to guide deeper manual or AI-driven analysis. Use this tool when you have access to original source code or when you want to analyze decompiled output exported to a file. Args: file_path: Path to the source code file. language: Optional language hint (e.g., 'c', 'python'). If None, infer…

  • complete_memory_session

    Mark an analysis session as completed with a summary. Use this when finishing an analysis to save a summary for future reference. Args: session_id: Session ID to complete summary: AI-generated summary of the analysis findings Returns: Confirmation of completion

  • create_memory_session

    Create a new memory session to store memories. Use this when starting a new reverse engineering analysis. The session name should be descriptive and follow a template format like 'malware_analysis_2024_001' or 'game_cheat_detection'. Args: name: Template name for the session (e.g., 'malware_sample_001') binary_name: Name of the binary being analyzed (optional) binary_path: Path to binary for automatic hash calculation (optional) Returns: Session information including ID for future reference

  • cve_fuzz_target

    Execute hybrid fuzzing campaign with Sanitizer tracking and angr concolic seed solver. Runs target fuzzer binary with AddressSanitizer, detects coverage stalls, and uses angr symbolic execution to solve magic byte constraints. Args: target_binary_path: Path to compiled fuzzer binary in workspace. corpus_dir: Optional directory with seed testcases. dictionary_path: Optional path to AFL++ dictionary file (.dict). max_total_time_seconds: Max fuzzing duration in seconds (default: 20s). enable_angr_concolic: Whether to trigger angr symbolic solving when stalled. timeout: M…

  • cve_minimize_poc

    Minimize crash testcase payload via delta-debugging and generate standalone PoC scripts. Bsects crash input to find the smallest reproducible byte sequence, and generates standalone Python (subprocess/pwntools) and C reproduction code. Args: binary_path: Path to target binary in workspace. crash_input_path: Path to crash-inducing input file. target_function: Optional target parser function name. timeout: Maximum execution timeout in seconds. Returns: ToolResult with minimized payload bytes and standalone PoC scripts.

  • cve_synthesize_harness

    Synthesize LibFuzzer/AFL++ C/C++ test harness and format dictionary (.dict) for target parser. Analyzes target headers, exports, and sample files to extract candidate parser functions, magic byte signatures, and generate ready-to-compile LLVMFuzzerTestOneInput harness code. Args: header_or_binary_path: Path to target header (.h), source (.c/.cpp), or binary. sample_file_path: Optional path to a valid sample file to extract dictionary tokens. target_function: Optional target function name to fuzz. timeout: Maximum execution timeout in seconds. Returns: ToolResult with syn…

  • cve_triage_crash

    Triage AddressSanitizer/UBSan crash log and compute CWE and CVSS v3.1 rating. Extracts bug class (heap-buffer-overflow, UAF, double-free), faulting PC, memory access type, allocation/free/crash callstacks, and calculates CVSS score and vector. Args: crash_log_or_text: Raw ASan log text or path to crash log file. timeout: Maximum execution timeout in seconds. Returns: ToolResult with structured crash diagnostics, CWE mapping, and CVSS v3.1 score.

  • find_similar_patterns

    Find similar patterns from previous analyses. Use this to check if current findings match anything from past analyses. Enables knowledge transfer across projects. Args: pattern_signature: Pattern to search for pattern_type: Limit to specific type (optional) current_session_id: Exclude current session from results limit: Maximum results Returns: List of similar patterns with session context

  • get_job_result

    Retrieve the status and result of a background job from the task queue. Args: job_id: The ID of the queued job to check. Returns: ToolResult containing status details or the job output if finished.

  • get_memory_session_detail

    Get complete details and context for a specific session. Use this when resuming an analysis or reviewing past work. Returns all memories and patterns associated with the session. Args: session_id: Session ID to retrieve Returns: Full session context including all memories and patterns

  • get_relevant_context

    Get relevant context from past analyses for current work. Use this proactively when analyzing something new to check if there's relevant knowledge from previous sessions. Args: description: Description of what you're currently analyzing current_session_id: Current session to exclude limit: Maximum relevant items Returns: Relevant memories from past sessions

  • get_server_health

    Get the current health status and resource usage of the MCP server. Use this to monitor the server's uptime, memory consumption, and tool execution statistics. Returns: ToolResult containing: - uptime_seconds: Server uptime - memory_usage_mb: Current memory usage in MB - status: 'healthy' or 'degraded' - tool_stats: Summary of tool execution success/failure

  • get_tool_metrics

    Get detailed execution metrics for specific or all tools. Args: tool_name: Optional tool name to filter results Returns: Detailed metrics including execution times, call counts, and error rates.

  • hunt_cve_vulnerabilities

    Run one-click CVE hunting against a compiled LibFuzzer target executable. This pipeline does not compile source or header files. Generate and compile a harness for those targets separately, then pass the resulting executable here. Performs end-to-end vulnerability discovery: 1. Hybrid fuzzing and angr concolic branch solving 2. ASan crash triage, CWE mapping, and CVSS v3.1 scoring 3. Testcase minimization and standalone PoC generation 4. Vendor-ready Security Advisory Markdown report draft Args: target_path: Path to a compiled LibFuzzer executable. Generate and compile a harness for …

  • list_memory_sessions

    List all analysis sessions with timestamps and status. Use this to see what analyses have been done before, or to find a session to resume. Args: status: Filter by status ('in_progress', 'completed', 'paused') limit: Maximum number of sessions to return Returns: List of sessions with metadata

Show 36 more tools
  • Radare2_analyze

    Run binary analysis with optional depth level. Args: file_path: Path to the binary file level: Analysis depth as an INTEGER from 0 to 4 (default: 2). IMPORTANT: Must be an integer. Do NOT pass strings like "full", "deep", or "auto" — those will be rejected. 0 = aa (basic, fastest) 1 = aaa (auto) 2 = aaaa (experimental, recommended default) 3 = aaaaa (deep, slow) 4 = aaaaaa (very deep, very slow) arch: Optional architecture (e.g., 'mips', 'arm64', 'riscv', 'x86_64') bits: Optional architecture bits (e.g., 32, 64) Returns…

  • Radare2_calculate

    Evaluate a math expression using radare2's number parser. Useful for: 64-bit math, resolving addresses for symbols, avoiding hallucinated results. Args: file_path: Path to the binary file expression: Math expression to evaluate (e.g., "0x100 + sym.flag - 4") Returns: Calculated result in hex and decimal

  • Radare2_close_file

    Close the currently open radare2 session for a file. Args: file_path: Path to the file to close Returns: Status of the close operation

  • Radare2_decompile_function

    Show C-like pseudocode of the function at the given address. Use this to inspect code in a function. Do not run multiple times on the same offset. Includes smart line windowing and function summary header. Args: file_path: Path to the binary file address: Address of the function to decompile line_offset: Starting line offset for windowed pseudocode (default: 0) max_lines: Maximum lines of pseudocode per window (default: 200) cursor: Legacy pagination cursor (overridden by line_offset if provided) page_size: Legacy page size (overridden by max_lines if provided) Retur…

  • Radare2_disassemble

    Disassemble a specific number of instructions from an address. Use this to inspect a portion of memory as code without depending on function analysis boundaries. Args: file_path: Path to the binary file address: Address to start disassembly num_instructions: Number of instructions to disassemble (default: 10, max: 1000) Returns: Disassembled instructions

  • Radare2_disassemble_function

    Show assembly listing of the function at the specified address. Args: file_path: Path to the binary file address: Address OR symbol name of the function to disassemble. Accepts hex addresses (e.g. '0x401000', '0x8d4') as well as function/symbol names (e.g. 'main', 'sym.secret_backdoor', 'sym.process_request'). Symbol names are automatically resolved to their virtual address before disassembly. format: Output format - 'compact' (compact instruction tuples [addr, mnemonic, ops, comment]) or 'raw' (raw visual text output). Default: 'compact'. …

  • Radare2_get_current_address

    Show the current seek position and function name. Args: file_path: Path to the binary file Returns: Current address and function name

  • Radare2_get_function_prototype

    Retrieve the function signature at the specified address. Args: file_path: Path to the binary file address: Address of the function Returns: Function prototype/signature

  • Radare2_list_all_strings

    Scan the entire binary for strings with optional regex filter. More thorough than list_strings, but slower. Args: file_path: Path to the binary file filter: Regular expression to filter results cursor: Pagination cursor page_size: Number of lines per page Returns: List of all strings with pagination

  • Radare2_list_classes

    List class names from various languages (C++, ObjC, Swift, Java, Dalvik). Args: file_path: Path to the binary file filter: Regular expression to filter results Returns: List of classes

  • Radare2_list_decompilers

    Show all available decompiler backends. Args: file_path: Path to the binary file Returns: List of available decompilers

  • Radare2_list_entrypoints

    Display program entrypoints, constructors and main function. Args: file_path: Path to the binary file Returns: Entrypoint information

  • Radare2_list_functions

    List all functions discovered during analysis. Args: file_path: Path to the binary file only_named: If true, exclude functions with numeric suffixes filter: Regular expression to filter results Returns: List of functions with addresses and names

  • Radare2_list_functions_tree

    List functions and their successors (call tree). Args: file_path: Path to the binary file Returns: Function call tree

  • Radare2_list_imports

    List imported symbols. Note: Use list_symbols for addresses with sym.imp. prefix. Args: file_path: Path to the binary file filter: Regular expression to filter results Returns: List of imports

  • Radare2_list_libraries

    List all shared libraries linked to the binary. Args: file_path: Path to the binary file Returns: List of linked libraries

  • Radare2_list_methods

    List all methods belonging to the specified class. Args: file_path: Path to the binary file classname: Name of the class to list methods for Returns: List of methods in the class

  • Radare2_list_sections

    Display memory sections and segments from the binary. Args: file_path: Path to the binary file Returns: Sections and segments information

  • Radare2_list_strings

    List strings from data sections with optional regex filter. Args: file_path: Path to the binary file filter: Regular expression to filter results cursor: Pagination cursor (line number to start from) page_size: Number of lines per page (default: 1000, max: 10000) Returns: List of strings with pagination

  • Radare2_list_symbols

    Show all symbols (functions, variables, imports) with addresses. Args: file_path: Path to the binary file filter: Regular expression to filter results Returns: List of symbols

  • Radare2_open_file

    Opens a binary file with radare2 for analysis. Call this tool before any other r2mcp tool. Use an absolute file_path. Args: file_path: Absolute path to the binary file to analyze Returns: Status of the file opening operation, including session_id

  • Radare2_rename_flag

    Rename a flag (variable or data reference) at the specified address. Args: file_path: Path to the binary file address: Address of the flag name: Current flag name new_name: New flag name Returns: Confirmation

  • Radare2_rename_function

    Rename the function at the specified address. Args: file_path: Path to the binary file address: Address of the function to rename name: New function name Returns: Confirmation

  • Radare2_run_command

    Execute a raw radare2 command directly. NOTE: Only analysis commands are allowed. Write and shell commands are blocked. Args: file_path: Path to the binary file command: The radare2 command to execute Returns: Command output

  • Radare2_set_comment

    Add a comment at the specified address. Args: file_path: Path to the binary file address: Address to add comment message: Comment text Returns: Confirmation

  • Radare2_set_function_prototype

    Set the function signature (return type, name, arguments). Args: file_path: Path to the binary file address: Address of the function prototype: Function signature in C-like syntax Returns: Confirmation

  • Radare2_show_function_details

    Display detailed information about a function. Args: file_path: Path to the binary file address: Function address (uses current if not specified) Returns: Detailed function information

  • Radare2_show_headers

    Display binary headers and file information. Args: file_path: Path to the binary file Returns: Binary header information

  • Radare2_use_decompiler

    Select which decompiler backend to use. Args: file_path: Path to the binary file name: Decompiler name (ghidra, r2dec, pdc) Returns: Confirmation or error

  • Radare2_xrefs_to

    Find all code references TO the specified address. Args: file_path: Path to the binary file address: Address to check for cross-references (hex or symbol name) limit: Maximum number of xrefs to return (default: 50) Returns: Structured list of xrefs with callers_by_function and xref_count. xref_count=0 means NO callers exist (not an error). Each xref entry contains: from, type, opcode, ref.

  • recall_memory_item

    Search and recall memories from past analyses. Use this when you need to remember something from earlier, or when the user asks about previous findings. Args: query: Search query (keywords or phrases) session_id: Limit search to specific session (optional) memory_type: Filter by type ('finding', 'pattern', 'instruction', 'context') limit: Maximum number of results (default 10) Returns: List of matching memories with context

  • resume_memory_session

    Resume a previous analysis session with full context restoration. Use this when the user says "continue where we left off" or "resume yesterday's analysis". Args: session_id: Specific session ID to resume (optional) binary_name: Find latest session for this binary (optional) Returns: Full session context for resumption Note: If neither argument provided, resumes the most recent session.

  • save_memory_item

    Save important information to long-term memory. Use this to remember: - Function addresses and their purposes - Vulnerability patterns discovered - API call sequences - User instructions and preferences - Interesting strings or structures Args: session_id: Session ID from create_memory_session memory_type: Type of memory: - 'finding': Analysis discoveries - 'pattern': Code/behavior patterns - 'instruction': User preferences/instructions - 'context': General context information category: Optional category: - 'function': Function-related info…

  • save_pattern

    Save a code/behavior pattern for cross-session similarity search. Use this when you discover a notable pattern that might appear in other samples. This enables "Hey, this looks similar to before!" Args: session_id: Current session ID pattern_type: Type of pattern: - 'api_sequence': Sequence of API calls - 'code_pattern': Assembly/code pattern - 'behavior': Behavioral pattern pattern_signature: Normalized pattern signature for matching Example: "VirtualAlloc,WriteProcessMemory,CreateRemoteThread" description: Human-readable description of the pa…

  • update_memory_session_time

    Update the cumulative analysis time for a session. Call this periodically to track how long an analysis takes. Args: session_id: Session ID duration_seconds: Additional time to add (in seconds) Returns: Confirmation

  • verify_path_and_get_args

    Run symbolic execution using angr to verify path reachability and extract inputs. Allows proving path reachability and verifying data-flow taint to a target instruction. Args: file_path: Workspace-relative or absolute path to the binary to analyze. target_addr: The target instruction address to reach (hex or integer). start_addr: Optional starting instruction address. If omitted, starts from entry point. avoid_addrs: Optional list of instruction addresses to avoid. source_addr: Optional source instruction address introducing user data. source_api: Optional name of the…

Compare and alternatives

    Featured in

    Signals

    Stars
    212
    Forks
    24
    Open issues
    6
    Contributors
    6
    Weekly downloads
    170
    Last commit
    Oct 17, 2026 (12 days ago)
    Last release
    Sep 28, 2026 (1 month ago)
    Last package publish
    Sep 28, 2026 (1 month ago)

    From GitHub (fetched Oct 24, 2026) and the package registry.

    Details

    Registry name
    io.github.sjkim1127/reversecore-mcp
    Version
    3.0.5
    Auth
    No auth
    Packages
    pypi reversecore-mcpoci ghcr.io/sjkim1127/reversecore_mcp:3.0.5
    License
    MIT
    First seen
    Oct 24, 2026
    Last checked
    Oct 24, 2026
    Cite this page

    Reversecore MCP. Agent Mart. https://agentmart.dev/connectors/sjkim1127-reversecore-mcp (last updated 2026-10-24)