MetasploitMCP

MetasploitMCP is an MCP server that bridges MCP clients (e.g., Claude Desktop via STDIO or other MCP clients via HTTP/SSE) to the Metasploit Framework using the Metasploit RPC service (msfrpcd). It exposes MCP tools for discovering exploit/payload modules, running exploit/auxiliary/post modules, managing sessions and listeners, and generating payload files.

Evaluated Mar 30, 2026 (21d ago)
Repo ↗ Security security penetration-testing metasploit mcp automation exploit-management
⚙ Agent Friendliness
48
/ 100
Can an agent use this?
🔒 Security
40
/ 100
Is it safe for agents?
⚡ Reliability
21
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
55
Documentation
60
Error Messages
0
Auth Simplicity
75
Rate Limits
0

🔒 Security

TLS Enforcement
20
Auth Strength
45
Scope Granularity
10
Dep. Hygiene
55
Secret Handling
70

The tool enables powerful exploitation capabilities by bridging an MCP client to Metasploit RPC. README emphasizes responsible use but does not document MCP-level auth/authorization, fine-grained permissions, or rate limiting. TLS/transport security for the MCP HTTP/SSE mode is not described beyond an MSF_SSL=false env var for Metasploit RPC. Secrets are provided via environment variables (e.g., MSF_PASSWORD), which is a better practice than hardcoding, but no additional guidance is provided about logging/handling.

⚡ Reliability

Uptime/SLA
0
Version Stability
50
Breaking Changes
0
Error Recovery
35
AF Security Reliability

Best When

In a segregated, permissioned testing lab where a user explicitly authorizes exploit execution and can review actions before they run.

Avoid When

When running in sensitive environments, without clear authorization, or as a publicly reachable service without strong network controls and operator oversight.

Use Cases

  • AI-assisted exploration of Metasploit modules (exploits, payloads)
  • Automating Metasploit exploitation workflows from an MCP-enabled assistant
  • Managing Metasploit sessions (run commands, terminate sessions)
  • Creating/managing handlers/listeners programmatically
  • Generating payloads via Metasploit RPC and saving them to disk

Not For

  • Unauthenticated/automated internet-facing deployment
  • Environments without explicit authorization for penetration testing
  • Production systems requiring strict change-control (post-exploitation alters systems)
  • Use as a general-purpose 'security scanner' without human review

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: Metasploit RPC password authentication for msfrpcd (MSF_PASSWORD / -P)
OAuth: No Scopes: No

README indicates authentication is handled by msfrpcd using a password. No separate MCP-level auth is documented for the MCP server itself.

Pricing

Free tier: No
Requires CC: No

Open-source (Apache-2.0). Operational cost depends on environment and any LLM/MCP client usage.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • High-risk actions can be executed (run_exploit, run_post_module, start_listener). Ensure the agent/operator has strong gating and human approval.
  • Requires Metasploit RPC (msfrpcd) to be running and reachable; incorrect MSF_SERVER/MSF_PORT or password will break functionality.
  • If used with STDIO (e.g., Claude Desktop), ensure the client process environment variables (MSF_PASSWORD, PAYLOAD_SAVE_DIR) are set correctly.
  • Payload generation writes files locally; agents should avoid repeated payload generation that overwrites or fills disk.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for MetasploitMCP.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered