Remote MCP server that scores and rewrites AI-assisted prose while preserving names, numbers, quotes, links and facts.
What you can do
Score and rewrite pasted prose, returning edited or unchanged text with exact before-and-after writing scores.
Check that names, numbers, quotes, links and facts survive the edit, with completed-check metadata and review warnings.
Optionally pass a genre and audience to steer the editing.
When to use it
Useful when a user wants to remove stock AI phrasing or polish outward-facing writing, and wants a measurable before-and-after quality score rather than a free-form rewrite.
Requirements
A remote streamable HTTP endpoint; no package, account, API key or environment variable is declared. The draft text, genre and optional audience are sent to the hosted service for scoring and editing.
Before you install
Drafts are sent to a third-party hosted service, so avoid pasting confidential or personal material. The server's own instructions say not to use it to hide authorship, evade disclosure rules or impersonate a named person.
Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/io.github.manavmishra%2Fzero-slop/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.
Processes pasted prose with server-side scoring and source-preservation checks, plus bounded hosted AI editing when needed. Inputs are text, genre, and an optional audience. Returns edited or unchanged text, exact before-and-after writing scores, completed-check metadata, and review warnings when editing targets are missed.
Parameterstextrequiredgenreaudienceoperation
Version history
21
v2.12.33LatestOct 31, 2026
v2.12.32Oct 26, 2026
v2.12.29Oct 26, 2026
v2.12.28Oct 25, 2026
v2.12.26Oct 17, 2026
v2.12.25Oct 15, 2026
v2.12.24Oct 15, 2026
v2.12.23Oct 14, 2026
v2.12.22Oct 6, 2026
v2.12.21Oct 5, 2026
v2.12.19Oct 4, 2026
v2.12.18Oct 4, 2026
v2.12.15Oct 4, 2026
v2.12.14Oct 4, 2026
v2.12.12Sep 30, 2026
v2.12.11Sep 23, 2026
v2.12.10Sep 22, 2026
v2.12.9Sep 22, 2026
v2.12.6Sep 22, 2026
v2.12.4Sep 22, 2026
v2.12.1Sep 16, 2026
Score
85%
85% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
Reached in the last 30 daysRequired25 pts
Auth declaredRequired10 pts
Tools listedRequired15 pts
DescriptionRequired15 pts
Logo10 pts
Documentation15 pts
Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.