Repository navigation
feat: add MCP server support for agent integration - #55
Merged
Merged
Conversation
Add MCP (Model Context Protocol) server so LLM agents can programmatically query PyTorch memory snapshots without shelling out to CLI commands. - src/pt_snap_cli/api.py: SnapshotAnalyzer service layer (no MCP dep) - src/pt_snap_cli/mcp/server.py: FastMCP server with 5 tools, 1 resource, 1 prompt - pyproject.toml: add mcp optional dependency and pt-snap-mcp entry point - tests/test_api.py, tests/test_mcp_server.py: 23 new tests Tools exposed: get_focus, set_focus, list_templates, get_template_info, execute_query. Backward compatible — existing CLI unchanged. Fixes #54
CI installs only core + dev dependencies. Having mcp as optional meant 'pip install -e .[dev]' skipped it, causing all MCP tests to fail with ModuleNotFoundError.
Update README (EN/ZH), quickstart guides, and add dedicated MCP docs covering tools, resources, prompts, and usage workflow.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
📝 Description
Add MCP (Model Context Protocol) server support so LLM agents (Claude Desktop, Cursor, etc.) can programmatically query PyTorch memory snapshots without shelling out to CLI commands.
New architecture layer:
api.py—SnapshotAnalyzerservice layer (no MCP dependency, reusable by CLI and MCP)mcp/server.py— FastMCP server with 5 tools, 1 resource, 1 promptmcpoptional dependency —pip install pt-snap-cli[mcp]🔗 Related Issue
Fixes #54
🧪 Testing
test_api.py,test_mcp_server.py)✅ Checklist
📋 Additional Notes
MCP Tools Exposed
get_focusset_focuslist_templatesget_template_infoexecute_queryUsage