mdreview-service
Related Servers
Alternatives to mdreview-service
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to submit work for human review over MCP or REST, then retrieve approvals, edits, or change requests without blocking. Reviewers can approve, edit, or send back items from a web or phone interface.MIT
- FlicenseNot gradedqualityDmaintenanceProvides lightweight documentation review tools including issue detection, readability scoring, style checking, and document summarization for integration with MCP-compatible clients.-
- AlicenseNot gradedqualityCmaintenanceEnables LLM agents to propose non-destructive CriticMarkup edits, manage threaded review comments, and inspect Markdown efficiently so authors can accept or reject changes in compatible editors.MIT
- AlicenseNot gradedqualityDmaintenanceA local-first markdown review tool with MCP integration, enabling AI and humans to collaboratively annotate documents inline and generate revision prompts.1MIT
- AlicenseNot gradedqualityDmaintenanceEnables reviewing Markdown files in a browser with inline annotations, submitting or cancelling reviews, and returning structured feedback through the review_markdown MCP tool.MIT
- AlicenseNot gradedqualityAmaintenanceEnables MCP clients to read articles, preview Markdown output, and manage publishing tasks across supported platforms.MIT
TDQS
Scored across 21 tools
Most tools target clearly distinct resource+action pairs (review, source, comment, asset, turn). The only real friction is the read surface: get_review vs get_status vs get_source vs get_feedback, and get_feedback vs list_comments/get_comment overlap slightly, though the descriptions explicitly steer ('for the full threads use list_comments', 'use get_source(with_revision=true) not this poll'). Those caveats make the boundaries learnable but not frictionless.
The set is dominated by a clean verb_noun snake_case pattern (list_reviews, create_review, get_source, update_source, resolve_comment, delete_comment, attach_asset). Three outliers — hand_back, ping_working, server_info — are idiomatic and self-describing, so they read as minor deviations rather than a broken convention.
21 tools is heavy for a review service; the comment CRUD block (create/list/get/reply/resolve/delete) plus four read variants on one review account for most of the surface. Each tool is well motivated, but coordination extras (hand_back, ping_working, server_info, get_git_url) push it into borderline territory where a few could collapse into options on existing calls.
Coverage is strong: full review lifecycle, optimistic-concurrency source updates, history and git backends, assets, comment threads with resolve/reopen, and turn/lease coordination. Gaps are small — assets can be attached and listed but not removed, review metadata is immutable (kind, project), and reopen is deliberately reviewer-only, all workable around.