Yumi Python Import Layout Evidence
Server Details
Static PyPI artifact/source import-layout evidence; no installs, execution, or resolver claims.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 3 tools
Each tool targets a clearly distinct evidence domain: network address-set comparison, PyPI wheel tag intersection, and Python import-layout comparison against GitHub sources. The descriptions explicitly delineate boundaries and non-goals, leaving little risk of misselection.
All three tools use consistent snake_case noun_evidence naming: network_set_evidence, pypi_wheel_evidence, and python_import_layout_evidence. The pattern is predictable and readable.
Three well-scoped tools fit the focused evidence-reporting purpose without redundancy. Each tool covers a distinct analytical operation, so none feels extraneous or missing for the stated scope.
The surface covers three targeted evidence workflows but is relatively narrow: there is no standalone address-set normalization tool, no source-distribution evidence tool, and no generic way to compose or export combined evidence across domains. These are minor gaps for the apparent read-only evidence scope, not blockers for the core workflows.
Available Tools
3 toolsnetwork_set_evidenceARead-onlyIdempotentInspect
Compares bounded mathematical IPv4 and IPv6 address sets and reports canonical normalized, added, removed, count, and witness evidence; it does not assess reachability, routing, security policy, configuration, or host usability.
Inputs: after (required), before (required).
pypi_wheel_evidenceBRead-onlyIdempotentInspect
Reports provider-reported filename/tag intersection for PyPI wheels; it does not perform compatibility, security, or digest verification.
Inputs: tags (required), releases (required).
python_import_layout_evidenceBRead-onlyIdempotentInspect
Compares one exact PyPI artifact with a full-commit public GitHub Python source tree and named public consumer files. Reports parser-backed static imports, ImportError fallbacks, artifact SHA-256 evidence, and bounded module-layout results; unknown or ambiguous cases stay UNKNOWN.
Inputs: source (required), release (required), targets (required), consumers (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Browser-local and CLI static evidence for deployed AI model artifacts.
Verify PyPI and npm packages, symbols, and version diffs against real artifacts. Free, no account.
Fresh PyPI install/import evidence on Linux x86_64 / CPython 3.13.
Stateless TS/JS compiler facts for agents: references, imports, impact. No repo index or OAuth.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables deterministic static analysis of Python code, providing tools to inspect classes, functions, imports, dependencies, and more, without executing the code.1MIT
- AlicenseBqualityCmaintenanceEnables read-only inspection of Python repositories through stdio tools that scan AST inventories, inspect dependency topology and entry-point flows, and verify existing lessons' citations and coverage.3MIT
- AlicenseCqualityBmaintenanceEnables coding agents to query Python source repositories for exact and variant identifier occurrences with location and syntactic role, using deterministic AST-based evidence without executing code.11MIT
- AlicenseNot gradedqualityBmaintenanceEnables local static analysis of AI deployment artifacts, producing SHA-256 hashes, serialized structure, defects, cautions, evidence gaps, and limitations without executing model code.Apache 2.0
Glama MCP Gateway
Add one secure layer between your agents and this server.