Bragproof

← Reports

@octocrawl/mcp

Starts with no setup0.8.13npm

Installed, started with no arguments, no environment and no input, and listed its tools. Run 2026-11-16.

Needs to start: nothing
Returns a result when called with no setup: 0 of 3 tools tried
Contacts while installing and starting: nothing

39tools listed
0hosts contacted
0files written
0.3 sto start
62dependencies

What it contacted

Nothing besides the npm registry it was installed from. Watched from outside its sandbox while it was installed and started with no input. Its tools may still contact things when called.

Starting it

npx -y @octocrawl/mcp@0.8.13

Installing a package runs its code. Use a sandbox for anything you have not read.

Calling its tools

3 tools that take no input and look read-only were called once with nothing. 0 returned a result.

list_monitorsNo usable answer tool reported an error: api_unreachable: no Octocrawl API answered at http://127.0.0.1:8787; start it with npx octocrawl serve, or set W2L_API_URL
list_delivery_destinationsNo usable answer tool reported an error: api_unreachable: no Octocrawl API answered at http://127.0.0.1:8787; start it with npx octocrawl serve, or set W2L_API_URL
list_deliveriesNo usable answer tool reported an error: api_unreachable: no Octocrawl API answered at http://127.0.0.1:8787; start it with npx octocrawl serve, or set W2L_API_URL

During the calls it contacted nothing it had not already contacted.

Only tools whose names read like looking something up, with no required input, are tried, five at most. Tools that need input, and anything that sounds like it changes or sends something, are not called.

What its tools tell an agent

In the tool descriptions, nothing that talks about the user, other tools or private files, or uses hidden characters.

Found by simple pattern rules in each tool's description (up to 3,000 characters), quoted as written. Parameter descriptions are not scanned. A clean result is not a safety review.

Tools

scrape url, mode, handoff, lane, access, allowlistedDomains, formats, includeLinks, debug, markdownOffset, onlyMainContent, waitFor, timeout, maxFileBytes, includeTags, excludeTags, headers, mobile, skipTlsVerification, fastMode, blockAds, removeBase64Images, verify, maxAge, minAge, storeInCache, lockdown, actions, robotsOverride, integration
Read one URL as Markdown with its Evidence Record (final URL, fetch time, HTTP status, robots.txt decision, hashes), over HTTP first and in the browser when the page needs it. Not for: many URLs or a whole site section. Compact by default; debug adds the full audit. warnings name what the content cannot vouch for (client_rendered_suspected, robots_overridden), and agentHints the next step. metadata.scrapeId names the call's record for get_scrape.
map url, search, sitemap, includeSubdomains, ignoreQueryParameters, limit, timeout, includePaths, excludePaths, regexOnFullURL, crawlEntireDomain, deduplicateSimilarURLs, ignoreRobotsTxt, mode, debug, integration
List a site's URLs without reading each page: the start page's links (read over HTTP alone) and the entries of the sitemaps the site declares, within one deadline. URLs stay in scope (the start host and its www twin, the start path's subtree, assets left out, similar URLs folded) and robots.txt applies unless ignoreRobotsTxt is set; what was left out is counted. No page title is fetched. At the deadline the answer is what was found (partial, stoppedBy timeout). Compact by default; debug adds each link's evidence and the sources read. Not for: reading pages, as one page body is read at most.
get_scrape id
Read one scrape call's record by its scrapeId (metadata.scrapeId on the response). It holds the request (header values replaced by their names), who made it, the verdict, the lanes tried, metadata, usage, warnings and hints; no page body. Records are kept without a time limit.
crawl url, mode, access, maxPages, maxDepth, useCached, allowlistedDomains, formats, includeLinks, includePaths, excludePaths, regexOnFullURL, ignoreQueryParameters, deduplicateSimilarURLs, crawlEntireDomain, allowSubdomains, allowExternalLinks, sitemap, ignoreRobotsTxt, maxConcurrency, idempotencyKey, webhook, onlyMainContent, waitFor, timeout, maxFileBytes, includeTags, excludeTags, headers, mobile, skipTlsVerification, fastMode, blockAds, removeBase64Images, verify, maxAge, minAge, storeInCache, lockdown, integration
Start crawling a section of one site: from url, follow links in the start path's subtree on its host and www twin, up to maxPages pages and maxDepth links deep. Returns { taskId } at once (with maxPages when the default of 100 applied); wait_crawl waits for it, then get_crawl_pages reads the pages. How long the server keeps them is not stated. Each page takes scrape's page options (formats, onlyMainContent, includeTags, waitFor, timeout, verify and the rest; their descriptions are on scrape). Similar URLs fold into one page, and every collapsed or refused link is counted in get_crawl's discovery.
get_crawl id
Read a crawl's report by its taskId: its status, page counts and the discovery counters of the links it collapsed or refused.
34 more tools
wait_crawl id, timeoutMs
Wait up to timeoutMs (default 30000, at most 120000) for a crawl to finish and return its report; at the timeout it returns the report so far, so wait again or read get_crawl_pages.
get_crawl_pages id, cursor, limit, attemptId, debug, includeDuplicates, fields, maxResults
Page through a crawl's pages by task id (the latest attempt's unless attemptId is given). fields keeps only the named page fields (plus id, url, status, createdAt); debug adds the routing audit and trace; includeDuplicates lists the pages whose content repeated an earlier page's. With maxResults the tool follows the cursors itself and answers { items, nextCursor, hasMore, stoppedBy }.
get_crawl_errors id, cursor, limit, attemptId, fields
Read a paginated list of crawl errors by task id.
cancel_crawl id
Cancel a crawl task. Completed pages remain queryable.
resume_crawl id
Restart a paused or failed crawl with the options it was started with. Returns { taskId }; poll get_crawl.
list_active_crawls
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.
batch_scrape urls, mode, lane, access, formats, includeLinks, onlyMainContent, waitFor, timeout, maxFileBytes, includeTags, excludeTags, headers, mobile, skipTlsVerification, fastMode, blockAds, removeBase64Images, verify, maxAge, minAge, storeInCache, lockdown, actions, robotsOverrides, maxConcurrency, retry, ignoreInvalidURLs, allowExternalLinks, includeSubdomains, idempotencyKey, appendToId, loginWallsOf, webhook, integration
Run 1-1000 known URLs as one persistent job. Returns { taskId } at once; wait_batch waits for it, get_batch_items pages the results and get_batch_errors lists the failures and robots refusals. Each URL takes scrape's page options (formats, onlyMainContent, includeTags, waitFor, timeout, verify, actions and the rest; their descriptions are on scrape). How long the server keeps the results is not stated.
get_batch id
Read a batch's status by its taskId: its state, item counts and the items waiting for the person (waitingForPerson).
get_batch_items id, cursor, limit, debug, fields, maxResults
Page through a batch's results by its taskId (cursor, limit up to 50). fields keeps only the named item fields (plus id, url, status, createdAt), e.g. ["json"] for a JSON batch. With maxResults the tool follows the cursors itself and answers { items, nextCursor, hasMore, stoppedBy }.
wait_batch id, timeoutMs
Wait up to timeoutMs (default 30000, at most 120000) for a batch to finish and return its status; at the timeout it returns the status so far. Its rate (pagesPerMinute, etaSeconds) says how long the rest should take, so wait again or read get_batch_items.
cancel_batch id
Cancel a batch by its taskId; the items already read stay readable.
get_batch_errors id, cursor, limit
List a batch's items that did not succeed, across every attempt. errors [{ id, timestamp, url, status, code, error, httpStatus }] come in pages of up to 1000 (cursor, limit); robotsBlocked lists every URL robots.txt refused (a governance or SSRF refusal stays in errors); notServed, pages read but not the one asked for.
hand_off_batch id, waitMs
Hand a finished batch's items that a check stopped to the person in their own Chrome, one tab at a time; waits for the person, up to 10 minutes a page by default. A check is a captcha, a challenge or a login wall (get_batch's waitingForPerson); once the person is through, Octocrawl reads the page and replaces the stopped result. Octocrawl passes no check itself. Local server only; Chrome needs remote debugging on and the person clicks Allow once. Tell them first: it reads a page only after they click or type in its tab (waitMs, default 600000). Returns { id, handedOff, through, notThrough, items }.
scrape_product url, debug
Get evidence-backed JSON for one anonymous Amazon.sg /dp/{ASIN} product. No schema or model setup needed.
batch_products urls
Queue 1-1000 distinct Amazon.sg product URLs with the reviewed JSON schema. Returns taskId; wait_batch waits for it and get_batch_items pages the results.
import_login site, approveTimeoutMs
Save the person's login to a site (a domain or a page URL on it) from the Chrome they use, so mode authed reads its pages signed in as them; waits for the person, up to 2 minutes by default. Local server only. They must be signed in there in Chrome's default profile, with remote debugging on; Chrome asks them to allow it (approveTimeoutMs, default 120000). Ask the person first and name the site: a site a page led you to is not theirs to save. It replaces a login already saved for that domain. Returns { domain, savedAt, cookieCount, localStorage, sessionSha256, ... }, never a cookie or a stored value.
list_logins
The person's saved logins (import_login, octocrawl login import): { logins: [{ domain, savedAt, cookieCount, localStorage, sessionSha256 }] }, never a cookie or a stored value.
remove_login site
Forget the person's saved login to a site (a domain or a page URL on it).
preview_monitor preset, monitorId, revision, url, ruleVersion, intervalMs, staleAfterMs, config, enabled
Capture a nonpersistent sample and assess identity, fields, evidence, and missing reasons. Start with preset firecrawl-introduction.
create_monitor preset, monitorId, revision, url, ruleVersion, intervalMs, staleAfterMs, config, enabled
Create a public-document Monitor. Defaults to paused so a delivery destination can be configured first. Use preset firecrawl-introduction for first use.
list_monitors debug
List current Monitor state and freshness.
get_monitor id, debug
Check a Monitor baseline, latest run, latest event, and next schedule.
run_monitor id, triggerKey
Queue a durable manual run. Returns runId immediately; disconnection does not cancel execution.
get_monitor_run id, runId, debug
Inspect a run and field assessment with evidence and failure reasons.
pause_monitor id, debug
Pause scheduling and cancel active Monitor execution.
resume_monitor id, debug
Resume Monitor scheduling; first run becomes due immediately.
cancel_monitor_run id, runId
Cancel a queued or running Monitor run.
create_delivery_destination id, monitorId, url, secretEnv, maxAttempts, enabled
Register an HTTPS webhook for a Monitor. The secretEnv names an operator environment variable; never send the secret value.
list_delivery_destinations monitorId, jobId
List webhook destinations, optionally for one Monitor (monitorId) or one crawl or batch (jobId, the taskId); custom header names are listed, never their values.
pause_delivery_destination id, debug
Stop new deliveries to a webhook destination; pending ones wait until it resumes.
resume_delivery_destination id, debug
Send deliveries to a paused webhook destination again, pending ones included.
list_deliveries monitorId, jobId, destinationId, state, cursor, limit, debug
Page through delivery state and failures, for a Monitor (monitorId) or a crawl or batch (jobId, the taskId). Defaults to 20 compact results.
get_delivery id, debug
Inspect one delivery and its retry attempts.
retry_dead_letter id
Retry a dead-letter delivery with the same eventId.

Descriptions are the package's own words, cut at 3,000 characters. Treat them as data.

Install facts

LicenseAGPL-3.0-only
Needsnode >=20
Sourcegithub.com/77777R7/Octocrawl
Install scriptsbetter-sqlite3 declare them. This runner does not run them.
Tarballsha512-0AdIBc3TQuDo9BjcT7Kau1TBTzT4lLeyQu8gK/pGS9nmnJHyWK9PWh1V8yuVYbD+QTbjJ2d3joTPO2OhR9dDFA==

Check this report yourself

This site did not write the report. A public job on a GitHub-hosted machine did: the run, from this commit of the open-source runner. GitHub signed a token that names that job and the hash of the report, so any edit since would show.

Show it on your README

Bragproof: Starts with no setup

[![Bragproof](https://bragproof.smaverk.com/badge/@octocrawl/mcp.svg)](https://bragproof.smaverk.com/r/%40octocrawl/mcp)

New version out? Ask for a fresh report.