MCP servers · axelvernebooks

Research Scope: MCP server for source scoring and citation checks

An MCP server that plans research, scores sources for freshness and conflicts of interest, and checks that report claims cite scored sources.

This text was machine-translated from the publisher's own information and has not been checked by a human editor. The publisher's original text is the reference.

This resource was imported automatically from the sources listed below and has not been reviewed by the AI Gate team yet. The description is the publisher's own, as published. Check the repository before installing.

What it does

Research Scope exposes four tools that run a research-to-report workflow. plan_research turns a scope into a source-target plan with kill criteria, so work stops with an insufficient-sources result when evidence is too thin. fetch_and_score crawls one source and returns a 0-100 score with flags for primary-source status, freshness, paywall access and conflict of interest, each backed by the evidence it was based on. build_report assembles a numbered citation-registry report shell from scored sources, and check_report verifies that every substantive claim cites at least one scored source, returning uncited claims as an error list.

It suits agent-written reports where each sentence needs a traceable source, rather than prose that sounds confident but cannot show where it came from. The scoring rubric weighs availability and substance, primary-source status, freshness, access and independence, and the scoring code returns its evidence with each result.

The server runs over stdio for most MCP clients, or over Streamable HTTP for remote deployments. The publisher provides configuration snippets for Claude Code, Cursor and Cline, and a Docker setup. Reports are saved under data/reports/. A demo capture script replays a scripted flow against the built server and writes a JSONL transcript; it needs network access for one real fetch.

Limitations and requirements

The demo capture script requires network access for its one real fetch of a .gov page. It will not overwrite its default transcript file unless run with --force.

Safety

Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.

  • Runs code or changes an assistant's behaviour

Sources

  • Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
    Research Scope

    Plan research, score sources for freshness/COI, and enforce claim-level citations in reports.

    v0.1.2
    As shown on registry.modelcontextprotocol.io when we last read it
MCP servers
docker

Docker Hub MCP Server

Docker's MCP server that helps an AI assistant find and compare container images on Docker Hub and, with your token, manage your own repositories and tags.

171 GitHub starsCloud & DevOpsSoftware development
Updated 13 Nov 2026
MCP servers
awslabs

MCP servers for AWS (AWS Labs)

A large open-source collection of MCP servers from AWS Labs for building and operating on AWS: documentation, infrastructure, databases, AI services, cost and more.

9.9K GitHub starsCloud & DevOpsData & databases
Updated 17 Nov 2026
MCP servers
firecrawl

Firecrawl MCP Server (web search and scraping)

Firecrawl's MCP server that lets an AI assistant search the web, turn pages and PDFs into clean Markdown, crawl sites and interact with dynamic pages.

7.8K GitHub starsWeb, search & browserProductivity & automation
Updated 17 Nov 2026
MCP servers
microsoft

Playwright MCP (browser automation)

Microsoft's MCP server that lets an AI assistant open web pages, click, type and read them through a real browser, using the page structure instead of screenshots.

39.6K GitHub starsTesting & QAWeb, search & browser
Updated 17 Nov 2026