projtool
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
projtool
Status: M0–M5 complete, plus the post-M5 v3→v4 container-layout refactor. 34 MCP tools shipped; ~1970 unit + ~110 integration tests. The full MNIST workflow (retrofit → experiment → train → report → image build) runs end to end. See
docs/development/M1-M5-roadmap.mdfor milestone detail.
projtool is a Python package + Claude Code MCP server that supports a single ML researcher running experiments across a local development machine and remote AutoDL GPU containers.
A retrofitted project lives under a single container directory (v4 layout):
<container>/code/main/— the git repo holding model code. Each experiment gets anexp/<topic>branch in a sibling worktree under<container>/code/.<container>/output/— training products (metrics, figures, manifests). Synced from the remote via mutagen, large binary artifacts filtered out.<container>/docs/— an independent git repository holding analysis reports, organized by code-repo branch namespace; cross-branch summaries go insummary/.<container>/data/— datasets (may be a symlink to a NAS path).
Day zero: the user runs projtool setup once. From then on, every action
goes through mcp__projtool__* tool calls in Claude Code: experiment
creation, training launch, run polling, report writing, AutoDL instance
lifecycle, and project-image builds.
Documentation
docs/product-spec.md— what projtool is, design decisions, scope.docs/workflow.md— the workflow this tool exists to automate.docs/architecture.md— implementation design.docs/handbook.md— development handbook, conventions, anti-patterns.docs/development/M1-M5-roadmap.md— milestone breakdown.docs/development/retrofit-design.md— M3 detailed design.docs/development/autodl-module-plan.md— M0 detailed design.docs/development/v3-to-v4-changelog.md— the v3→v4 container-layout refactor.
Related MCP server: mlagents-mcp
Project structure
src/projtool/
├── assets/ # data shipped to user projects (templates, skills, hooks)
├── setup_cli.py # `projtool setup` entry point
├── project_layout.py # ProjectLayout — single source of truth for container paths (v4)
├── project_config.py # .proj-tool/project.toml reader/writer
├── state.py # state.json + shared pydantic schemas
├── errors.py # ProjtoolError hierarchy
├── mcp/ # MCP server + 34 tool handlers (mcp/tools/), manifest + report templates
├── retrofit/ # detect + write_template + check/apply upgrade
├── autodl/ # AutoDL API client + instance lifecycle
├── git_ops/ # subprocess wrappers for git, worktrees, docs repo
├── mutagen/ # subprocess wrappers for mutagen code/output/data sync sessions
├── ssh/ # subprocess wrappers for ssh / remote exec
└── diagnose/ # health-check helpers (stale-state detection)The assets/ tree is data, not code. It gets packaged with the wheel and
read at runtime via importlib.resources, then copied into user projects
during retrofit. See CLAUDE.md for the asset/code boundary.
Development
Requires Python 3.11+.
git clone <this-repo>
cd projtool
python -m venv .venv
source .venv/bin/activate # Linux/macOS
# .venv\Scripts\activate # Windows
pip install -e ".[dev]"
pytestStatus
Milestone | Scope | Status |
M0 |
| ✅ Done — see |
M1 | setup CLI + MCP server skeleton + instance lifecycle | ✅ Done |
M2 |
| ✅ Done |
M3 | retrofit (detect + write_template + check/apply upgrade) | ✅ Done |
M4 | reports + worktree management ( | ✅ Done |
M5 | image build + remote exec + full MNIST e2e | ✅ Done |
post-M5 | v3 → v4 container-layout refactor ( | ✅ Done |
See docs/development/M1-M5-roadmap.md for what each milestone covers.
License
MIT.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Work on your own computers from Claude or ChatGPT: run commands, edit and search files.
Source-checked CLI guides and model-aware planning for Claude Code, Codex, and Grok Build.
Research-backed lint + generation for agent context files (CLAUDE.md, AGENTS.md) + prompt enhancer.
AI cloud for agents: launch GPUs, run jobs that stop their own billing, schedule runs.
Related MCP Servers
- AlicenseBqualityDmaintenanceEnables Claude Code to interact with Jupyter notebooks, perform semantic search over knowledge files, and manage research projects.334MIT
- FlicenseAqualityDmaintenanceControls Unity ML-Agents training runs from Claude Code, enabling launch, stop, resume, monitor, compare, and export via natural language.18-
- AlicenseNot gradedqualityDmaintenanceManages AutoDL GPU cloud instances, including lifecycle management, SSH operations, file transfer, and GPU monitoring.3MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents and MCP clients to manage AutoDL GPU instances programmatically, including creating, listing, powering on/off, executing commands, transferring files, and enforcing automatic shutdown.42 npm4MIT