BinAssist (Binary Ninja)
BinAssistMCP provides a complete bridge between Binary Ninja and Large Language Models through dual transport support (SSE and STDIO), enabling AI-assisted reverse engineering workflows. Built by Jason Tang using Python with FastMCP, it exposes over 40 Binary Ninja tools including decompilation, IL analysis, symbol management, type system manipulation, and cross-reference analysis, while supporting multi-binary sessions with automatic context management. The implementation integrates directly as a Binary Ninja plugin with auto-startup capabilities and configurable settings, making it valuable for security researchers, malware analysts, and reverse engineers who want to leverage AI assistance for binary analysis tasks like vulnerability research, code understanding, and automated documentation generation.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- security
- Source
- PulseMCP
- Repository
- github.com/symgraph/binassistmcp
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve BinAssist (Binary Ninja) from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.