mcghidra/pyproject.toml
Ryan Malloy c747abe813
Some checks failed
Build Ghidra Plugin / build (push) Has been cancelled
feat: Add cursor-based pagination with grep filtering
- Implement pagination system for large responses (10K+ items)
- Add grep/regex filtering capability to results
- Session isolation for multi-client MCP scenarios
- Cursor management tools (next, list, delete, delete_all)
- Upgrade to mcp>=1.22.0 for FastMCP Context support
- Switch to date-based versioning (2025.12.1)
- Add prominent _message field to guide LLMs on cursor usage

10 tools with pagination support:
- functions_list - list all functions
- functions_decompile - decompiled code (line pagination)
- functions_disassemble - assembly (instruction pagination)
- functions_get_variables - function variables
- data_list - defined data items
- data_list_strings - string data
- xrefs_list - cross-references
- structs_list - struct types
- analysis_get_callgraph - call graph edges
- analysis_get_dataflow - data flow steps
2025-12-02 09:53:23 -07:00

22 lines
575 B
TOML

[project]
name = "ghydramcp"
version = "2025.12.1"
description = "AI-assisted reverse engineering bridge: a multi-instance Ghidra plugin exposed via a HATEOAS REST API plus an MCP Python bridge for decompilation, analysis & binary manipulation"
readme = "README.md"
requires-python = ">=3.11"
dependencies = [
"mcp>=1.22.0",
"requests>=2.32.3",
]
[project.scripts]
ghydramcp = "bridge_mcp_hydra:main"
[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"
[tool.hatch.build.targets.wheel]
packages = ["."]
only-include = ["bridge_mcp_hydra.py"]