ReversecoreCAUTION
A security-first MCP server that empowers AI agents to perform automated reverse engineering, malware analysis, forensics, vulnerability research, and SAST — powered by Radare2, YARA, LIEF, Capstone, and more.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
AI-Powered Reverse Engineering & Security Analysis via Model Context Protocol
An MCP server that gives AI assistants like Claude and Cursor the ability to perform reverse engineering, malware analysis, vulnerability research, digital forensics, and source code auditing through natural language.
[](https://github.com/sjkim1127/ReversecoreMCP/actions/workflows/main.yml) [](https://www.python.org/) [](LICENSE) [](#testing) [](#testing) [](https://github.com/jlowin/fastmcp) [](https://pypi.org/project/reversecore-mcp/) [](https://github.com/sjkim1127/ReversecoreMCP/pkgs/container/reversecoremcp) [](https://scorecard.dev/viewer/?uri=github.com/sjkim1127/ReversecoreMCP) [](https://hvtracker.net/agents/reversecore-mcp)
[](https://youtu.be/wJGW2bp3c5A) [](https://safeskill.dev/scan/sjkim1127-reversecore-mcp)
Table of Contents
- What is Reversecore MCP?
- Architecture
9bde4640871eOBSERVED · 2026-10-06Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add reversecore-mcp -- None reversecore-mcp==3.0.5
claude mcp add reversecore_mcp:3.0.5 -- docker run -i --rm ghcr.io/sjkim1127/reversecore_mcp:3.0.5:None
Exposed tools (48)
39 read · 9 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
Radare2_analyze | read | |
Radare2_calculate | read | |
Radare2_close_file | read | |
Radare2_decompile_function | read | |
Radare2_disassemble | read | |
Radare2_disassemble_function | read | |
Radare2_get_current_address | read | |
Radare2_get_function_prototype | read | |
Radare2_list_all_strings | read | |
Radare2_list_classes | read | |
Radare2_list_decompilers | read | |
Radare2_list_entrypoints | read | |
Radare2_list_functions | read | |
Radare2_list_functions_tree | read | |
Radare2_list_imports | read | |
Radare2_list_libraries | read | |
Radare2_list_methods | read | |
Radare2_list_sections | read | |
Radare2_list_strings | read | |
Radare2_list_symbols | read | |
Radare2_open_file | read | |
Radare2_rename_flag | write | |
Radare2_rename_function | write | |
Radare2_run_command | write | |
Radare2_set_comment | write | |
Radare2_set_function_prototype | write | |
Radare2_show_function_details | read | |
Radare2_show_headers | read | |
Radare2_use_decompiler | read | |
Radare2_xrefs_to | read | |
complete_memory_session | read | |
create_memory_session | write | |
divide_numbers | read | if b == 0: |
dummy | read | A dummy tool |
find_similar_patterns | read | |
get_memory_session_detail | read | |
get_relevant_context | read | |
get_server_health | read | |
get_tool_metrics | read | |
list_memory_sessions | read | |
multi_step_decompilation | read | if ctx: |
n | read | d |
ping | read | return |
recall_memory_item | read | |
resume_memory_session | read | |
save_memory_item | write | |
save_pattern | write | |
update_memory_session_time | write |
Trust audit
CAUTIONgrade F · trust 46/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (5 observation(s))
- Network
- declared (10 observation(s))
- Shell
- declared (2 observation(s))
- Dependencies
- pinned
- Secrets in source
- found
Findings (25)
module = importlib.import_module(module_path)
module = importlib.import_module(name)
if any(kw in caps_lower for kw in ("network", "http", "connect", "socket", "beacon", "c2")):"exfiltration",
"exfiltration",
"beacon": "C2 beaconing pattern",
"beacon",
# ALLOWED_ORIGINS=http://localhost:3000,http://127.0.0.1:3000
"ptrace": "[!] Process Injection / Debugger",
"IsDebuggerPresent": "[!] Anti-Debugging",
ApiSymbol("kernel32.dll", "IsDebuggerPresent", "BOOL IsDebuggerPresent()"),"IsDebuggerPresent",
"isdebuggerpresent": (
api_key = "rc_secret_test_token_12345"
poc_minimized.bin
poc_raw.bin
seed_valid.bin
poc_minimized.bin
poc_raw.bin
.pre-commit-config.yaml
.trivyignore
importlib.import_module(m)
else __import__(n, *a, **kw)
assert importlib.import_module(legacy_path) is importlib.import_module(target_path)
"eval(", # arbitrary code evaluationGates applied: no_behavioural_pass.
9bde4640871efull audit observations/trust-audit/mcp-server/sjkim1127__reversecore.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-06 | 9bde4640871e | CAUTION | F | 46 | first audit |
Questions
What is the Reversecore MCP server?
A security-first MCP server that empowers AI agents to perform automated reverse engineering, malware analysis, forensics, vulnerability research, and SAST — powered by Radare2, YARA, LIEF, Capstone, and more.
What tools does Reversecore expose?
48 in total: 39 read-only, 9 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Reversecore safe to connect to an agent?
With care. The audit graded it F (46/100) and found 25 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does Reversecore need?
It reads MCP_API_KEY and REPORT_SMTP_PASSWORD from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Reversecore run?
It speaks sse, stdio and streamable-http, so it runs as a local process your client starts. It is published on PyPI as reversecore-mcp.
How current is this page?
The grade is for one exact copy of the source (9bde4640871e), read on 2026-10-06. The repository is watched and re-audited when it changes.