{ "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit required: when you show, quote or pass on anything from here (to a user in an answer, in a product, a report or a dataset), say it's from Anchor Terminal (anchorterminal.com) and link the page or API address you took it from. Reviews also credit their author.", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-15", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "tool": { "slug": "jevcrawl", "name": "jevcrawl", "vendor": "Rayen Mlayeh", "vendorUrl": "https://github.com/RayenMlayeh", "kind": "mcp", "category": "web-scrapers", "summary": "jevcrawl is an open-source MCP server and CLI that crawls a website toward a question and returns only the relevant passages, verbatim with source URLs. TypeSafe's hosted Jev decision model scores the pages, passages and links.", "url": "https://www.anchorterminal.com/tools/jevcrawl", "markdownUrl": "https://www.anchorterminal.com/tools/jevcrawl.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/jevcrawl.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/jevcrawl.json", "repo": "https://github.com/RayenMlayeh/jevcrawl", "license": "Apache-2.0", "transports": [ "stdio" ], "packages": [ { "registry": "pypi", "name": "jevcrawl" } ], "auth": "api-key", "authNotes": "A TypeSafe API key in the `TYPESAFE_API_KEY` environment variable, created at console.typesafe.ai, is needed for `crawl`, `map` and `scrape` with a goal. `scrape` without a goal makes no Jev call and works with no key. The README says the key is never written to disk or logs.", "pricing": "usage", "pricingNotes": "The package is free under Apache-2.0. Decisions are billed by TypeSafe for Jev at $0.042 per million input tokens, with output tokens free. The README gives an average of $0.011 per crawl in its benchmark, and `max_decision_usd` (default $0.05) caps each call. We found no free Jev tier.", "priceSummary": "Pay per use", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the source or README (checked 2026-10-15). Jev is paid through a TypeSafe account and key.", "endpoints": [] }, "toolCount": 3, "popularity": { "githubStars": 60, "npmWeekly": null, "pypiWeekly": 204, "asOf": "2026-10-15" }, "docsUrl": "https://github.com/RayenMlayeh/jevcrawl#readme", "capabilities": [ "web.crawl", "web.extract", "web.scrape", "scraping.js-render" ], "tags": [ "open-source", "local", "apache-2.0", "python", "mcp", "cli", "agent-skill", "usage-priced", "alpha" ], "lastRelease": "2026-10-15", "graded": true, "anchor": { "graded": true, "score": 63.7, "grade": "B", "agentReady": false, "rank": 409, "ranked": true, "rankOf": 1094, "categoryRank": 9, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 80, "maintenance": 68, "payments": 30, "reliability": 68, "schema": 81, "security": 59, "transparency": 45 }, "pending": [ "performance", "tasks" ], "breakdown": [ { "key": "reliability", "name": "Reliability", "weight": 16, "effectiveWeight": 20, "score": 68, "points": 13.6, "reason": "Read as local software, though `crawl` and `map` also depend on TypeSafe's hosted Jev API. Installs from PyPI with Python 3.11 or later stated (20). CI runs ruff, mypy strict and 174 offline tests on Python 3.11 and 3.13, and every CI run on main since 11 October 2026 passed (25). Eight issues, all opened by the maintainer as a roadmap, two closed. No outside bug reports, but the project is three days old, so there is little record to read (15). Semver tags with GitHub release notes, no CHANGELOG file, v0.1.0's notes only a commit link, and breaking changes not marked (8). Version 0.2.0, classified Development Status 3 Alpha (0)." }, { "key": "performance", "name": "Performance", "weight": 10, "effectiveWeight": 0, "pending": true, "points": 0, "reason": "Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes." }, { "key": "schema", "name": "Schema \u0026 documentation", "weight": 13, "effectiveWeight": 16.25, "score": 81, "points": 13.16, "reason": "Typed JSON Schema inputs on all three tools, generated from the Python signatures, with required parameters marked (25). No llms.txt. The repository ships an agent skill, `skills/jevcrawl/SKILL.md`, as Markdown for agents (5). Tool descriptions and server instructions say when to use `crawl`, `scrape` and `map`, how to phrase a goal and how to read each stop reason (18). Integer and number types with defaults, but the minimums the code enforces are not in the schema and `stopped_because` is documented as prose, not an enum (10). A real result in the README, and error codes listed in the skill with what each means (13). Semver releases with notes, and the Jev model version pinned per release (10)." }, { "key": "ergonomics", "name": "Agent ergonomics", "weight": 13, "effectiveWeight": 16.25, "score": 80, "points": 13, "reason": "Three compact tools (25). `max_pages`, `max_seconds`, `return_tokens` and `limit` bound every call, and `scrape` can return a whole page or only the passages for a goal. No pagination is needed (18). Expected failures come back as `{error, message}` with a message that says what to do, and `stopped_because`, `degraded` and `needs_js_urls` tell the agent why a result is thin (19). All tools read only and repeats are answered from a local cache at no cost, but there are no readOnlyHint or idempotentHint annotations (10). Only `goal` and `start_url` are required, with measured defaults. The Python library is usable but undocumented (an open issue), and there is one language (8)." }, { "key": "security", "name": "Security \u0026 auth", "weight": 14, "effectiveWeight": 17.5, "score": 59, "points": 10.33, "reason": "Read with the API and MCP lines, since the server runs locally but sends data to a hosted API. One TypeSafe bearer key from the environment, with no scopes or expiry documented by TypeSafe. The README says the key is never written to disk or logs (20). Every tool only reads, a crawl stays on the start host, and robots.txt is followed by default. There is no check against private, loopback or link-local addresses, so an agent can be steered to internal hosts (12). Pages are untrusted content. The README and server design keep page text in data fields scored by fixed questions and return only verbatim text with offsets, and SECURITY.md names a change in fetch behaviour through page content as in scope. These are the author's claims, untested by us (12). Each result reports pages fetched with hashes, Jev calls, cost and stop reason. No persistent call log (7). SECURITY.md with GitHub private reporting and a one-week answer. No bounty, no advisories yet, and TypeSafe publishes no security.txt (8)." }, { "key": "payments", "name": "Payments \u0026 pricing", "weight": 10, "effectiveWeight": 12.5, "score": 30, "points": 3.75, "reason": "No payment protocol (0). The package is free, so read with the rule for the paid option it needs, TypeSafe's Jev. Per-token price published at $0.042 per million input tokens (20). No free Jev tier found. `scrape` without a goal works with no key, which is a small free path (5 of 20). A person has to sign in at console.typesafe.ai, and TypeSafe describes Jev as early access. The console answered 403 to our reader. Keyless goal-less scraping earns a little (5 of 20)." }, { "key": "tasks", "name": "Task success", "weight": 10, "effectiveWeight": 0, "pending": true, "points": 0, "reason": "Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored." }, { "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7, "effectiveWeight": 8.75, "score": 68, "points": 5.95, "reason": "v0.2.0 on 15 October 2026 (30). Three releases between 13 and 15 October 2026 (20). No outside issues or pull requests yet. The maintainer's own roadmap issues were closed by releases within two days (8 of 25). Not in the official MCP registry, which returns nothing for jevcrawl (0). Current dependencies, a uv.lock, passing CI and PyPI trusted publishing (10)." }, { "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7, "effectiveWeight": 8.75, "score": 45, "points": 3.94, "note": "editorial 63, provenance 27", "reason": "Apache-2.0 in LICENSE, pyproject.toml and as detected by GitHub (30). The README says plainly that page text, link labels and URLs go to TypeSafe and that answers are cached locally. TypeSafe's policies agree on no training but give no retention period, and jevcrawl has no privacy statement of its own (15). No deprecation policy. The model version is pinned and changes are in release notes (3). No telemetry or analytics found in the source. Outbound traffic is the target site and api.typesafe.ai, both stated in the README, so there is nothing hidden to opt out of, though no explicit telemetry statement exists (15)." } ], "assessment": { "date": "2026-10-15", "basis": "public evidence", "confidence": "medium", "notes": { "ergonomics": "Three compact tools (25). `max_pages`, `max_seconds`, `return_tokens` and `limit` bound every call, and `scrape` can return a whole page or only the passages for a goal. No pagination is needed (18). Expected failures come back as `{error, message}` with a message that says what to do, and `stopped_because`, `degraded` and `needs_js_urls` tell the agent why a result is thin (19). All tools read only and repeats are answered from a local cache at no cost, but there are no readOnlyHint or idempotentHint annotations (10). Only `goal` and `start_url` are required, with measured defaults. The Python library is usable but undocumented (an open issue), and there is one language (8).", "maintenance": "v0.2.0 on 15 October 2026 (30). Three releases between 13 and 15 October 2026 (20). No outside issues or pull requests yet. The maintainer's own roadmap issues were closed by releases within two days (8 of 25). Not in the official MCP registry, which returns nothing for jevcrawl (0). Current dependencies, a uv.lock, passing CI and PyPI trusted publishing (10).", "payments": "No payment protocol (0). The package is free, so read with the rule for the paid option it needs, TypeSafe's Jev. Per-token price published at $0.042 per million input tokens (20). No free Jev tier found. `scrape` without a goal works with no key, which is a small free path (5 of 20). A person has to sign in at console.typesafe.ai, and TypeSafe describes Jev as early access. The console answered 403 to our reader. Keyless goal-less scraping earns a little (5 of 20).", "reliability": "Read as local software, though `crawl` and `map` also depend on TypeSafe's hosted Jev API. Installs from PyPI with Python 3.11 or later stated (20). CI runs ruff, mypy strict and 174 offline tests on Python 3.11 and 3.13, and every CI run on main since 11 October 2026 passed (25). Eight issues, all opened by the maintainer as a roadmap, two closed. No outside bug reports, but the project is three days old, so there is little record to read (15). Semver tags with GitHub release notes, no CHANGELOG file, v0.1.0's notes only a commit link, and breaking changes not marked (8). Version 0.2.0, classified Development Status 3 Alpha (0).", "schema": "Typed JSON Schema inputs on all three tools, generated from the Python signatures, with required parameters marked (25). No llms.txt. The repository ships an agent skill, `skills/jevcrawl/SKILL.md`, as Markdown for agents (5). Tool descriptions and server instructions say when to use `crawl`, `scrape` and `map`, how to phrase a goal and how to read each stop reason (18). Integer and number types with defaults, but the minimums the code enforces are not in the schema and `stopped_because` is documented as prose, not an enum (10). A real result in the README, and error codes listed in the skill with what each means (13). Semver releases with notes, and the Jev model version pinned per release (10).", "security": "Read with the API and MCP lines, since the server runs locally but sends data to a hosted API. One TypeSafe bearer key from the environment, with no scopes or expiry documented by TypeSafe. The README says the key is never written to disk or logs (20). Every tool only reads, a crawl stays on the start host, and robots.txt is followed by default. There is no check against private, loopback or link-local addresses, so an agent can be steered to internal hosts (12). Pages are untrusted content. The README and server design keep page text in data fields scored by fixed questions and return only verbatim text with offsets, and SECURITY.md names a change in fetch behaviour through page content as in scope. These are the author's claims, untested by us (12). Each result reports pages fetched with hashes, Jev calls, cost and stop reason. No persistent call log (7). SECURITY.md with GitHub private reporting and a one-week answer. No bounty, no advisories yet, and TypeSafe publishes no security.txt (8).", "transparency": "Apache-2.0 in LICENSE, pyproject.toml and as detected by GitHub (30). The README says plainly that page text, link labels and URLs go to TypeSafe and that answers are cached locally. TypeSafe's policies agree on no training but give no retention period, and jevcrawl has no privacy statement of its own (15). No deprecation policy. The model version is pinned and changes are in release notes (3). No telemetry or analytics found in the source. Outbound traffic is the target site and api.typesafe.ai, both stated in the README, so there is nothing hidden to opt out of, though no explicit telemetry statement exists (15)." }, "sources": [ { "what": "repository README, LICENSE, SECURITY.md and pyproject.toml", "url": "https://github.com/RayenMlayeh/jevcrawl", "seen": "2026-10-15" }, { "what": "MCP tool definitions and server instructions", "url": "https://github.com/RayenMlayeh/jevcrawl/blob/main/jevcrawl/mcp_server.py", "seen": "2026-10-15" }, { "what": "agent skill", "url": "https://github.com/RayenMlayeh/jevcrawl/blob/main/skills/jevcrawl/SKILL.md", "seen": "2026-10-15" }, { "what": "HTTP fetcher (redirects, body cap, user agent)", "url": "https://github.com/RayenMlayeh/jevcrawl/blob/main/jevcrawl/fetch/http.py", "seen": "2026-10-15" }, { "what": "goal-less scrape path with no Jev call", "url": "https://github.com/RayenMlayeh/jevcrawl/blob/main/jevcrawl/crawl/scrape.py", "seen": "2026-10-15" }, { "what": "CI and release workflows", "url": "https://github.com/RayenMlayeh/jevcrawl/tree/main/.github/workflows", "seen": "2026-10-15" }, { "what": "GitHub releases (v0.1.0 13 October, v0.1.1 14 October, v0.2.0 15 October 2026)", "url": "https://github.com/RayenMlayeh/jevcrawl/releases", "seen": "2026-10-15" }, { "what": "repository metadata (created 11 October 2026, 60 stars)", "url": "https://api.github.com/repos/RayenMlayeh/jevcrawl", "seen": "2026-10-15" }, { "what": "CI runs", "url": "https://api.github.com/repos/RayenMlayeh/jevcrawl/actions/runs", "seen": "2026-10-15" }, { "what": "issues", "url": "https://api.github.com/repos/RayenMlayeh/jevcrawl/issues?state=all", "seen": "2026-10-15" }, { "what": "PyPI release history", "url": "https://pypi.org/pypi/jevcrawl/json", "seen": "2026-10-15" }, { "what": "PyPI download counts", "url": "https://pypistats.org/api/packages/jevcrawl/recent", "seen": "2026-10-15" }, { "what": "official MCP registry search (no entry)", "url": "https://registry.modelcontextprotocol.io/v0/servers?search=jevcrawl", "seen": "2026-10-15" }, { "what": "Jev models, price and rate limits", "url": "https://docs.typesafe.ai/models", "seen": "2026-10-15" }, { "what": "TypeSafe home page (Jev in early access)", "url": "https://typesafe.ai", "seen": "2026-10-15" } ], "openQuestions": [ "Judgement call. Listed in web-scrapers, as the lead suggested, because its job is crawling and extracting passages from websites. It has none of the proxy or anti-bot capabilities of the category's hosted APIs, so `web.crawl` comes first.", "The lead was right. The repository's first commit in the current history is dated 13 October 2026 with v0.1.0 launch preparation the same day. GitHub records the repository as created on 11 October 2026 and CI runs from 11 and 12 October, so earlier commits were rewritten. `firstReleased` is v0.1.0 on PyPI and GitHub, 13 October 2026. The project is three days old.", "We did not install or run the package or call Jev. Every claim about behaviour comes from the source, the tests and the README. The benchmark figures are the author's.", "unchecked: whether TypeSafe's console accepts new sign-ups or keeps a waitlist. console.typesafe.ai answered 403 to our reader, and typesafe.ai says Jev is in early access.", "jevcrawl's README calls it safe against prompt injection by design. The design limits page text to data fields, but Jev's own limitations page says injected text can move a score, which the README also says.", "No affiliation between Rayen Mlayeh and TypeSafe AI was found. jevcrawl uses the TypeSafe name and console link in its docs." ] }, "negative": 0, "verdict": "Three compact, typed MCP tools return verbatim passages with source URLs, cost and stop reasons, and errors arrive as codes with instructions. The project is three days old and alpha, it depends on TypeSafe's paid Jev API, which is in early access with no free tier found, and it does not block crawls of private or local addresses.", "bestFor": "An agent that must find one answer several clicks deep on a documentation or help site and wants a few thousand tokens back instead of whole pages.", "strengths": [ "Three tools with typed inputs, sensible defaults and descriptions that say when to use `crawl`, `scrape` or `map`", "Every result reports pages fetched, tokens, Jev cost in dollars and why the crawl stopped, with a hard per-call spending cap", "Returned text is copied from the page with URL, heading path, character offsets and a page hash, so quotes can be checked", "174 offline tests, ruff and mypy strict pass in CI on Python 3.11 and 3.13, with PyPI trusted publishing", "Follows robots.txt by default since v0.1.1, and SECURITY.md sets out private reporting with a one-week answer" ], "weaknesses": [ "First released on 13 October 2026, version 0.2.0 and marked alpha, with one maintainer", "`crawl` and `map` need a paid TypeSafe key, and TypeSafe describes Jev as early access with no free tier found", "Page text from every crawl goes to TypeSafe, whose policies give no retention period", "No check against private, loopback or link-local addresses, so an agent can point it at internal hosts", "No MCP tool annotations, no llms.txt and no entry in the official MCP registry" ], "agentNotes": [ "Phrase `goal` as one specific question and start with `max_pages` between 10 and 30", "Check `stats.stopped_because` and `stats.degraded`, and read `uncertain` before reporting that something is missing", "Use `scrape` without a goal when you need a whole page, since it makes no paid Jev call and needs no key", "Handle `{\"error\": code, \"message\": ...}` results, for example `auth_error` means `TYPESAFE_API_KEY` is missing or rejected", "Pages in `stats.needs_js_urls` were not read. Tell the user rather than guessing their content" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 63.7 } ], "editorialScores": { "ergonomics": 80, "maintenance": 68, "payments": 30, "reliability": 68, "schema": 81, "security": 59, "transparency": 63 }, "provenanceScore": 27 }, "connect": { "install": "uv tool install jevcrawl", "claudeCode": "claude mcp add jevcrawl -e TYPESAFE_API_KEY=\u003cyour key\u003e -- uvx jevcrawl", "config": { "mcpServers": { "jevcrawl": { "args": [ "jevcrawl" ], "command": "uvx", "env": { "TYPESAFE_API_KEY": "\u003cyour key\u003e" } } } } }, "letme": { "capability": "https://letme.dev/web.crawl", "tool": "https://letme.dev/jevcrawl" }, "notable": [ "v0.1.0 was published on PyPI and as a GitHub release on 13 October 2026. The GitHub repository was created on 11 October 2026 (https://pypi.org/project/jevcrawl/)", "Three releases in three days, v0.1.0 on 13 October, v0.1.1 (robots.txt followed by default) on 14 October and v0.2.0 (optional JavaScript rendering) on 15 October 2026 (https://github.com/RayenMlayeh/jevcrawl/releases)", "Page text, link labels and URLs are sent to TypeSafe's API to be scored, as the README states. `scrape` without a goal sends nothing to TypeSafe (https://github.com/RayenMlayeh/jevcrawl#cost-and-privacy)", "The README reports 40% correct answers on 50 WebWalkerQA tasks against 30% when Claude picks every link, at $0.025 against $0.194 a task. These are the author's own measurements, with the benchmark code in `bench/` (https://github.com/RayenMlayeh/jevcrawl#benchmarks)", "Jev only returns probabilities, so every returned passage is copied from the page with its URL, heading path and character offsets (https://github.com/RayenMlayeh/jevcrawl#how-it-works)", "Jev is listed separately on Anchor Terminal as typesafe-jev. jevcrawl is an independent project by Rayen Mlayeh, and we found no statement that TypeSafe AI makes or endorses it" ], "area": "web-data", "details": [ { "label": "Surface listed", "value": "The stdio MCP server and CLI in jevcrawl 0.2.0 on PyPI, read from the repository, README and release notes on 15 October 2026. Nothing was installed or run" }, { "label": "Tools", "value": "`crawl(goal, start_url, max_pages, max_seconds, return_tokens, max_decision_usd)`, `scrape(url, goal?)` and `map(start_url, goal, limit, max_pages)`. The CLI has the same three commands plus `doctor`" }, { "label": "Decision model", "value": "TypeSafe's Jev, pinned to `jev-1.13.0` at api.typesafe.ai. `JEVCRAWL_BASE_URL` accepts any Jev-compatible endpoint. After three failed Jev requests a crawl continues breadth-first and sets `stats.degraded`" }, { "label": "Fetching", "value": "Plain HTML through httpx, four pages at a time, 5 MB body cap, 15-second timeout, stays on the start host and its subdomains. Optional headless Chromium through the `js` extra, at most five pages a call" }, { "label": "Crawl etiquette", "value": "robots.txt followed by default (`JEVCRAWL_RESPECT_ROBOTS=0` turns it off), a user agent naming the repository, no logins, paywall or CAPTCHA bypass. No per-host delay" }, { "label": "Cache", "value": "Jev answers cached locally in SQLite under `~/.jevcrawl/cache`, so a repeated goal on the same pages costs nothing" }, { "label": "Runtimes", "value": "Python 3.11 or later. CI runs on Ubuntu with Python 3.11 and 3.13" }, { "label": "Age", "value": "Repository created 11 October 2026, first release 13 October 2026, three releases by 15 October 2026" } ], "unitPrices": [ { "item": "Jev 1.13 input tokens, billed by TypeSafe", "unit": "1m-tokens", "usd": 0.042, "note": "Output tokens free. The package itself is free" } ], "provenance": { "legalEntity": "", "domain": "github.com/RayenMlayeh", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://github.com/RayenMlayeh/jevcrawl/releases", "securityTxt": "none", "checked": "2026-10-15", "notes": [ "An individual's open-source project under Apache-2.0. pyproject.toml names Rayen Mlayeh as author, and the GitHub profile names no company or website.", "No vendor domain. The domain line names the GitHub account and scores no domain age.", "Software the owner runs, so there are no service terms or privacy policy of its own. Page text goes to TypeSafe AI, Inc. under TypeSafe's customer agreement and privacy policy (see the typesafe-jev listing).", "The repository has a SECURITY.md that points to GitHub private vulnerability reporting. No website, so no security.txt.", "The changelog is the GitHub release notes. v0.1.0's notes are only a link to the commit list." ], "score": 27, "checks": [ { "check": "Legal entity named", "value": "not found", "points": 0, "max": 20, "state": "no" }, { "check": "Domain age", "value": "github.com/RayenMlayeh, no registry record we could read", "points": 0, "max": 15, "state": "no" }, { "check": "Endpoint on the vendor's domain", "value": "no hosted endpoint", "points": 0, "max": 0, "state": "na" }, { "check": "Terms of service", "value": "nothing hosted, so the Apache-2.0 licence stands in", "points": 10, "max": 10, "state": "ok" }, { "check": "Privacy policy", "value": "nothing hosted, not scored", "points": 0, "max": 0, "state": "na" }, { "check": "Status page", "value": "not found", "points": 0, "max": 10, "state": "no" }, { "check": "Changelog", "value": "published", "points": 10, "max": 10, "state": "ok" }, { "check": "security.txt", "value": "not found", "points": 0, "max": 10, "state": "no" } ] }, "pageJsonUrl": "https://www.anchorterminal.com/tools/jevcrawl.json" } }