Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Check if references exist or were retracted, look up journal AI policies, and preview manuscripts.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Works in Claude on the web, desktop and mobile:
https://manusights.com/mcpRun this in your terminal
claude mcp add --transport http manusights https://manusights.com/mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"manusights": {
"url": "https://manusights.com/mcp"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"manusights": {
"type": "http",
"url": "https://manusights.com/mcp"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
ChatGPT connects only to servers on the internet:
https://manusights.com/mcpMenu names can differ slightly by plan and over time.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Tool names and descriptions exactly as the server reported them on Nov 7, 2026. The maker wrote them, not us; we show them as plain text.
check_referencesUse this when the user wants to check references or citations from any source: a manuscript, a bibliography, a literature review, or citations an AI assistant gave earlier in the conversation. It reports whether each one exists, points to the right paper, or has been retracted, c
get_journal_ai_policyUse this when the user asks what a named journal or publisher allows or requires about AI: AI as an author, disclosure statements and where they go, AI-generated images, uploading manuscripts to AI tools, or reviewers' and editors' AI use. It returns the rules as recorded from th
review_manuscriptUse this when the user wants Manusights to review, check or assess a scientific manuscript they attached (PDF, Word, ODT, RTF, TXT, Markdown or LaTeX, up to 75 MB). Starts a pre-submission preview and returns a review_id right away. The preview takes a few minutes, so read it aft
review_manuscript_textUse this when the user wants Manusights to review, check or assess a scientific manuscript and you have its full text (for example from a file the user attached or pasted), but cannot pass the file itself. Send the complete manuscript text, not a summary or excerpt: title, abstra
get_manuscript_reviewUse this to read the preview, and the Full Review if the account has one, for a review_id returned by review_manuscript or list_manuscript_reviews. While preview.status is "processing", wait check_again_after_seconds and call again with the same review_id. Report status only whil
list_manuscript_reviewsUse this when the user asks about their earlier Manusights reviews. Returns the 20 most recent, newest first.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 8, 2026
The registry name was verified against the domain manusights.com (the registry checks domain ownership)
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Responded in 170 ms (HTTP 200)
No sign-in needed
Read 6 tool descriptions and found no hidden instructions to the AI
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 3 of 3 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed –, and the latest version (1.1.0) reached the registry 16 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
In the same category: Spec Driven Development, Remote Desktop Commander, MIDAS Gen NX / Civil NX
Servers in the same category from other makers, sorted by stars.
Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Read and carefully change the model open in MIDAS Gen NX or Civil NX on this PC.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
Manusights checks a manuscript before submission. This remote MCP server lets an AI assistant check references for retractions and DOI mismatches, look up a journal's recorded AI-use rules, and start a pre-submission preview of a manuscript.
https://manusights.com/mcp (streamable HTTP)com.manusights/manusights in the official MCP RegistryThis repository holds the server's public description and setup notes, packaged as an Agent Plugins plugin: plugin.json (manifest), mcp.json and .mcp.json (the remote server), and one skill, skills/check-before-submission/SKILL.md, that tells an assistant how to use the tools and report their results. The server itself runs at manusights.com; there is no code to install.
| Tool | What it does | Account |
|---|---|---|
check_references | Checks references against Crossref, the DOI registry and Retraction Watch. References without a DOI are also searched in Semantic Scholar, PubMed, arXiv, Open Library and CRAN. Reports retractions, corrections, expressions of concern, DOI mismatches and references with no matching record. | Optional |
get_journal_ai_policy | Returns a journal's recorded AI-use and disclosure rules with the official policy link and the date they were checked. | Optional |
review_manuscript_text | Starts a preview from the complete manuscript text: a readiness score, a verdict and the main risks a reviewer may raise. Figures are not reviewed from text. | Required |
review_manuscript | Starts a preview from an attached file, in clients that can pass the file's download URL (ChatGPT). | Required |
get_manuscript_review | Reads a preview or review on your account. | Required |
list_manuscript_reviews | Lists your account's 20 most recent reviews. | Required |
Matching a record shows that a reference exists, not that it supports the claim it is cited for. A reference with no matching record may be a typo or a gap in the registries, not an invented paper.
Claude (claude.ai, desktop and mobile): open Customize, then Connectors, choose Add custom connector, name it Manusights and enter https://manusights.com/mcp. Guide: https://manusights.com/claude
ChatGPT: install Manusights from the ChatGPT app directory. Guide: https://manusights.com/chatgpt
Claude Code:
claude mcp add --transport http manusights https://manusights.com/mcp
Then run /mcp, choose manusights and authenticate when you need a preview.
Codex:
codex mcp add manusights --url https://manusights.com/mcp
codex mcp login manusights
Cursor: add to .cursor/mcp.json in a project, or ~/.cursor/mcp.json for every project:
{ "mcpServers": { "manusights": { "url": "https://manusights.com/mcp" } } }
VS Code: add to .vscode/mcp.json:
{ "servers": { "manusights": { "type": "http", "url": "https://manusights.com/mcp" } } }
Ask for Manusights by name, for example: "Use Manusights to check these references before I submit."
A reference check sends only the references to Manusights. A preview sends the manuscript text or file you share and saves the preview to your Manusights account. Manusights does not write or rewrite manuscripts. Privacy policy: https://manusights.com/privacy. Terms: https://manusights.com/terms. Developer reference: https://manusights.com/developers/connector
team@manusights.com