pulsemcp verified Safe content atomic mcp-remote

Ghidra

GhidraMCP by LaurieWired bridges the Ghidra reverse engineering platform with AI assistants through a dual-component architecture: a Java plugin that runs an embedded HTTP server within Ghidra (configurable port, defaults to 8080) and a Python MCP server that translates between the HTTP API and MCP protocol. The implementation exposes core Ghidra functionality including function decompilation, disassembly, symbol management, cross-reference analysis, string extraction, and program modification capabilities like renaming functions/variables and setting prototypes. Built for Ghidra 11.3.2 with Maven packaging and GitHub Actions CI/CD, it supports multiple MCP clients (Claude Desktop, Cline, 5ire) through both stdio and SSE transports, enabling AI-assisted reverse engineering workflows where language models can autonomously analyze binaries, understand program structure, and suggest meaningful names and annotations based on code patterns and context.

Cognium trust score
100%
Tier
Verified

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 2026-09-19.

Scan details: Circle-IR · 2026-09-19 · Appeal

View full trust & usage report →

Metadata

Version
1.0.0
Skill type
atomic
Execution layer
mcp-remote
Category
version-control
Source
PulseMCP
Author type
human
Last scanned
2026-09-19
Updated
2026-09-19
View source Find related skills

Use via MCP

MCP

Resolve Ghidra 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
Swap --scope user for --scope project to commit it to .mcp.json.

Search SkillsRegistry