paperassist
Related Servers
Alternatives to paperassist
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI-assisted scientific research workflow management through MCP, including project creation, ideation, experiment execution, and artifact handling, with integration for ChatGPT, Codex, and Claude Code.Apache 2.0
- AlicenseAqualityBmaintenanceEnables AI agents and MCP clients to run research as an explicit scientific process: forming hypotheses, designing and executing sealed experiments, capturing observations and artifacts, linking claims to supporting evidence, and reviewing provenance. Exposes coordinated MCP services so users can inspect, reproduce, and audit every step from question to conclusion rather than trusting an opaque final answer.4621Apache 2.0
- AlicenseNot gradedqualityBmaintenanceEnables MCP hosts to run auditable multi-agent work through a SQLite task registry, DAG orchestration, three collaboration modes (pipeline, iterative refinement, and proposal voting), human-in-the-loop approvals, an enforced sandbox, compliance scanning, and long-term memory. Exposes these capabilities as 36 tools so every consequential step stays gated behind a human checkpoint.AGPL 3.0
- FlicenseBqualityBmaintenanceEnables deterministic, harness-neutral research workflows by unifying research object identity, evidence receipts, claim-evidence graphs, and append-only decision logs, along with specialized scholarly skills for literature analysis, reproducibility audits, and multi-agent review.18660 PyPI1-
- AlicenseNot gradedqualityAmaintenanceEquips AI assistants and MCP clients with software development tooling for deep research, codebase mapping, PRD and user story generation, project scaffolding, and multi-step workflow execution. It also provides AI-native task management and context curation, usable through an MCP server, a natural-language CLI, or an interactive REPL.42 npmMIT
- AlicenseAqualityBmaintenanceEnables AI agents to manage projects, roadmaps, periods, and tasks through MCP tools, backed by a local SQLite database with schema validation.20MIT
TDQS
Scored across 16 tools
The surface splits into two near-parallel families: pack_scaffold/pack_plan/pack_task/pack_import and writing_pack/writing_plan/writing_task/writing_import, which differ mainly by domain (ideation/experiment vs writing) and are easy to cross-select. Additionally research_os bundles corpus_bind, claim_audit, quality_score and planning, so the boundary between the composite and the individual tools is blurry. Descriptions do clarify intent, which keeps this from being worse.
All snake_case, but conventions are mixed: noun_status (harness_status), verb_noun (pack_scaffold, corpus_bind, claim_audit), and a bare name (research_os). More importantly the same conceptual operations appear under two different prefixes (pack_plan vs writing_plan, pack_import vs writing_import), which reads as inconsistent rather than a single scheme.
16 tools for an academic-writing pipeline is at the heavy end of the acceptable range. The count is inflated by two nearly identical four-tool families, so some tools are redundant rather than each earning a distinct slot.
The lifecycle is well covered: scaffolding, planning, task retrieval, result import, corpus binding, claim auditing, scoring, revision verification, journal formatting, and patching. Minor gaps exist — no tool to list or remove existing packs/artifacts, making discovery and cleanup awkward.