Skip to content

MCP servers › network.curated › curated

MCP server · registry snapshot 2026-10-23 · last tested 2026-10-23

network.curated/curated

Keep and share lists of recommendations with your own notes, and read lists from people you trust. — the publisher's description

1 of 2 record checks metRead-only · tools listed 2026-10-23Topic: productivity-and-docs · AI-classifiedPricing: free · AI-classifiedversion 1.0.1streamable HTTP48 tools

Summary

network.curated/curated is a remote MCP server listed in the official MCP registry at version 1.0.1. On 2026-10-23 ProtocolProbe connected to it in read-only mode and read its inventory: 48 tools, 1 resource and 3 prompts.

Record checks

1 of 2 record checks met · 7 do not apply

  • met: Registry entry is active and says how to run it
  • not met: Source repository link opens
  • not applicable: Repository is not archived
  • not applicable: Code pushed to the repository in the 90 days before our check
  • not applicable: Repository publishes a security policy (SECURITY.md)
  • not applicable: Package names its licence with a standard (SPDX) identifier
  • not applicable: The version the registry lists can be installed and is not withdrawn
  • not applicable: npm package carries build provenance (attestation)
  • not applicable: No known critical or high advisory in the package or its dependencies
  • Not ranked by downloads: a remote server publishes no download figure
  • Not ranked by stars: no public GitHub repository

From public records, not a safety rating. Each check with its reason · Is it safe to install?

Key facts

Runs
remote (hosted by the publisher)
Transport
streamable HTTP
Sign-in
none needed to open a session
Tools
48
Described as changing data
24 of 48 toolsAI-classified
Mainly works on
files and code on the machine it runs on; accounts and data in outside web servicesAI-classified
Topic
productivity-and-docsAI-classified
Pricing
freeAI-classified
Last tested
2026-10-23

Add to your client

Observed fact

This server accepted a session without any credential and lists 18 tools whose name or declaration suggests they change data (create_list, update_list, archive_list, delete_list, add_item and 13 more). That is our reading of the names; we did not call them. Source: our connection, 2026-10-23.

Worth knowing before you connect it

  • 24 tools are described as changing something (create_list, update_list, archive_list, …): our AI model's reading of the descriptions, not something we tested, and the server opened a session without any credential. We did not call them.

Each line comes from a section below, with its source and date.

How fresh this is

Live-tested
yes, a real session (not a text-only review)
Last tested
2026-10-23
Mode
read-only (no tool calls)
Latest version
1.0.1, published 2026-10-19 (registry, as of the 2026-10-23 snapshot)
First listed version
2026-10-17 (earliest version still in the registry; older removed versions would be earlier)
Version history
2 versions listed, 2026-10-17 to 2026-10-19; 2 in the 90 days before the 2026-10-23 snapshot.
Most recent 2 versions
  • 1.0.1 · 2026-10-19
  • 1.0.0 · 2026-10-17
(versions still listed in the registry only)
Registry data
snapshot 2026-10-23
Package and repository
checked 2026-10-23
Engine
mcp-runtime-engine@0.1.0 · sdk@1.32.0

Changes since the last refresh

New in the registry: not in the list of 2026-10-04, listed on 2026-10-23 with version 1.0.1 (published 2026-10-19).

Source: the official MCP Registry list on 2026-10-04 and on 2026-10-23.

What it is

What does this server offer?

Observed inventory
48tools
1resources
3prompts

What it mainly works on, as our AI model read its tool descriptions: files and code on the machine it runs on; accounts and data in outside web services.

24 of 48 tools are described as changing something (creating, editing, deleting, sending or running). For 8 the reading was uncertain, so no mark is shown.

  • account_contextreads or searches

    “Verify the connected account and its readiness before creating or changing lists.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    Takes no inputs.

  • list_my_listsreads or searches

    “Return the person's own lists (slug, title, status, Inbox flag) and the lists they have access to.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    Takes no inputs.

  • create_liston 11 other serverscreates or changes datadescribed as changing data

    “Create a new private list and return the exact slug to reuse in add_item.”

    Publisher declares: read-only no · destructive no · idempotent no · open-world no

    4 inputs, 1 required
    • titlestringrequired“List title, 120 characters or fewer.”
    • subtitlestring“One-line description of what the list is and who it's for.”
    • categorystring“Usually omit: Curated picks the category from the title and picks.”
    • idempotency_keystring“Optional retry key.”
  • update_liston 2 other serverscreates or changes datadescribed as changing data

    “Edit a list's title, subtitle, or category.”

    Publisher declares: read-only no · destructive yes · idempotent yes · open-world no

    4 inputs, 1 required
    • liststringrequired“Which list: slug, exact title, or id.”
    • titlestring“New title.”
    • subtitlestring“New subtitle.”
    • categorystring“The category the person chose: Food & Drink, Travel, Books, Music, Movies & TV, Gear & Tools, Software, Fashion, Home & Garden, Ideas & Essays, Art, or Spiritu…”
  • archive_liston 1 other serverdeletesdescribed as changing data

    “Archive one of the person's lists: it leaves their profile, search and readers' view, and its page stops working.”

    Publisher declares: read-only no · destructive yes · idempotent yes · open-world no

    1 input, 1 required
    • liststringrequired“Which list: slug, exact title, or id.”
  • unarchive_listcreates or changes datadescribed as changing data

    “Bring an archived list back.”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world no

    1 input, 1 required
    • liststringrequired“Which archived list: slug, exact title, or id.”
  • delete_liston 8 other serversdeletesdescribed as changing data

    “Delete one of the person's lists for good.”

    Publisher declares: read-only no · destructive yes · idempotent no · open-world no

    2 inputs, 2 required
    • liststringrequired“Which list: slug, exact title, or id.”
    • confirmTitlestringrequired“The list's exact title, after the person confirms deleting it.”
  • add_itemon 5 other serverscreates or changes datadescribed as changing data

    “Capture one pick with the person's own note.”

    Publisher declares: read-only no · destructive no · idempotent no · open-world yes

    7 inputs
    • liststring“List slug or title.”
    • urlstring“The URL being captured, if any.”
    • titlestring“Short title for the pick (e.g.”
    • notestring“The curator's own note on why they like or recommend this pick.”
    • authorstring“Author or creator as the person gives it (books, articles, posts), e.g.”
    • create_if_missingboolean“When true and no list matches `list`, create that private list and save there.”
    • idempotency_keystring“Optional retry key.”
  • add_itemson 1 other servercreates or changes datadescribed as changing data

    “Add up to 50 picks to one list in a single call, in order.”

    Publisher declares: read-only no · destructive no · idempotent no · open-world yes

    3 inputs, 2 required
    • idempotency_keystring“Stable key for this reviewed batch.”
    • liststringrequired“Which list: exact slug, handle/slug, or id from a previous result.”
    • itemsarrayrequired“Up to 50 picks, added in the order given.”
  • import_from_urlon 1 other servercreates or changes datadescribed as changing data

    “Import picks into a list from one link: a Google Maps list shared with "Anyone with the link" (every place, in order, with the owner's notes; pasting it again adds only new places), a Google Maps pla…”

    Publisher declares: read-only no · destructive no · idempotent no · open-world yes

    2 inputs, 2 required
    • liststringrequired“Which list: exact slug, handle/slug, or id from a previous result.”
    • urlstringrequired“A Google Maps shared list or place link (maps.app.goo.gl works), Spotify playlist, YouTube playlist (a link with list=) or Letterboxd list URL.”
  • start_importcreates or changes datadescribed as changing data

    “Bring a whole list in to sort, privately.”

    Publisher declares: read-only no · destructive no · idempotent no · open-world yes

    8 inputs
    • urlstring“A Google Maps shared-list link (maps.app.goo.gl works).”
    • titlestring“The source list's own name, e.g.”
    • source_ownerstring“Whose list or account it is, when it is not the person's own, e.g.”
    • own_listboolean“True (default) when the source is the person's own: their notes become their notes.”
    • sortboolean“True when most entries are probably not recommendations (an account's posts, saved posts): everything arrives unsorted for the person to keep or skip.”
    • liststring“Optional destination list.”
    • picksarray
    • idempotency_keystring“Optional retry key.”
  • stage_pickscreates or changes datadescribed as changing data

    “Add up to 1,000 more picks to an import started with start_import, for sources longer than one call.”

    Publisher declares: read-only no · destructive no · idempotent no · open-world no

    3 inputs, 2 required
    • import_idstringrequired“The id start_import returned.”
    • picksarrayrequired
    • sortboolean“Same meaning as in start_import.”
Show 36 more tools
  • review_importon 1 other serverreads or searches

    “Read an import's entries with their ids and states (kept, skipped, unsorted), to show the person or to sort.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    3 inputs, 1 required
    • import_idstringrequired
    • statestring“Only entries in this state.”
    • offsetinteger
  • sort_importcreates or changes datadescribed as changing data

    “Keep or skip entries in an import, by id or all unsorted at once, as the person decides.”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world no

    4 inputs, 1 required
    • import_idstringrequired
    • keeparray“Entry ids to keep.”
    • skiparray“Entry ids to skip.”
    • reststring“Then keep or skip every entry still unsorted.”
  • commit_importon 2 other serverscreates or changes datadescribed as changing data

    “Add the kept entries of an import to a list, privately: the list given at start_import, another list of theirs, or a new private list.”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world no

    4 inputs, 1 required
    • import_idstringrequired
    • liststring“Destination, when start_import had none.”
    • new_list_titlestring“Title for a new list.”
    • connectboolean“Keep a Google Maps list connected (default true).”
  • list_sourceson 92 other serversreads or searches

    “Show what one of the person's lists is connected to: when it was last checked, what is new and waiting, and what is gone at the source.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    1 input, 1 required
    • liststringrequired“Which list: exact slug, handle/slug, or id from a previous result.”
  • check_sourceon 1 other servercreates or changes datadescribed as changing data

    “Read a connected list's source again now (up to 10 times a day per list).”

    Publisher declares: read-only no · destructive no · idempotent no · open-world yes

    2 inputs, 1 required
    • source_idstringrequired“A connection id from list_sources.”
    • policystring“Optionally change what happens to new entries first: wait to be sorted (ask) or be added privately (add_private).”
  • list_itemson 11 other serversreads or searches

    “Read every pick in one of your lists, in reader order, with item ids.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    1 input, 1 required
    • liststringrequired“Which list: exact slug, handle/slug, or id from a previous result.”
  • search_itemson 17 other serversreads or searches

    “Search the curator's own picks by title or URL.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    2 inputs, 1 required
    • querystringrequired“Search string.”
    • liststring“Optional list slug or title to scope the search.”
  • update_itemon 8 other serverscreates or changes datadescribed as changing data

    “Edit one pick's title, curator note, URL or author.”

    Publisher declares: read-only no · destructive yes · idempotent yes · open-world no

    5 inputs, 1 required
    • itemIdstringrequired“Item id from list_items or search_items.”
    • titlestring“New title.”
    • notestring“New curator note.”
    • urlstring“New URL.”
    • authorstring“Author or creator as the person gives it (books, articles, posts), e.g.”
  • remove_itemon 1 other serverdeletesdescribed as changing data

    “Remove one pick from a list.”

    Publisher declares: read-only no · destructive yes · idempotent yes · open-world no

    1 input, 1 required
    • itemIdstringrequired“Item id from list_items or search_items.”
  • removed_itemsreads or searches

    “List picks removed from one of the person's lists that have not been put back, newest first, with their notes and ids for restore_item.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    2 inputs, 1 required
    • liststringrequired“Which list: exact slug, handle/slug, or id from a previous result.”
    • cursorstring“nextCursor from the previous removed_items page; omit for the newest picks.”
  • restore_itemon 1 other servercreates or changes datadescribed as changing data

    “Put a removed pick back on its list where it was, with the same id, note, details, links and saves.”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world no

    1 input, 1 required
    • itemIdstringrequired“removedId from remove_item, or an id from removed_items.”
  • reorder_itemscreates or changes datadescribed as changing data

    “Put a list's picks in a new order.”

    Publisher declares: read-only no · destructive yes · idempotent yes · open-world no

    3 inputs, 3 required
    • liststringrequired“Which list: exact slug, handle/slug, or id from a previous result.”
    • orderarrayrequired“Every item id in the list, in the new order.”
    • revisionstringrequired“The `revision` list_items returned.”
  • move_itemson 1 other servercreates or changes datadescribed as changing data

    “Move picks from one of the person's lists to another, keeping each pick's note, details and history.”

    Publisher declares: read-only no · destructive yes · idempotent no · open-world no

    5 inputs, 4 required
    • fromstringrequired“The list the picks are in now.”
    • tostringrequired“The list to move them to.”
    • itemIdsarrayrequired“Item ids from list_items on the `from` list.”
    • revisionstringrequired“The `revision` list_items returned for the `from` list.”
    • toRevisionstring“Optional: the destination revision, to refuse the move if it changed too.”
  • review_itemsreads or searches

    “After adding or importing picks, fetch their enriched preview here.”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world yes

    1 input, 1 required
    • liststringrequired“Which list: exact slug, handle/slug, or id from a previous result.”
  • pick_review_statusreads or searches

    “Read whether an exact pick preview was already confirmed, is pending, or expired.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    1 input, 1 required
    • reviewIdstringrequired“reviewId from review_items.”
  • confirm_itemscreates or changes datadescribed as changing data

    “After the person approves the enriched preview from review_items, finish adding those exact picks.”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world yes

    1 input, 1 required
    • reviewIdstringrequired“reviewId from review_items.”
  • publish_listreads or searches

    “Prepare first publication or a list-wide update.”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world no

    1 input, 1 required
    • liststringrequired“Which list: exact slug, handle/slug, or id from a previous result.”
  • confirm_publicationcreates or changes datadescribed as changing data

    “Publish the exact list the owner reviewed, after they explicitly agree to that summary in this conversation.”

    Publisher declares: read-only no · destructive yes · idempotent yes · open-world yes

    2 inputs, 1 required
    • reviewIdstringrequired“review.reviewId from publish_list.”
    • handlestring“Only when the review showed an unconfirmed handle: the same handle, after the owner confirms it's theirs to show publicly.”
  • search_listsreads or searches

    “Search every live list on Curated, not just the person's own.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    3 inputs, 1 required
    • querystringrequired“What to look for, e.g.”
    • categorystring“Optional category slug to narrow results, e.g.”
    • limitnumber“Max results, 1 to 25.”
  • find_listsreads or searches

    “Search live Curated lists by topic, title, or curator handle.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    1 input, 1 required
    • querystringrequired“What the user is looking for.”
  • get_liston 17 other serversreads or searches

    “Read one list: every pick of a live list, or of one of the person's own.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    2 inputs, 1 required
    • liststringrequired“Which list: handle/slug, slug, title, or id.”
    • formatstring“How to render the reply text.”
  • get_list_itemsreads or searches

    “Read one list and report each pick's details status.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    2 inputs, 1 required
    • liststringrequired“Exact returned slug, handle/slug, title, or id.”
    • formatstring“How to render the reply text.”
  • save_liston 2 other serverscreates or changes datadescribed as changing data

    “Save a live list to Library under Saved lists, with its new picks.”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world no

    1 input, 1 required
    • liststringrequired“Exact list id or slug.”
  • saved_listsreads or searches

    “Read back Saved lists, matching the app.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    1 input
    • limitnumber
  • save_itemon 4 other serverscreates or changes datadescribed as changing data

    “Save one pick from a list you can read, yours or anyone's, to Library under Saved picks.”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world no

    2 inputs, 1 required
    • itemIdstringrequired“Item id from get_list_items, list_items or search_items.”
    • liststring“Optional list id, slug or handle/slug the pick came from; rejected if the pick is on a different list.”
  • unsave_itemdeletesdescribed as changing data

    “Remove one pick from Saved picks.”

    Publisher declares: read-only no · destructive yes · idempotent yes · open-world no

    1 input, 1 required
    • itemIdstringrequired“Item id from saved_items.”
  • saved_itemsreads or searches

    “Read back your saved picks across every list, newest first, matching Saved picks in the app.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    3 inputs
    • liststring“Optional list id, slug or handle/slug to show saves from one list.”
    • limitnumber
    • cursorstring“The cursor from a previous saved_items result, to read further.”
  • add_saved_itemcreates or changes datadescribed as changing data

    “Add a pick you can read, usually one from saved_items, to one of your own lists as a new pick.”

    Publisher declares: read-only no · destructive no · idempotent no · open-world yes

    3 inputs, 2 required
    • itemIdstringrequired“Item id from saved_items or get_list_items.”
    • liststringrequired“Your list slug or title.”
    • idempotency_keystring“Stable across retries so a lost response does not add the pick twice.”
  • “The lists this person saved, each bringing its new picks.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    1 input
    • limitnumber“Max lists, 1 to 200.”
  • search_libraryon 22 other servers

    “Search inside the lists this person has access to: "what was that ramen place from the Tokyo list?".”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    3 inputs, 1 required
    • querystringrequired“Search string, matched against pick titles, URLs, and descriptions.”
    • liststring“Optional: restrict to one list (handle/slug, slug, title, or id).”
    • limitnumber“Max picks, 1 to 50.”
  • library_updates

    “What's new in the lists this person has access to since a point in time.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    2 inputs
    • sincestring“ISO 8601 timestamp.”
    • limitnumber“Max new picks, 1 to 200.”
  • get_list_updates

    “Older name for save_list on a live free list: saves it to Library with its new picks.”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world no

    1 input, 1 required
    • liststringrequired
  • follow_curator

    “Explicitly follow or unfollow a curator by handle.”

    Publisher declares: read-only no · destructive yes · idempotent yes · open-world no

    2 inputs, 2 required
    • handlestringrequired
    • followingbooleanrequired
  • curator_notifications

    “Read a followed curator's email preference, or set `enabled` only on an explicit email request.”

    Publisher declares: read-only no · destructive yes · idempotent yes · open-world no

    2 inputs, 1 required
    • handlestringrequired
    • enabledboolean
  • list_notificationson 16 other servers

    “Read every notification setting when `push` and `email` are omitted.”

    Publisher declares: read-only no · destructive yes · idempotent yes · open-world no

    3 inputs
    • liststring“List id, slug or handle/slug; required when setting.”
    • pushboolean
    • emailboolean
  • unlock_list

    “Save a live free list with its new picks, only when the person asks.”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world yes

    1 input, 1 required
    • liststringrequired“Which list: handle/slug, slug, title, or id.”

Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-10-23.

How well are its tools described?

Features #4 and #5

How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.

Descriptions

AI reading of each description

Says what the tool does
100% of 40 tools
Says what it returns
39% of 36 tools
States limits, defaults or errors
13% of 40 tools
Says when to use it
18% of 38 tools
Items covered per tool
1.7 of 4 on average

Counted from the listing

Parameters with a description
86% of 109
Tools with a description
100% of 48
Typical description length
209 characters

The tool set

Counted from the listing

Tools
48
Size of the list
about 10,449 tokens for an agent to load (characters ÷ 4)
Naming
48 of 48 names use snake_case

AI reading: easy to mix up

No pair found.

The AI items cover 40 of 48 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none, comparing tools within groups of 40. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.

How do I add it to my client?

Config from the registry entry

From the remote endpoint (Streamable HTTP)

We connected to this URL on 2026-10-23 (a read-only session: no tool was called).

Add to CursorAn install link in the format Cursor documents, holding the Cursor config below.

Claude Desktop or claude.ai
Settings → Connectors → Add custom connector, then paste:
https://mcp.curated.network/
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
  "mcpServers": {
    "curated": {
      "url": "https://mcp.curated.network/"
    }
  }
}
VS Code · .vscode/mcp.json
{
  "servers": {
    "curated": {
      "type": "http",
      "url": "https://mcp.curated.network/"
    }
  }
}
VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"curated","type":"http","url":"https://mcp.curated.network/"}'
Claude Code
claude mcp add --transport http curated https://mcp.curated.network/
Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+
npx @modelcontextprotocol/inspector@2.11.0 --server-url https://mcp.curated.network/ --transport http
  • The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
  • The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.

Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.

Does the registry listing match what we found?

Feature #6

The registry verifies a package once, when it is published, and does not re-check it. A difference below is about the listing, not a judgement of the publisher.

Registry saysWe foundResultSource · date
Remote endpoint mcp.curated.network/Session openedmatchesour test · 2026-10-23
No credential declared as requiredOpened a session without any credentialmatchesour test · 2026-10-23

Choosing

Record checks

Public records · not a safety rating

1 of 2 record checks met · 7 do not apply

  • Not ranked by downloads: a remote server publishes no download figure
  • Not ranked by stars: no public GitHub repository
  • MetRegistry entry is active and says how to run itActive, with a package or a remote address.
  • Not metSource repository link opensThe registry entry gives no repository link.
  • Does not applyRepository is not archivedNo public GitHub repository to read.
  • Does not applyCode pushed to the repository in the 90 days before our checkNo public GitHub repository to read.
  • Does not applyRepository publishes a security policy (SECURITY.md)No public GitHub repository to read.
  • Does not applyPackage names its licence with a standard (SPDX) identifierRemote server: it ships no package.
  • Does not applyThe version the registry lists can be installed and is not withdrawnRemote server: it ships no package.
  • Does not applynpm package carries build provenance (attestation)Remote server: it ships no package.
  • Does not applyNo known critical or high advisory in the package or its dependenciesRemote server: it ships no package.

Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-10-23. No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating. How each check works · Leaderboards

Common questions about network.curated/curated

Answered from the data above

Is network.curated/curated safe to install?

We do not rate servers as safe or unsafe. 1 of its 2 applicable record checks are met (facts from public records, each listed on this page). What the records show: 24 of its tools describe changing data (our AI model's reading of the descriptions). These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.

Is network.curated/curated free to use?

Its website (curated.network/agent-setup/instructions) describes a free pricing model. This is an AI-classified reading of the page on 2026-10-23, so check the page itself before relying on it.

Does network.curated/curated need an API key or sign-in?

It opened a session without any credential on 2026-10-23. The registry entry declares no required credential; no declaration is not a guarantee.

Has network.curated/curated been security tested?

Partly. 5 of the 16 checks that apply to it were exercised. It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. No security verdict is published before verification.

What can network.curated/curated do?

It lists 48 tools. In our AI model's reading of their descriptions (two runs had to agree, nobody checked it by hand), they include tools that read or search, create or change data and delete. We did not call any tool, so this describes the text, not the behaviour.

Can network.curated/curated change or delete data?

24 of its tools say in their description that they create, edit, delete, send or run something (our AI model's reading). We did not call any tool, so we cannot say what actually happens.

Found this page useful?

Anonymous · no sign-in

A quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.

Similar servers

Same topic · AI-read

Active servers whose topic is also “productivity-and-docs” and that have at least one tool of the same kind; most kinds in common first, then most GitHub stars. The topic and the tool kinds are an AI model's reading of the publishers' descriptions, not checked by hand. Similar is not a recommendation.

Compare with another server

Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.

Security testing

What did we test, and what did we leave out?

18 checks · features #1, #2

Open without sign-in

It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. No security score is given; a check we did not run is never counted as passed.

The 18 checks at a glanceour test · 2026-10-23
  1. Inventory: exercised
  2. Hidden instructions: exercised
  3. Real execution: not run · our policy
  4. Secret leak: not run · nothing to check it against
  5. Internal addresses: not run · our policy
  6. Unconfirmed changes: not run · our policy
  7. Bad input: not run · our policy
  8. Model requests: not run · nothing to check it against
  9. Sensitive questions: not run · nothing to check it against
  10. Folder boundary: not run · our policy
  11. Log leaks: not run · nothing to check it against
  12. Hidden content: exercised
  13. Fake assistant turns: exercised
  14. Token passthrough: not applicable
  15. Token audience: not applicable
  16. Sign-in redirect: not run · our policy
  17. Consent handling: not testable from outside
  18. Sign-in metadata: exercised

5 exercised11 not run (reason given)2 not applicable

Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 5 of the 16 checks that apply to it were exercised. We do not publish security-check outcomes for named servers.

Exercised · 5
  • 1Inventory
    tool-list
    Reads the declared tools, resources and prompts.exercised
  • 2Hidden instructions
    description-poisoning
    Looks for hidden instructions in tool descriptions.exercised
  • 12Hidden content
    audience-hiding
    Checks resources that hide content from the user.exercised
  • 13Fake assistant turns
    fake-assistant-turn
    Checks prompts that pose as the assistant's own words.exercised
  • 18Sign-in metadata
    oauth-url-scheme
    Checks the published sign-in metadata for unsafe URLs.exercised
Not run, with the reason · 11
  • 3Real execution
    real-execution
    Calls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
  • 4Secret leak
    canary-leak
    Plants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 5Internal addresses
    ssrf
    Checks whether a tool can be steered to internal addresses.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
  • 6Unconfirmed changes
    write-without-confirmation
    Checks whether tools that change data act without asking.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
  • 7Bad input
    error-handling
    Sends bad input and watches how the server answers.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
  • 8Model requests
    sampling
    Checks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 9Sensitive questions
    elicitation-sensitive-data
    Checks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 10Folder boundary
    root-boundary
    Checks whether the server reaches outside the folders it was given.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
  • 11Log leaks
    logging-side-channel
    Checks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 16Sign-in redirect
    open-redirect
    Checks the sign-in redirect for abuse.Testing the sign-in redirect means sending probes to the operator's sign-in service, which we do not do.not run · our policy
  • 17Consent handling
    confused-deputy
    Checks consent handling when one service acts for another.Depends on the operator's own consent screen, which differs per server and cannot be tested from outside.not testable from outside
Does not apply to this server · 2
  • 14Token passthrough
    token-passthrough
    Checks whether the server forwards a user's token to other services.The server opened a session without sign-in, so there is no token flow to check.not applicable
  • 15Token audience
    token-audience-validation
    Checks whether tokens meant for another service are accepted.The server opened a session without sign-in, so there is no token flow to check.not applicable

Source: our own test, 2026-10-23, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.

What happened during the test?

Feature #8

The steps in order, as the test record holds them.

  1. 0 msStarted a read-only session with the server's remote endpoint
  2. 990 msConnected after 0 redirects. No credential was sent or needed.
  3. Read the inventory: 48 tools, 1 resource, 3 prompts.
  4. 5,585 msFinished: 5 checks exercised.

Reference

How is it classified?

18 fields

One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.

TopicAI-classified
AI-classified (Gemini + Claude agreed) · 2026-10-23
Pricing modelAI-classified
free
read from curated.network/agent-setup/instructions · 2026-10-23

“Every list on Curated is free to read today.”

Programming language
does not apply
no existing GitHub repository (server declares no repository link, so there is nothing to fetch)
Hosting type
registry · 2026-10-23
MCP capability
prompts, resources, tools
our test · 2026-10-23
Transport
streamable HTTP
registry · 2026-10-23
Required credentials
none declared
registry · no declaration is not a guarantee
Package registry
does not apply
remote-only server: no package is shipped, so there is no package registry
Freshness
0–30 days
registry updatedAt · 2026-10-23
Lifecycle status
registry · 2026-10-23
License class
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Integrity hash
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Signature / provenance
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Dependency advisories
does not apply
ships no package, so there are no dependencies to audit
Popularity
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Publisher signals
not stated
no readable GitHub owner to describe
Maintenance
does not apply
server declares no repository link, so there is nothing to fetch
Environment
the publisher's infrastructure
where it runs, from the hosting type

“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.

Cite or correct this page

Sources and corrections

Suggested citation

ProtocolProbe. “network.curated/curated: MCP server record.” Data checked 2026-10-23. https://protocolprobe.com/mcp/servers/network.curated/curated

Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.

As JSON: this record in the API · API documentation.

Badge for your README

ProtocolProbe: 1 of 2 record checks met

[![ProtocolProbe](https://protocolprobe.com/api/v1/badge/network.curated/curated)](https://protocolprobe.com/mcp/servers/network.curated/curated)

It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.

Something wrong, or is this yours?

If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here.

Write to hello@protocolprobe.com · corrections log · methodology