← Index

methods-mcp

io.github.FlynnLachendro/methods-mcp·v0.1.7·Other

MCP server for structured methods extraction + reproducibility heuristics on academic papers.

Trust verdict · v1 advisory · method
NOT YET SCREENEDno verdict on file

Verdict not yet evaluated for this tool. The semantic screen takes adversarial cases first; coverage rolls out as the corpus expands (15/150 labels to graduation). The deterministic conformance probe is built but has not yet run on the public corpus, so a recorded verdict here is REVIEW or UNVERIFIED, never a clearing ALLOW. Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: the eval, four-state verdict, honest limits.

Own this server? Screen its description →

Environment variables
ANTHROPIC_API_KEY
requiredsecret

Required for LLM-driven extraction tools (extract_methods, summarize_paper, methods_repro_review).

GITHUB_TOKEN
secret

Optional. Raises the GitHub REST API rate limit used by reproducibility assessment.

METHODS_MCP_MODEL

Override the default Claude model (default: claude-sonnet-4-6).

MCP quality score · maturity, not trust · methodology
freshness
23
completeness
20
installability
25
documentation
15
stability
5
Alternatives in Other