Skip to content

Presend dependency checks MCP server

io.github.presendapp/presend-depspresendappstreamable-httpv1.0.0Scanned

Check an npm/PyPI package before an AI agent installs it: 5 focused supply-chain tools.

5 tools: 5 change things.

Tools: 0 delete, 0 irreversible, 5 write, 0 read.
  • Reads private data · 0
  • Reads text others write · 4
  • Can send data out · 0
  • 2 findings

Tools listed without sign-in. Remote posture

With Anlyon

5 tools here change things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the Presend dependency checks MCP server can do

The Presend dependency checks MCP server is published by the GitHub account presendapp. It has 5 tools. It can create or change data (5 tools: maintainer_change_check, repo_health_check, supply_chain_check, typosquat_check and 1 more), but cannot delete data. None of its tools only reads.

4 tools bring in text other people can write (maintainer_change_check, repo_health_check, supply_chain_check and 1 more).

The fixed checks matched 2 findings (annotation-conflict). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 20, 2026, version 1.0.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

5 tools

Changes things 5Claude Code: ask
  • maintainer_change_checkPublisher-change analysis is npm only.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Publisher-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.

    Annotations the server declares

    • title: Package maintainer change check
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • repo_health_checkMaintenance 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.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Maintenance 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.

    Annotations the server declares

    • title: Repository health check
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • supply_chain_checkCall 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.Reads text others write1 finding

    Why it is in this group

    • The description's first verb is "call": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Warn

      The server marks "supply_chain_check" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "call": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Call 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 and should not be installed. 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 the name is worth confirming 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'. Also flags a version marked deprecated on npm or yanked on PyPI.

    Annotations the server declares

    • title: Package supply-chain check
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • typosquat_checkCall before installing a package whose name you typed or recalled.1 finding

    Why it is in this group

    • The description's first verb is "call": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "typosquat_check" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "call": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Call 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.

    Annotations the server declares

    • title: Package typosquat check
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • vulnerability_checkChecks a package (optionally a specific version) against OSV.dev for known vulnerabilities: npm, PyPI, Go, crates.io, Maven, RubyGems, Packagist and NuGet.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Checks a package (optionally a specific version) against OSV.dev for known vulnerabilities: npm, PyPI, Go, crates.io, Maven, RubyGems, Packagist and NuGet. For npm and PyPI, a name that does not exist returns found: false and vulnerable: null, never a clean result. Use supply_chain_check for a combined verdict.

    Annotations the server declares

    • title: Package vulnerability check
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write4
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:09 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
5
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 5 tools that change things (5 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://presend.pages.dev/mcp-deps: tools/list returned 5 tools to an anonymous client, including maintainer_change_check (write), repo_health_check (write), supply_chain_check (write), typosquat_check (write), vulnerability_check (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

2 warn
  • The server marks "supply_chain_check" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "call": a word for a change.

    What this check looks for
  • The server marks "typosquat_check" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "call": a word for a change.

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http presend-deps https://presend.pages.dev/mcp-deps
claude mcp add --transport http presend-deps https://presend.pages.dev/mcp-deps

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__presend-deps__maintainer_change_check",
      "mcp__presend-deps__repo_health_check",
      "mcp__presend-deps__supply_chain_check",
      "mcp__presend-deps__typosquat_check",
      "mcp__presend-deps__vulnerability_check"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as presend-deps. Review it before you use it.

Capability tags behind 4 rules
  • mcp__presend-deps__maintainer_change_check untrusted-input
  • mcp__presend-deps__repo_health_check untrusted-input
  • mcp__presend-deps__supply_chain_check untrusted-input
  • mcp__presend-deps__vulnerability_check untrusted-input

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/io.github.presendapp/presend-deps/verify?hash=a54e4eed9abf2bf281b5cf48a2736f3b88349f8f6aa5daa20a2eba9c944328f2" | jq -e '.changed == false'

Pinned hash a54e4eed9abf, from Nov 20, 2026, 08:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.presendapp/presend-deps/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.github.presendapp/presend-deps
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.presendapp/presend-deps.svg)](https://radar.anlyon.com/servers/io.github.presendapp/presend-deps)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:45 UTC.

Presend dependency checks MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Presend dependency checks MCP server safe?

No scan can promise that. What its definitions show: 5 tools, 5 of which can change, send or delete something, and 2 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Presend dependency checks MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the Presend dependency checks MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the Presend dependency checks MCP server have?

5 tools: 5 write. maintainer_change_check, repo_health_check, supply_chain_check, typosquat_check and vulnerability_check.

Does the Presend dependency checks MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Presend dependency checks MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the Presend dependency checks MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 20, 2026.