scholar-mcp
CLAUDE.md2 starsChanged yesterdayMITView on GitHub
Indexed by Repowise. Last indexed: 2026-09-10 (commit 7292fb2). Confidence: 100%. ### How to work in this repo
Files
CLAUDE.md
<!-- Add your custom instructions below. Repowise will never modify anything outside the REPOWISE markers. --><!-- Examples: coding style rules, test commands, workflow preferences, constraints --><!-- REPOWISE:START — Do not edit below this line. Auto-generated by Repowise. -->Codebase Intelligence for scholar-mcp (Repowise)
Indexed by Repowise. Last indexed: 2026-09-10 (commit 7292fb2). Confidence: 100%.
How to work in this repo
- Trust the index.
verified: truemeans the bytes were checked against the live tree, so never re-read those lines. Re-read only onbounds: "approximate",_meta.stale_warning,search_method: "bm25"orconfidence: "low";index_behind: truealone is informational. - Pre-edit, not instead-of-edit. These tools decide which files to read and edit. Claude Code requires a raw Read of any file you will Edit, and that Read is correct and expected.
- Noisy commands (tests, builds,
git log/diff, searches, listings): preferrepowise distill <cmd>— same command, exit code preserved, errors-first output. A[repowise#<ref>: N lines omitted]marker is recoverable viarepowise expand <ref>(add-q <regex>to filter); never re-run the command to see omitted output. - Recording a decision you had to reason out:
repowise decision add --title T --decision Drecords it without prompting and prints the id (--format jsonto parse it back). It landsproposed, for a person to confirm.
Tools
| Tool | When and why | |||
get_answer(question) | First call for any how/where/why question. Cite confidence: "high" or grounding: "extracted" directly; degraded means judge by retrieval_quality. symbol_bodies has live bodies. | |||
get_context(targets=[...]) | Triage card for files/modules/symbols: docs, signatures, hotspot, fix history. No source bytes — include=["skeleton"] for the whole file verified, `["callers" | "decisions"]` for depth. Batch targets. | ||
get_symbol(id, depth?) | Follow-up, not an entry point — one verified body for an id a prior response named (path.py::Name, path.py:140-180, repowise#<hex>). Never walk a file symbol by symbol; Read it. | |||
search_codebase(query) | Hybrid search, auto-routed by query shape; force with `mode=symbol | path | concept | hybrid. A hit whose sourcesare[fts]` only has no semantic agreement, so verify it. |
get_why(query, targets?) | Why the code is shaped this way: decision records, git archaeology, rationale comments. Call before a refactor or a pattern divergence. | |||
get_risk(targets, changed_files?, include?) | File history and structural reach. PR mode leads with directive; its 0-10 structural heuristic is uncalibrated, not a probability. Read typed test recommendations and coverage state first. | |||
get_change_risk(revspec?, extensions?, exclude_patterns?) | Deterministic live-diff review signal for a commit or range. Lead with benchmarked percentile/classification; the 0-10 diff-shape score is supporting, not a probability. get_risk scores paths. | |||
get_health(targets?, include?) | Defect / maintainability / performance scores and findings. Self-check the files you touched before finishing. | |||
get_dead_code(tier?, min_confidence?, safe_only?) | Confidence-tiered unreachable files / unused exports / zombie packages. For cleanup sweeps, not targeted fixes. | |||
get_overview() | Architecture map. Call once, first, in an unfamiliar repo; skip it after that. |
Architecture
repo is a scholarly research orchestration engine that ingests bibliographic metadata and unstructured document inputs, processes them through a multi-provider API pipeline (Semantic Scholar, OpenAlex, CrossRef, Google Books), and exposes enriched research artifacts via a Model Context Protocol (MCP) server for LLM-integrated analysis.
Key modules
community-0— The tests module serves as the validation and quality assurance layer of the scholar_mcp ecosystem — it consumes the core service clients…community-4— The tests module serves as the validation and quality assurance layer of the scholar_mcp system — it consumes the core logic of the…community-1— The scholar_mcp module acts as the standards-ingestion and knowledge-retrieval subsystem of the repowise architecture — it orchestrates the…community-5— The scholar_mcp module serves as the primary transport adapter and orchestration layer for the Scholar MCP subsystem, consuming…community-2— The scholar_mcp module serves as the primary transport adapter and integration layer for repowise, bridging the Model Context Protocol…community-3— The scholar_mcp module serves as the architecturally central transport adapter and tool-orchestration layer for repowise's…community-6— The scholar_mcp module serves as the transport adapter and service orchestration layer for the Scholar MCP subsystem, consuming…community-81— The tests module serves as the verification and quality assurance layer of the scholar_mcp system — it consumes the core logic defined in…
Entry points
src/scholar_mcp/server.pysrc/scholar_mcp/cli.pypackaging/mcpb/src/server.py
Files that need care (bug-fix history first, then churn — check get_risk before editing)
src/scholar_mcp/_tools_graph.py— 16 bug fixes, last fix 5 months ago (bug magnet); 2 commits/90dsrc/scholar_mcp/_tools_pdf.py— 10 bug fixes, last fix 12 days ago (bug magnet); 4 commits/90dsrc/scholar_mcp/_tools_patent.py— 9 bug fixes, last fix 12 days ago (bug magnet); 4 commits/90dsrc/scholar_mcp/_tools_books.py— 8 bug fixes, last fix 12 days ago (bug magnet); 2 commits/90dsrc/scholar_mcp/_standards_client.py— 10 bug fixes, last fix 5 months ago (bug magnet); 0 commits/90d
Code health
Three co-equal signals: defect risk 7.28/10 avg, hotspot health 5.15/10 (stable), worst scripts/gen_config_surface.py at 1.0/10 · maintainability 9.11/10 · performance risk 21 open static I/O-in-loop / N+1 findings. Detail: get_health().
Critical files:
CHANGELOG.md— change entropy — impact −3.0scripts/gen_config_surface.py— untested hotspot — impact −2.0docs/deployment/oidc.md— untested hotspot — impact −2.0docs/deployment/docker.md— untested hotspot — impact −2.0pyproject.toml— untested hotspot — impact −2.0
Commands
- Test:
pytest - Lint:
ruff check . - Format:
ruff format . - Typecheck:
mypy .
<!-- REPOWISE:END -->In this repository16 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- applying-template-updatesSkill
- authoring-issues-prsSkill
- config-contractSkill
- designing-tool-outcomesSkill
- logging-standardSkill
- releasingSkill
- repository-protectionSkill
- researching-referencesSkill
- roadmappingSkill
- self-reviewingSkill
- tool-registrationSkill
- writing-documentationSkill
- writing-model-facing-textSkill
- writing-release-notesSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.