footnote-mcp
OCI · GHCR.IO/KAZKOZDEV/FOOTNOTE-MCP:0.2.6 · 2 COMPONENTS · SCANNED SEP 20
Source-grounded web research: search, extraction, verification, and browser automation.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security0
- Malware scan not yet available for this package.Unverified
- Known CVEs could not be checked: this artifact ships no SBOM, so there is no dependency list to read. Publishing one would let us assess it.Unverified
- Install-script risk not yet assessed.Unverified
- Dependency health could not be checked: this artifact ships no SBOM, so there is no dependency list to read. Publishing one would let us assess it.Unverified
Provenance & Transparency48
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 45 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability78
- AI-judged instruction clarity (excellent).Pass
- Tool/resource definitions use about 2847 tokens (~63/item across 45 items; 45 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management80
- Stability observed for 24 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage78
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 33% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 45 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 45 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
How do I install the footnote-mcp server?
footnote-mcp runs locally as a container image, launched with docker run --rm -i ghcr.io/kazkozdev/footnote-mcp:0.2.6. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.
oci · ghcr.io/kazkozdev/footnote-mcp:0.2.6
claude mcp add kazkozdev-footnote-mcp -- docker run --rm -i ghcr.io/kazkozdev/footnote-mcp:0.2.6
{
"mcpServers": {
"kazkozdev-footnote-mcp": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"ghcr.io/kazkozdev/footnote-mcp:0.2.6"
]
}
}
} {
"servers": {
"kazkozdev-footnote-mcp": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"ghcr.io/kazkozdev/footnote-mcp:0.2.6"
]
}
}
} codex mcp add kazkozdev-footnote-mcp -- docker run --rm -i ghcr.io/kazkozdev/footnote-mcp:0.2.6
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"kazkozdev-footnote-mcp": {
"type": "local",
"command": [
"docker",
"run",
"--rm",
"-i",
"ghcr.io/kazkozdev/footnote-mcp:0.2.6"
],
"enabled": true
}
}
} mcp_servers:
kazkozdev-footnote-mcp:
command: "docker"
args: ["run", "--rm", "-i", "ghcr.io/kazkozdev/footnote-mcp:0.2.6"] {
"McpServers": {
"kazkozdev-footnote-mcp": {
"Transport": "stdio",
"Command": "docker",
"Arguments": [
"run",
"--rm",
"-i",
"ghcr.io/kazkozdev/footnote-mcp:0.2.6"
]
}
}
} {
"mcpServers": {
"kazkozdev-footnote-mcp": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"ghcr.io/kazkozdev/footnote-mcp:0.2.6"
]
}
}
} Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 20 Sept 26 −3
- Stability: pass → 0.80 functional
- 19 Sept 26 +1
- Stability: 0.97 → pass security
- 17 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
- 14 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.
- 13 Sept 26 −3
- Stability: pass → 0.80 functional
- 12 Sept 26 +1
- Stability: 0.97 → pass security
- 10 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
- 7 Sept 26 +2
- Security disclosure: fail → pass ▲ functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 20 Sept 2026 · Analysed oci/ghcr.io/kazkozdev/footnote-mcp:0.2.6
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | oci |
| Reason | No attestation published |
Background: How many MCP packages publish verified provenance →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
archive_search ~105
Find archived captures of a URL or host through the Wayback Machine and Common Crawl; optionally extract archived text.
| Name | Type | Req | Description |
|---|---|---|---|
| fetch_text | boolean | – | – |
| lang | string | – | – |
| num | integer | – | – |
| source | string | – | auto | wayback | common_crawl |
| timestamp | string | – | Optional Wayback target YYYYMMDD or YYYYMMDDhhmmss |
| url | string | yes | Full URL, host, or Common Crawl URL pattern |
No output schema declared.
No examples provided.
browser_extract_tables ~38
Extract visible tables from the current browser page after navigation/interactions.
| Name | Type | Req | Description |
|---|---|---|---|
| max_rows | integer | – | – |
| max_tables | integer | – | – |
No output schema declared.
No examples provided.
browser_extract_tables_for_date_range ~67
Set date range in the current browser page, submit it, then extract visible tables.
| Name | Type | Req | Description |
|---|---|---|---|
| end_date | string | yes | YYYY-MM-DD |
| max_rows | integer | – | – |
| max_tables | integer | – | – |
| start_date | string | yes | YYYY-MM-DD |
No output schema declared.
No examples provided.
browser_set_date_range ~53
Best-effort browser date-range setter for interactive pages with date inputs.
| Name | Type | Req | Description |
|---|---|---|---|
| end_date | string | yes | YYYY-MM-DD |
| start_date | string | yes | YYYY-MM-DD |
| submit | boolean | – | – |
No output schema declared.
No examples provided.
build_research_debug_report ~68
Build a compact diagnostic report for a research run: queries, URLs, source quality, and verification gaps.
| Name | Type | Req | Description |
|---|---|---|---|
| requirements | object | – | – |
| search_memory | object | – | – |
| sources | array | – | – |
| task | string | yes | – |
| verification | object | – | – |
No output schema declared.
No examples provided.
check_date_completeness ~108
Validate date-range completeness for structured results. Supports day, week, and month granularity.
| Name | Type | Req | Description |
|---|---|---|---|
| actual_items | array | yes | – |
| calendar | string | – | calendar | business_day | crypto_24_7 | forex_weekday | us_business_day | ru_business_day |
| end_date | string | yes | YYYY-MM-DD |
| granularity | string | – | day | week | month |
| holidays | array | – | – |
| start_date | string | yes | YYYY-MM-DD |
No output schema declared.
No examples provided.
classify_source ~59
Classify a source as official, aggregator, blog, forum, interactive, blocked, or error.
| Name | Type | Req | Description |
|---|---|---|---|
| content_type | string | – | – |
| status_code | integer | – | – |
| text_sample | string | – | – |
| url | string | yes | – |
No output schema declared.
No examples provided.
corroborate_claim ~67
Triangulate a claim across multiple source excerpts; returns a corroboration verdict (corroborated/conflicting/single_source/...).
| Name | Type | Req | Description |
|---|---|---|---|
| backend | string | – | heuristic | auto | ollama | local_nli |
| claim | string | yes | – |
| excerpts | array | yes | – |
No output schema declared.
No examples provided.
encyclopedia_search ~89
Search Wikipedia articles and Wikidata entities, or execute a read-only Wikidata SPARQL query.
| Name | Type | Req | Description |
|---|---|---|---|
| lang | string | – | – |
| num | integer | – | – |
| query | string | yes | Entity/topic query; still required when sparql is supplied |
| source | string | – | auto | wikipedia | wikidata |
| sparql | string | – | Optional read-only SPARQL SELECT query |
No output schema declared.
No examples provided.
evidence_entailment ~75
Strict entailment check for claim vs source excerpt. Supports heuristic, Ollama judge, or auto fallback.
| Name | Type | Req | Description |
|---|---|---|---|
| backend | string | – | auto | heuristic | ollama | local_nli |
| claim | string | yes | – |
| model | string | – | Optional Ollama model name |
| source_excerpt | string | yes | – |
No output schema declared.
No examples provided.
export_dataset ~71
Write extracted rows to a consolidated file (csv | xlsx | json) and return the path.
| Name | Type | Req | Description |
|---|---|---|---|
| columns | array | – | – |
| format | string | – | csv | xlsx | json |
| path | string | – | Optional output path; defaults to cache exports dir |
| rows | array | yes | – |
No output schema declared.
No examples provided.
generate_search_queries ~52
Generate specialized search queries using operators like site:, filetype:, API, CSV, and data-table variants.
| Name | Type | Req | Description |
|---|---|---|---|
| max_queries | integer | – | – |
| requirements | object | – | – |
| task | string | yes | – |
No output schema declared.
No examples provided.
github_search ~64
Search public GitHub repositories, issues, code, or commits. Authentication is optional; zero-key requests use GitHub's public rate limit.
| Name | Type | Req | Description |
|---|---|---|---|
| kind | string | – | repositories | issues | code | commits |
| num | integer | – | – |
| query | string | yes | – |
No output schema declared.
No examples provided.
locate_claim_span ~59
Locate the sentence(s) in a source that best support a claim, with character offsets and a containment score (span-level provenance).
| Name | Type | Req | Description |
|---|---|---|---|
| claim | string | yes | – |
| max_spans | integer | – | – |
| source_text | string | yes | – |
No output schema declared.
No examples provided.
papers_search ~66
Search scientific publications through Crossref and arXiv. Uses no API key and returns one normalized paper result shape.
| Name | Type | Req | Description |
|---|---|---|---|
| lang | string | – | – |
| num | integer | – | – |
| query | string | yes | – |
| source | string | – | auto | crossref | arxiv |
No output schema declared.
No examples provided.
recipe_registry ~62
Manage promoted extraction recipes: list, get, run, or delete saved recipes.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | list | get | run | delete |
| input_payload | object | – | – |
| recipe_id | string | – | – |
| source_text | string | – | – |
No output schema declared.
No examples provided.
reconcile_time_series ~61
Align several time series on a common key, compute deltas vs the first series, and flag missing keys and outliers.
| Name | Type | Req | Description |
|---|---|---|---|
| on | string | – | Key field to align on |
| series | array | yes | – |
| value_field | string | – | – |
No output schema declared.
No examples provided.
resolve_units ~32
Resolve units, currencies, and currency pairs from text so incompatible rows can be rejected.
| Name | Type | Req | Description |
|---|---|---|---|
| text | string | yes | – |
No output schema declared.
No examples provided.
source_cache_get ~25
Read persistent source cache entry for a URL.
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | – |
No output schema declared.
No examples provided.
source_cache_put ~33
Write arbitrary parsed source payload into persistent source cache.
| Name | Type | Req | Description |
|---|---|---|---|
| payload | object | yes | – |
| url | string | yes | – |
No output schema declared.
No examples provided.
startup_health_check ~25
Check optional parser, OCR, browser, and cache dependencies for this MCP server.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
tool_code_generate ~37
Generate a safe starter extraction recipe function for the proposed spec. The result must still be validated before running.
| Name | Type | Req | Description |
|---|---|---|---|
| spec | object | – | – |
No output schema declared.
No examples provided.
tool_code_run_sandboxed ~72
Run validated extraction recipe code in a separate limited subprocess. Code must define extract(source_text, input_payload).
| Name | Type | Req | Description |
|---|---|---|---|
| code | string | yes | – |
| input_payload | object | – | – |
| max_output_chars | integer | – | – |
| source_text | string | – | – |
| timeout | integer | – | – |
No output schema declared.
No examples provided.
tool_code_validate ~40
Statically validate task-specific extraction code against the safe recipe contract and allowlist.
| Name | Type | Req | Description |
|---|---|---|---|
| code | string | yes | – |
| max_chars | integer | – | – |
No output schema declared.
No examples provided.
tool_promote ~77
Save a validated extraction recipe as reusable memory after an optional smoke test. Does not edit the MCP server.
| Name | Type | Req | Description |
|---|---|---|---|
| code | string | yes | – |
| expected_min_rows | integer | – | – |
| input_payload | object | – | – |
| name | string | yes | – |
| sample_source_text | string | – | – |
| spec | object | – | – |
No output schema declared.
No examples provided.
tool_spec_propose ~58
Propose a controlled task-specific extraction recipe spec when generic tools cannot extract structured rows.
| Name | Type | Req | Description |
|---|---|---|---|
| desired_output | string | – | – |
| observed_failure | string | – | – |
| source_url | string | – | – |
| task | string | yes | – |
No output schema declared.
No examples provided.
validate_unit_rows ~51
Reject structured rows that are incompatible with the expected unit, currency, or currency pair.
| Name | Type | Req | Description |
|---|---|---|---|
| expected_unit_or_pair | string | yes | – |
| rows | array | yes | – |
| text_fields | array | – | – |
No output schema declared.
No examples provided.
web_archive_fetch ~73
Find the closest Wayback Machine snapshot of a URL (for dead or changed sources) and optionally read its text.
| Name | Type | Req | Description |
|---|---|---|---|
| fetch_text | boolean | – | – |
| lang | string | – | – |
| timestamp | string | – | Optional target YYYYMMDD or YYYYMMDDhhmmss |
| url | string | yes | – |
No output schema declared.
No examples provided.
web_click ~43
Click an interactive element by its ref (e.g. @e3 from web_snapshot).
| Name | Type | Req | Description |
|---|---|---|---|
| ref | string | yes | Element ref from web_snapshot, like @e3 |
No output schema declared.
No examples provided.
web_crawl ~71
Breadth-first crawl from a start URL, fetching and extracting each page. Stays on the start host by default. Capped at 50 pages.
| Name | Type | Req | Description |
|---|---|---|---|
| lang | string | – | – |
| max_pages | integer | – | – |
| same_domain | boolean | – | – |
| start_url | string | yes | – |
No output schema declared.
No examples provided.
web_deep_search ~218
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.
| Name | Type | Req | Description |
|---|---|---|---|
| entailment_backend | string | – | heuristic | auto | ollama | local_nli |
| lang | string | – | Language code |
| max_fetch | integer|null | – | Adaptive total page/file fetch budget; defaults to num |
| max_iterations | integer | – | Maximum gap-driven research iterations |
| model | string|null | – | Ollama model for requirement planning and evidence extraction; otherwise FOOTNOTE_RESEARCH_MODEL/OLLAMA_MODEL |
| num | integer | – | Maximum discovery results before fetching |
| provider | string | – | Web provider: auto | auto+marginalia | searxng | tavily | brave | google | wiby | marginalia | scrape |
| query | string | yes | Search query |
| sources | array | – | Optional explicit source intents: web, papers, encyclopedia, github, archive. Empty enables automatic routing. |
No output schema declared.
No examples provided.
web_detect_downloads ~50
Detect downloadable CSV/XLS/XLSX/PDF/JSON/XML links on a page.
| Name | Type | Req | Description |
|---|---|---|---|
| lang | string | – | – |
| max_links | integer | – | – |
| url | string | yes | – |
No output schema declared.
No examples provided.
web_extract ~58
Extract text from the page. refs: comma-separated @eN, or 'visible' for all visible text, or 'all' for full HTML.
| Name | Type | Req | Description |
|---|---|---|---|
| refs | string | yes | Comma-separated refs, or 'visible', or 'all' |
No output schema declared.
No examples provided.
web_extract_tables ~66
Fetch a page, parse HTML tables, and return structured columns/rows with source URL provenance.
| Name | Type | Req | Description |
|---|---|---|---|
| lang | string | – | – |
| max_rows | integer | – | – |
| max_tables | integer | – | – |
| url | string | yes | – |
| use_cache | boolean | – | – |
No output schema declared.
No examples provided.
web_fetch_authenticated ~68
Fetch a page that needs cookies or custom headers (logged-in or gated pages).
| Name | Type | Req | Description |
|---|---|---|---|
| cookies | object | – | name→value cookie map |
| headers | object | – | extra request headers |
| lang | string | – | – |
| timeout | integer | – | – |
| url | string | yes | – |
No output schema declared.
No examples provided.
web_fetch_json ~57
Fetch an API/JSON URL directly and return parsed JSON with source URL provenance and persistent cache.
| Name | Type | Req | Description |
|---|---|---|---|
| lang | string | – | – |
| timeout | integer | – | – |
| url | string | yes | – |
| use_cache | boolean | – | – |
No output schema declared.
No examples provided.
web_navigate ~28
Navigate the browser to a URL.
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | Full URL to navigate to |
No output schema declared.
No examples provided.
web_parse_file ~64
Download and parse CSV/TSV/XLSX/PDF/JSON files, returning structured rows or extracted text with provenance.
| Name | Type | Req | Description |
|---|---|---|---|
| lang | string | – | – |
| max_rows | integer | – | – |
| url | string | yes | – |
| use_cache | boolean | – | – |
No output schema declared.
No examples provided.
web_read ~53
Fetch and extract text from a single URL. Returns extracted content (markdown).
| Name | Type | Req | Description |
|---|---|---|---|
| lang | string | – | Language code |
| url | string | yes | Full URL to fetch and extract |
| use_cache | boolean | – | – |
No output schema declared.
No examples provided.
web_screenshot ~49
Capture a PNG screenshot of the current browser page, save it to disk, and optionally OCR text locked inside the image.
| Name | Type | Req | Description |
|---|---|---|---|
| full_page | boolean | – | – |
| ocr | boolean | – | – |
No output schema declared.
No examples provided.
web_scroll ~34
Scroll the page: up, down, top, bottom.
| Name | Type | Req | Description |
|---|---|---|---|
| direction | string | yes | up | down | top | bottom |
No output schema declared.
No examples provided.
web_search ~142
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.
| Name | Type | Req | Description |
|---|---|---|---|
| lang | string | – | Language code: en, ru, etc. |
| num | integer | – | Max results to return |
| provider | string | – | auto | auto+marginalia | searxng | tavily | brave | google | wiby | marginalia | scrape |
| query | string | yes | Search query |
| semantic | boolean | – | Rerank results by meaning using local bge-m3 embeddings |
No output schema declared.
No examples provided.
web_search_recent ~65
Web search restricted to a recency window via DuckDuckGo's date filter (day/week/month/year).
| Name | Type | Req | Description |
|---|---|---|---|
| freshness | string | – | day | week | month | year |
| lang | string | – | – |
| num | integer | – | – |
| query | string | yes | – |
No output schema declared.
No examples provided.
web_snapshot ~42
Capture the current page state: URL, title, accessibility tree with stable refs (@e1, @e2...), and visible text. Use this before clicking/typing.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
web_type ~52
Type text into an input field by its ref.
| Name | Type | Req | Description |
|---|---|---|---|
| ref | string | yes | Input field ref from web_snapshot |
| submit | boolean | – | Press Enter after typing |
| text | string | yes | Text to type |
No output schema declared.
No examples provided.
What is the footnote-mcp server?
footnote-mcp is listed in the public MCP registry as io.github.KazKozDev/footnote-mcp. Source-grounded web research: search, extraction, verification, and browser automation. This page covers its container image (ghcr.io/kazkozdev/footnote-mcp:0.2.6).
Is the footnote-mcp server safe to use?
footnote-mcp scores 51 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the footnote-mcp server expose?
footnote-mcp exposes 45 tools: web_search, web_deep_search, web_read, web_extract_tables, web_detect_downloads, and 40 more. Their descriptions and schemas cost roughly 2,847 tokens of context every time the server is loaded.
Is the footnote-mcp server still maintained?
footnote-mcp is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the footnote-mcp server under?
footnote-mcp declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.