Name: Octocrawl
Author: 77777R7

Octocrawl MCP

Web scraper for agents: blocked, empty and wrong pages reported as such, with an Evidence Record.

Grade A Remote or local · Streamable HTTP · stdio API key 32 tools v0.4.2 · 13 Oct 2026

No reviews yet by 77777R7npm 993 Runs on your machine or at its publisher’s address — not through us

97/100

trust score

downloads a day

local

or remote

993

downloads in 30d

What it does

Web scraper for agents: blocked, empty and wrong pages reported as such, with an Evidence Record.

Quickstart

# 1 — add it to Claude Code
claude mcp add --scope user octocrawl-mcp '--' npx -y @octocrawl/mcp

# 2 — ask your agent for something these tools do
#   preview_monitor, create_monitor, list_monitors and 29 more

Octocrawl costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.

Publisher

77777R71 server

1 category

All 1 server

Installation

Where are you running it?

Every route below installs the same thing and ends at the same approval screen. This one can run either way — at an address its publisher runs, or as a process under your own user, with your files and your network — and this marketplace is in the path of neither.

Claude Codedeclared by this listing

This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.

claude mcp add --scope user octocrawl-mcp '--' npx -y @octocrawl/mcp

Reconnect, or start a new session, and the tools appear in the model’s tool list.

Or connect to its publisher’s address

Its publisher also runs it at https://mcp.octocrawl.dev/mcp: nothing to start on your machine, and this marketplace is not in the path.

claude mcp add --scope user --transport http octocrawl-mcp https://mcp.octocrawl.dev/mcp

Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.

What it asks of you

Nothing is required, but it can take W2L_API_URL (The Octocrawl API the server calls: npx octocrawl serve on this computer (default http://127.0.0.1:8787), or https://api.octocrawl.dev), W2L_API_TOKEN (A bearer token for a hosted or self-hosted API; none for a local one) if you want to set them.

What it writes

One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.

What you approve

32 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.

Tool surface

What the model actually sees. Descriptions are diffed on every release — see version history.

Only tools that write or reach the network

Capture a nonpersistent sample and assess identity, fields, evidence, and missing reasons. Start with preset firecrawl-introduction.

Parameter	Type	Required	Notes
preset	string	no	—
monitorId	string	no	—
revision	integer	no	—
url	string	no	—
ruleVersion	string	no	—
intervalMs	integer	no	—
staleAfterMs	integer	no	—
config	object	no	—
enabled	boolean	no	—

Create a public-document Monitor. Defaults to paused so a delivery destination can be configured first. Use preset firecrawl-introduction for first use.

Parameter	Type	Required	Notes
preset	string	no	—
monitorId	string	no	—
revision	integer	no	—
url	string	no	—
ruleVersion	string	no	—
intervalMs	integer	no	—
staleAfterMs	integer	no	—
config	object	no	—
enabled	boolean	no	—

List current Monitor state and freshness.

Parameter	Type	Required	Notes
debug	boolean	no	—

Check a Monitor baseline, latest run, latest event, and next schedule.

Parameter	Type	Required	Notes
id	string	yes	—
debug	boolean	no	—

Queue a durable manual run. Returns runId immediately; disconnection does not cancel execution.

Parameter	Type	Required	Notes
id	string	yes	—
triggerKey	string	no	—

Inspect a run and field assessment with evidence and failure reasons.

Parameter	Type	Required	Notes
id	string	yes	—
runId	string	yes	—
debug	boolean	no	—

Pause scheduling and cancel active Monitor execution.

Parameter	Type	Required	Notes
id	string	yes	—
debug	boolean	no	—

Resume Monitor scheduling; first run becomes due immediately.

Parameter	Type	Required	Notes
id	string	yes	—
debug	boolean	no	—

Explicitly cancel a queued or running Monitor run.

Parameter	Type	Required	Notes
id	string	yes	—
runId	string	yes	—

Register an HTTPS webhook for a Monitor. The secretEnv names an operator environment variable; never send the secret value.

Parameter	Type	Required	Notes
id	string	no	—
monitorId	string	yes	—
url	string	yes	—
secretEnv	string	no	—
maxAttempts	integer	no	—
enabled	boolean	no	—

List webhook destinations, optionally for one Monitor (monitorId) or one crawl or batch (jobId, the taskId); custom header names are listed, never their values.

Parameter	Type	Required	Notes
monitorId	string	no	—
jobId	string	no	—

Page through delivery state and failures, for a Monitor (monitorId) or a crawl or batch (jobId, the taskId). Defaults to 20 compact results.

Parameter	Type	Required	Notes
monitorId	string	no	—
jobId	string	no	—
destinationId	string	no	—
state	string	no	—
cursor	string	no	—
limit	integer	no	—
debug	boolean	no	—

Inspect one delivery and its retry attempts.

Parameter	Type	Required	Notes
id	string	yes	—
debug	boolean	no	—

Explicitly retry a dead-letter delivery with the same eventId.

Parameter	Type	Required	Notes
id	string	yes	—

Get evidence-backed JSON for one anonymous Amazon.sg /dp/{ASIN} product. No schema or model setup needed.

Parameter	Type	Required	Notes
url	string	yes	—
debug	boolean	no	—

Queue 1-1000 distinct Amazon.sg product URLs with the reviewed JSON schema. Returns taskId; page results with get_batch_items.

Parameter	Type	Required	Notes
urls	array	yes	—

Fetch one URL through the Octocrawl coverage ladder. Compact by default; set debug=true for the full audit. The result's warnings name what its content cannot vouch for: robots_overridden (robots.txt disallows the URL; a local server fetched it because you named it), or client_rendered_suspected…

Parameter	Type	Required	Notes
url	string	yes	http(s) URL
mode	string	no	authed reads the page with the login the person saved for its site (import_login), signed in as them: ask the person first, naming the site. Not with executeJavascript or a webhook: a script could rea
handoff		no	On a server running on the person's machine: when Octocrawl is stopped at a captcha, a challenge or a login wall, open the page in the person's own Chrome (remote debugging on, they click Allow), wait
lane	string	no	On a server running on the person's machine: read the page in the person's own Chrome instead of fetching it (lane my_browser, never cached). Chrome needs remote debugging on (chrome://inspect/#remote
access	string	no	How the pages are reached, as three plain choices; ask the person which they want when it matters. standard: Octocrawl's own fetching and its local browser, nothing that costs a third party. enhanced:
allowlistedDomains	array	no	—
formats	array	no	—
includeLinks	boolean	no	Include outbound links. Defaults to false.
debug	boolean	no	Include trace, ladderTrace, and full attempt audit.
actions		no	—
robotsOverride		no	—

Read the record of one scrape call by the scrapeId its response carried (metadata.scrapeId): the request (header values replaced by their names), who made it (origin, integration), the verdict, the lanes tried, the metadata, the snapshot, the usage, the warnings and the hints. No page body.…

Parameter	Type	Required	Notes
id	string	yes	metadata.scrapeId of a scrape response

List a site's URLs without fetching each page: the start URL, the links on its page (read on the http lane alone; no browser) and the entries of the sitemaps the site declares (robots.txt Sitemap: lines, else /sitemap.xml), inside one deadline. Every URL is in the crawl's scope (the start host and…

Parameter	Type	Required	Notes
url	string	yes	http(s) URL of the start page
search	string	no	Keep only the URLs in which every word (at most 10) appears, case-insensitively, in the decoded URL or its title. A filter, not a ranking: the order stays the discovery order, and limit counts the mat
sitemap	string	no	include (default): the start page's links and the sitemaps. skip: no sitemap is read. only: no page is read; the links are the sitemap entries in their listed order (the start URL only when a sitemap
includeSubdomains	boolean	no	Admit every host under the start URL's apex (the host with one leading www. removed; no public-suffix list). Default false. Each new host's robots.txt is read, for at most 20 hosts.
ignoreQueryParameters	boolean	no	Fold URLs that differ only in their query string into the first one seen, returned without its query; each merge is counted (refused.collapsed, with samples under debug). Default false.
limit	integer	no	Links returned at most. Default …; a hosted server takes up to 5000. Reaching it is status completed with stoppedBy limit.
timeout	integer	no	Milliseconds for the whole map. Default …; a hosted server takes up to 60000.
includePaths	array	no	Pathname regexes a URL must match (as on crawl).
excludePaths	array	no	Pathname regexes that leave a URL out; they win over includePaths.
regexOnFullURL	boolean	no	Match includePaths and excludePaths against the canonical URL instead of its pathname. Default false.
crawlEntireDomain	boolean	no	Admit URLs anywhere on the start host, not only in the start URL's path subtree. Default false.
deduplicateSimilarURLs	boolean	no	Fold /a and /a/, / and /index.html, www and apex, http and https into one URL. Default true.
ignoreRobotsTxt	boolean	no	Also return the URLs robots.txt disallows or whose robots.txt could not be read, each with that verdict (robots disallowed or unreachable), and read the start page and sitemaps past it. robots.txt is
mode	string	no	The declared identity robots.txt, the page and the sitemaps are read under. authed is not offered: a map reads public sitemaps and one public page.
debug	boolean	no	Return the full map response instead of the compact one.

Start a multi-page crawl. Returns { taskId } (HTTP 202 equivalent). By default it follows links in the start URL's path subtree on its host and www twin, folds similar URLs into one page, and reports every collapsed or refused link in get_crawl's discovery counters and each page's links_offered…

Parameter	Type	Required	Notes
url	string	yes	—
mode	string	no	authed is not offered: a crawl follows every link, and a sign-out link would end the user's session in Chrome too; send the pages as a batch in mode authed.
access	string	no	How the pages are reached: standard is Octocrawl's own fetching and its local browser, nothing that costs a third party; enhanced also uses the paid providers the server's operator approved (an access
maxPages	number/null	no	—
maxDepth	number/null	no	—
useCached	boolean	no	—
allowlistedDomains	array	no	—
formats	array	no	—
includeLinks	boolean	no	—
includePaths	array	no	Pathname regexes a discovered link must match; the start URL is always fetched.
excludePaths	array	no	Pathname regexes that skip a discovered link; they win over includePaths.
regexOnFullURL	boolean	no	Match includePaths and excludePaths against each link's canonical URL (scheme, host, path and query) instead of its pathname. Default false.
ignoreQueryParameters	boolean	no	Treat URLs that differ only in their query string as one page: the first variant seen is fetched, later ones are reported as collapsed in the page's links_offered trace event and the report's discover
deduplicateSimilarURLs	boolean	no	Treat /a and /a/, / and /index.html, www and apex, http and https as one page: the first variant seen is fetched, later ones are reported as collapsed. Default true. A page fetched and then found to r
crawlEntireDomain	boolean	no	Follow links anywhere on the start URL's host. Default false: links on that host are followed only inside the start URL's path subtree (its directory, or the directory of the file it names); the rest
allowSubdomains	boolean	no	Follow links to every host under the start URL's apex (the host with one leading www. removed; no public-suffix list, so a seed on www.gov.uk admits every *.gov.uk host). Default false. Each new host
allowExternalLinks	boolean	no	Follow links to any host, each with its own robots.txt read; maxDepth and maxPages bound the walk. Default false. Cannot be combined with allowlistedDomains.
sitemap	string	no	How the crawl uses the site's sitemap. include (default): the sitemaps the start URL's robots.txt names, or /sitemap.xml, are read with the crawl's identity and robots.txt verdict and their URLs queue
ignoreRobotsTxt	boolean	no	Fetch the pages and sitemap files robots.txt disallows, or whose robots.txt could not be read. robots.txt is still read for every host and its verdict recorded, Crawl-delay applied; each page fetched
maxConcurrency	integer	no	Pages this crawl fetches at once, at most; refused above the service's worker count (4 locally, 2 on the hosted host). It only lowers the crawl's parallelism: the per-host ceiling and minimum interval

Read a crawl by task id. Returns a CrawlReport.

Parameter	Type	Required	Notes
id	string	yes	taskId from crawl

Read a paginated list of crawl page results by task id (the latest attempt's unless attemptId is given). Pages omit the routing audit and trace unless debug is true, and leave out pages whose content repeated an earlier page's (status duplicate) unless includeDuplicates is true. With maxResults…

Parameter	Type	Required	Notes
id	string	yes	—
cursor	string	no	—
limit	number	no	—
attemptId	string	no	—
debug	boolean	no	—
includeDuplicates	boolean	no	List the pages whose body repeated an earlier page's too (status duplicate, markdown null). Default false.
maxResults	integer	no	Follow cursors from cursor on and return up to this many pages in all, each request no larger than what is still wanted; nextCursor then continues exactly after the last page returned, and stoppedBy s

Read a paginated list of crawl errors by task id.

Parameter	Type	Required	Notes
id	string	yes	—
cursor	string	no	—
limit	number	no	—
attemptId	string	no	—

Cancel a crawl task. Completed pages remain queryable.

Parameter	Type	Required	Notes
id	string	yes	—

Restart a paused or failed crawl with the options it was started with. Returns { taskId }; poll get_crawl.

Parameter	Type	Required	Notes
id	string	yes	—

List the crawls the API process is running (those it started and those it resumed at startup; never a batch): each with its id, start URL, status, pages so far and the options it was started with. Empty when nothing runs.

No parameter schema on file.

Persist and run 1-1000 explicit URLs. Returns a taskId (with ignoreInvalidURLs also invalidURLs, the entries skipped); use get_batch_items for paginated results and get_batch_errors for the URLs that failed or that robots.txt refused. With appendToId the urls are added to that existing batch…

Parameter	Type	Required	Notes
urls	array	yes	—
mode	string	no	authed reads the page with the login the person saved for its site (import_login), signed in as them: ask the person first, naming the site. Not with executeJavascript or a webhook: a script could rea
lane	string	no	On a server running on the person's machine: read every page in the person's own Chrome, one at a time, instead of fetching it (lane my_browser, never cached). The person clicks Allow in Chrome, then
access	string	no	How the pages are reached, as three plain choices; ask the person which they want when it matters. standard: Octocrawl's own fetching and its local browser, nothing that costs a third party. enhanced:
formats	array	no	—
includeLinks	boolean	no	—
actions		no	—
robotsOverrides	array	no	Recorded robots overrides, each for one URL of urls (see robotsOverride on scrape).
maxConcurrency	integer	no	Pages of this batch in flight at once; the per-host ceiling still applies. Only lowers the service's worker count; omitted takes it.
ignoreInvalidURLs	boolean	no	Start with the entries of urls that are http(s) URLs and report the rest as invalidURLs (on the answer and on get_batch) instead of refusing the batch. Default false: an entry that is not a URL is ref
allowExternalLinks	boolean	no	Accepted as false only, which already holds: a batch fetches the URLs given and follows no link. true is refused by name; a crawl takes allowExternalLinks, and extraction across links is the M5 multi-
includeSubdomains	boolean	no	Accepted as false only, which already holds: a batch fetches the URLs given and follows no link. true is refused by name; a crawl takes allowSubdomains.
idempotencyKey		no	—
appendToId	string	no	Add urls to this existing batch instead of starting a new job: the job keeps its mode, formats, includeLinks, maxConcurrency and page options (sending one is refused by name), and the answer carries r
webhook		no	—

The items of a batch that did not succeed, across every attempt (a resumed batch keeps its earlier failures): errors [{ id, timestamp, url, status, code, error, httpStatus }] in pages of up to 1000 (cursor, limit), and robotsBlocked, every URL robots.txt refused (policy_denied by a…

Parameter	Type	Required	Notes
id	string	yes	—
cursor	string	no	—
limit	integer	no	—

Hand a finished batch's items that a check stopped (a captcha, a challenge, a login wall: items whose handoff field is set, get_batch's waitingForPerson) to the person in their own Chrome, on a server running on their machine: each opens in a new Chrome tab, one at a time, the person gets through…

Parameter	Type	Required	Notes
id	string	yes	—
waitMs	integer	no	—

Save the person's login to a site (a domain like example.com, or a page URL on it) from the Chrome they already use, on a server running on their machine, so mode authed reads its pages signed in as them. They must be signed in to the site in Chrome's default profile (with a tab of it open for a…

Parameter	Type	Required	Notes
site	string	yes	—
approveTimeoutMs	integer	no	—

The person's saved logins (import_login, octocrawl login import): { logins: [{ domain, savedAt, cookieCount, localStorage, sessionSha256 }] }, never a cookie or a stored value.

No parameter schema on file.

Forget the person's saved login to a site (a domain or a page URL on it).

Parameter	Type	Required	Notes
site	string	yes	—

Free

$0 forever

Every tool, no call limit
No card, and mcprush charges nothing for it
Source published under AGPL-3.0
Runs on your machine — nothing of it reaches our gateway
Nothing to cap, because mcprush bills nothing

Nothing here is billable: mcprush charges nothing to install Octocrawl or to call it, at any volume.

ATrust score 97 / 100

Release 0.4.2 · scanned 13 Oct 2026

Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.

Threat score100

Client score97

Findings0 threat · 3 capability

Capabilitymoderate

Coveragesource

Verificationsource

Surface digest3a54b9cad73debcdae2b7bac560e7867c5c8b3bd4613eee2167c8acffa93a4c7

Score vectorthreat 100 → client 97

Term	Level	What it prices	Points
capability-exposure	moderate	capability blast radius (moderate) — client exposure if the model is manipulated	−3
verification-discount	source	publisher verification (provenance) — cryptographic build provenance ties the artifact to its source	−0
coverage-honesty	source	inspection depth (source) — how much of the target the scan could see	−0

score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.

What the scan could actually read

A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.

Tool surfaceread

Implementation sourceread

Package metadataread

Live transportnot available

Tools were statically extracted from the published source (32 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".

Capability — what it could do if the model were manipulated

Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.

Tool	Capability tags	Why the tag was assigned
preview_monitor	no tags
create_monitor	no tags
list_monitors	no tags
get_monitor	no tags
run_monitor	no tags
get_monitor_run	no tags
pause_monitor	no tags
resume_monitor	no tags
cancel_monitor_run	no tags
create_delivery_destination	external-sink	external-sink: keyword "webhook"
list_delivery_destinations	untrusted-input	untrusted-input: keyword "crawl"
list_deliveries	untrusted-input	untrusted-input: keyword "crawl"
get_delivery	no tags
retry_dead_letter	no tags
scrape_product	untrusted-input	untrusted-input: keyword "scrape", declares openWorldHint: true (interacts with entities outside the server)
batch_products	no tags
scrape	untrusted-input	untrusted-input: keyword "fetch"
get_scrape	untrusted-input	untrusted-input: keyword "scrape"
map	untrusted-input	untrusted-input: keyword "crawl", declares openWorldHint: true (interacts with entities outside the server)
crawl	untrusted-input	untrusted-input: keyword "crawl"
get_crawl	untrusted-input	untrusted-input: keyword "crawl"
get_crawl_pages	untrusted-input	untrusted-input: keyword "crawl"
get_crawl_errors	untrusted-input	untrusted-input: keyword "crawl"
cancel_crawl	untrusted-input	untrusted-input: keyword "crawl"
resume_crawl	untrusted-input	untrusted-input: keyword "crawl"
list_active_crawls	no tags
batch_scrape	untrusted-input	untrusted-input: keyword "scrape"
get_batch_errors	no tags
hand_off_batch	no tags
import_login	no tags
list_logins	no tags
remove_login	no tags

Toxic-flow graph

The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.

flow-1

Untrusted input can drive an external action even though no sensitive source is exposed.

Supply chain and provenance

Integrityfirst-seen

Surface digest3a54b9cad73debcd

Scanned2026-10-13

This is the first scan of this surface here, so there is nothing yet to compare it against.

Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.