Presend dependency checks MCP server
online · 100% uptimeio.github.presendapp/presend-deps·v1.0.0Check an npm/PyPI package before an AI agent installs it: 5 focused supply-chain tools.
0 stars
Reviews
Write oneNobody has reviewed Presend dependency checks yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Presend dependency checks tools (5)
write = sends, deletes, buys or postsmaintainer_change_checkFreePublisher-change analysis is npm only. Also reports whether the package exists (found) and its age (first_published, package_age_days, new_package if first published less than 30 days ago), for npm and for PyPI; on PyPI only existence and age are available. Flags a previously unseen human publisher taking over a package after 180+ days of inactivity, within the last 365 days (the event-stream attack pattern). npm trusted publishing (verified OIDC identity, not just a bot-like account name), pre-release, and handovers to a publisher who already maintains another widely used package (100k+ weekly downloads) are reported but not flagged. Does not detect hijacked existing accounts; a heuristic for review, not proof.
repo_health_checkFreeMaintenance signals for a GitHub repository given as owner/name: stars, forks, open issues, license, archived and fork flags, creation date and age, days since last push, topics. Use it to judge whether a dependency looks maintained or abandoned. For an npm or PyPI package whose repository you do not know, supply_chain_check resolves it from registry metadata and includes these signals. GitHub only; missing or private repositories return found: false.
supply_chain_checkFreeCall this before installing or adding a package (npm install, pip install, a new entry in a manifest), especially one whose name you recalled or that a model suggested. One-call risk check: combines vulnerability_check (OSV.dev), typosquat_check, maintainer_change_check (npm only) and repo_health_check (when the GitHub repo can be resolved) into one overall verdict. A package that does not exist on npm or PyPI gets overall_risk 'package_not_found': the name may be invented, do not install it. A package first published less than 30 days ago gets the 'new_package' flag and overall_risk 'review_recommended': new packages are where invented and look-alike names get registered, so confirm the name against the project's own documentation before installing (on PyPI the age is that of the oldest release still published; being new does not make a package malicious). Use the individual tools to investigate one signal. Vulnerabilities are checked for the given version, or the latest published one (version_checked, version_source). If a check could not run (rate limit, upstream error), it is listed in unavailable_checks and overall_risk is 'incomplete', never 'no_signals_found'.
typosquat_checkFreeCall before installing a package whose name you typed or recalled. Checks whether an npm or PyPI package name is a near-miss of a well-known package (typosquatting), with an edit-distance threshold scaled to name length; names of 3 characters or fewer are not fuzzy-matched. Uses a curated list of popular names, so a clean result does not prove a package is safe. It does not check that the package exists: supply_chain_check does.
vulnerability_checkFreeChecks a package (optionally a specific version) against OSV.dev for known vulnerabilities: npm, PyPI, Go, crates.io, Maven, RubyGems, Packagist and NuGet. Use cve_lookup when you already have a CVE/GHSA ID, or supply_chain_check for a combined verdict.
Public scan report
scanner v0.1.10 · 2026-10-03 · same rubric, same numbers if you re-run it
- –Code scanremote-only server, no package to scann/a
- Live reliabilityremote reachable in 292ms20/20
- Tool poisoning5 tool descriptions checked15/15
- Auth qualityopen endpoint, read-only tools10/15
- Maintenancelast push 0 days ago15/15
- Maintainer identityregistry namespace matches repository owner6/10
How Presend dependency checks compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 88/100
- higher than 80% of 4,460 AI and agents servers
- Tools
- 5
- the typical AI and agents server has 6
- Tools that change things
- 0%
- typical: 0%. Fewer write tools means less an agent can break
- Uptime
- 100%
- of our recent checks; the typical remote AI and agents server answers 100%
- Response time
- 148 ms
- faster than 77% of 2,331 AI and agents servers
What its tools let an agent do: 5 read
Install Presend dependency checks in Claude Code, Cursor or VS Code
claude mcp add --transport http presend-deps https://presend.pages.dev/mcp-deps
What the publisher says
From the Presend dependency checks repository's README, as published. We do not edit it. Read it on GitHub
Presend — Free Privacy Tools, a Security API, and an MCP Server for AI Agents
Presend checks npm and PyPI packages before they are installed: typosquats, known vulnerabilities of the version you use, publisher changes (npm), and names that do not exist or were first published in the last 30 days. It is available as a free API, an MCP server for AI agents and a GitHub Action. The site also has free browser tools; the file tools process files locally.
Open Presend · API docs · OpenAPI spec · MCP server · Measurements · For teams
Why Presend?
- Before an agent installs a package -- the MCP tool supplychaincheck reports packagenotfound for a name that does not exist on npm or PyPI (it may be invented by a model) and new_package for one first published less than 30 days ago.
- Measured false alarms -- the typosquat check is measured on the most downloaded PyPI packages and the npm-high-impact list, with the scripts to reproduce it: see the measurements page.
- Real supply-chain signal (API) -- maintainer-change-check flags a package recently taken over by a previously unseen publisher after a long dormancy (the event-stream pattern; it does not detect hijacked existing accounts).
- What it is not -- not a malware scanner: it reports signals worth a look before installing, it does not analyse package code.
- No account -- the API and the MCP server are free, with no signup and no key; per-minute rate limits apply. A paid offer for teams is being tested: Presend for teams.
- Browser file tools -- the file tools (EXIF, PDF, images, office files) run locally with Web Crypto, Canvas and FileReader. A few other tools rely on a network service (speech recognition, password breach lookup, link preview...); the privacy page lists each one.
- PWA -- install on mobile or desktop.
API & MCP Server
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Presend dependency checks: common questions
- Is Presend dependency checks MCP server safe?
- Yes, by our scan: it is graded A (88/100). Read the Presend dependency checks safety report
- How do I install Presend dependency checks?
- It runs remotely at presend.pages.dev. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
- Does Presend dependency checks need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Presend dependency checks maintained?
- The last commit was 32 days ago (2026-10-03). The latest release is v1.0.0.
- Is Presend dependency checks up?
- 100% of our last 28 checks got an answer. We check remote servers about four times a day.
- What can I use instead of Presend dependency checks?
- Servers from other publishers that do the same job: Decionis MCP server, mcptoon MCP server and Mockserver MCP server.
- How does Presend dependency checks compare with other AI and agents MCP servers?
- safety score 88/100 (higher than 80% of 4,460 AI and agents servers); tools 5 (the typical AI and agents server has 6); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to Presend dependency checks
Same job from other publishers: the closest match first, then the best rated.
- DecionisAuthorize consequential AI agent actions before executionnot reviewedEstablishedA
- mcptoonMCP tools + agent skills in one zero-dependency CLI: 71,929 -> 581 tokens (-99.2%, measured).not reviewedEstablishedA
- MockserverMock, record/replay, verify and chaos-test any HTTP, REST, gRPC or LLM dependency over MCP.not reviewedEstablishedA
- KilnSpawn an object into existence: describe it, and your agent designs it, checks it, and 3D prints it.not reviewedEstablishedB
- three.ws ProvenanceAppend-only, signed, on-chain-verifiable agent action log — record and audit what agents did.not reviewedEstablishedB