footnote-mcp server

Read from the package source without running it. The installed server may list more.

• archive_search

  Find archived captures of a URL or host through the Wayback Machine and Common Crawl; optionally extract archived text.

• browser_extract_tables

  Extract visible tables from the current browser page after navigation/interactions.

• browser_extract_tables_for_date_range

  Set date range in the current browser page, submit it, then extract visible tables.

• browser_set_date_range

  Best-effort browser date-range setter for interactive pages with date inputs.

• build_research_debug_report

  Build a compact diagnostic report for a research run: queries, URLs, source quality, and verification gaps.

• check_date_completeness

  Validate date-range completeness for structured results. Supports day, week, and month granularity.

• classify_source

  Classify a source as official, aggregator, blog, forum, interactive, blocked, or error.

• corroborate_claim

  Triangulate a claim across multiple source excerpts; returns a corroboration verdict (corroborated/conflicting/single_source/...).

• encyclopedia_search

  Search Wikipedia articles and Wikidata entities, or execute a read-only Wikidata SPARQL query.

• evidence_entailment

  Strict entailment check for claim vs source excerpt. Supports heuristic, Ollama judge, or auto fallback.

• export_datasetwrite action

  Write extracted rows to a consolidated file (csv | xlsx | json) and return the path.

• generate_search_queries

  Generate specialized search queries using operators like site:, filetype:, API, CSV, and data-table variants.

• github_search

  Search public GitHub repositories, issues, code, or commits. Authentication is optional; zero-key requests use GitHub's public rate limit.

• locate_claim_span

  Locate the sentence(s) in a source that best support a claim, with character offsets and a containment score (span-level provenance).

• papers_search

  Search scientific publications through Crossref and arXiv. Uses no API key and returns one normalized paper result shape.

• recipe_registry

  Manage promoted extraction recipes: list, get, run, or delete saved recipes.

• reconcile_time_series

  Align several time series on a common key, compute deltas vs the first series, and flag missing keys and outliers.

• resolve_units

  Resolve units, currencies, and currency pairs from text so incompatible rows can be rejected.

• source_cache_get

  Read persistent source cache entry for a URL.

• source_cache_putwrite action

  Write arbitrary parsed source payload into persistent source cache.

• startup_health_check

  Check optional parser, OCR, browser, and cache dependencies for this MCP server.

• tool_code_generate

  Generate a safe starter extraction recipe function for the proposed spec. The result must still be validated before running.

• tool_code_run_sandboxedwrite action

  Run validated extraction recipe code in a separate limited subprocess. Code must define extract(source_text, input_payload).

• tool_code_validate

  Statically validate task-specific extraction code against the safe recipe contract and allowlist.

• tool_promote

  Save a validated extraction recipe as reusable memory after an optional smoke test. Does not edit the MCP server.

• tool_spec_propose

  Propose a controlled task-specific extraction recipe spec when generic tools cannot extract structured rows.

• validate_unit_rows

  Reject structured rows that are incompatible with the expected unit, currency, or currency pair.

• web_archive_fetch

  Find the closest Wayback Machine snapshot of a URL (for dead or changed sources) and optionally read its text.

• web_click

  Click an interactive element by its ref (e.g. @e3 from web_snapshot).

• web_crawl

  Breadth-first crawl from a start URL, fetching and extracting each page. Stays on the start host by default. Capped at 50 pages.

• web_deep_search

  Iterative evidence-led deep research: decompose requirements, search unresolved gaps, extract text/tables/files, verify each fact, and return a diagnostic funnel plus source-grounded context.

• web_detect_downloads

  Detect downloadable CSV/XLS/XLSX/PDF/JSON/XML links on a page.

• web_extract

  Extract text from the page. refs: comma-separated @eN, or 'visible' for all visible text, or 'all' for full HTML.

• web_extract_tables

  Fetch a page, parse HTML tables, and return structured columns/rows with source URL provenance.

• web_fetch_authenticated

  Fetch a page that needs cookies or custom headers (logged-in or gated pages).

• web_fetch_json

  Fetch an API/JSON URL directly and return parsed JSON with source URL provenance and persistent cache.

• web_navigate

  Navigate the browser to a URL.

• web_parse_file

  Download and parse CSV/TSV/XLSX/PDF/JSON files, returning structured rows or extracted text with provenance.

• web_read

  Fetch and extract text from a single URL. Returns extracted content (markdown).

• web_screenshot

  Capture a PNG screenshot of the current browser page, save it to disk, and optionally OCR text locked inside the image.

• web_scroll

  Scroll the page: up, down, top, bottom.

• web_search

  General web discovery. Uses configured providers plus zero-key Bing, DuckDuckGo, Brave, and Wiby. Marginalia is opt-in through auto+marginalia. Returns normalized titles, URLs, snippets and scores.

• web_search_recent

  Web search restricted to a recency window via DuckDuckGo's date filter (day/week/month/year).

• web_snapshot

  Capture the current page state: URL, title, accessibility tree with stable refs (@e1, @e2...), and visible text. Use this before clicking/typing.

• web_type

  Type text into an input field by its ref.

• Code scan30 source files scanned25/25
• –Live reliabilityno gateway calls yet and no remote to proben/a
• –Tool poisoningtools not inspected (local package is not executed); not countedn/a
• Auth qualitylocal package, no credentials required12/15
• Maintenancelast push 59 days ago12/15
• Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Safety score

88/100

higher than 70% of 867 Scraping and browsing servers

Tools

45

the typical Scraping and browsing server has 6

Tools that change things

7%

typical: 0%. Fewer write tools means less an agent can break

GitHub stars

2

more than 65% of 584 Scraping and browsing servers

Downloads a week

27

more than 7% of 312 Scraping and browsing servers with a package

footnote-mcp: common questions

Is footnote-mcp server safe?

Yes, by our scan: it is graded A (88/100). Read the footnote-mcp safety report

How do I install footnote-mcp?

It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.

Does footnote-mcp need an API key?

Not as far as the registry entry and our scan can tell: no credentials are declared or required.

Is footnote-mcp maintained?

The last commit was 59 days ago (2026-09-07). The latest release is v0.2.6.

What can I use instead of footnote-mcp?

Servers from other publishers that do the same job: One Search MCP server, Anakin MCP server and SeleniumBase MCP server. Compare all footnote-mcp alternatives.

How does footnote-mcp compare with other Scraping and browsing MCP servers?

safety score 88/100 (higher than 70% of 867 Scraping and browsing servers); tools 45 (the typical Scraping and browsing server has 6); tools that change things 7% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.