# io.github.Piccolo123/url-manager-mcp (pypi · url-manager-mcp)

Agent-first bookmark management with auto-registration, categories, tags, and shared collections.

- Trust score: 64/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-20

## Components

- pypi · `url-manager-mcp`: 64/100 (this document), [markdown](https://verifymcp.io/servers/piccolo123-url-manager-mcp/url-manager-mcp.md), [page](https://verifymcp.io/servers/piccolo123-url-manager-mcp/url-manager-mcp)

## Channel facts

- Registry: `pypi`
- Package: `url-manager-mcp`
- Version: `1.0.2`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-20.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it.
  - 1 of 30 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 5 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 68/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2263 tokens (~107/item across 21 items; 21 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 67/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### Claude

```bash
claude mcp add piccolo123-url-manager-mcp -- uvx url-manager-mcp
```

### Codex

```bash
codex mcp add piccolo123-url-manager-mcp -- uvx url-manager-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "piccolo123-url-manager-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "url-manager-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add piccolo123-url-manager-mcp --command uvx --arg url-manager-mcp
```

### Hermes

```yaml
mcp_servers:
  piccolo123-url-manager-mcp:
    command: "uvx"
    args: ["url-manager-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "piccolo123-url-manager-mcp": {
      "command": "uvx",
      "args": [
        "url-manager-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-15 (score 64, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-08-14 (score 49)

First indexed and scored.

## MCP tools (21)

### `agent_register` (~88 tokens)

Create a new URL Manager account. Use when the user has no existing account
and no token is configured — the default path for first-time users.

No parameters. Token is auto-memorized for all subsequent calls.
⚠️ NEVER call this more than once! Each call creates a fresh empty account.
When in doubt, call my_info() first to check if a token is already active.

### `my_info` (~47 tokens)

Verify token validity and confirm connection. Use at the start of every
conversation, or when the user asks "Who am I?" / "What account is this?"

Returns username and membership status.

### `search_footprints` (~85 tokens)

Full-text search across titles, descriptions, and URLs.
Use when the user says "find that article about Docker" or "search for...".

Args:
    query: Search keywords
    limit: Results per page (max 100)
    offset: Pagination offset

Input parameters:

- `limit` (integer)
- `offset` (integer)
- `query` (string, required)

### `list_footprints` (~98 tokens)

List bookmarks by category. Use when the user says "show me my bookmarks",
"what have I saved?", or "list everything in this category".

Args:
    category_id: Category ID (0=all, get IDs from list_categories)
    limit: Results per page (max 100)
    offset: Pagination offset

Input parameters:

- `category_id` (integer)
- `limit` (integer)
- `offset` (integer)

### `get_footprint` (~72 tokens)

Get full details of a single bookmark. Use when the user says
"show me the details of that bookmark" or before updating to see
existing categories.

Args:
    footprint_id: Bookmark ID (from list_footprints or search results, field "id")

Input parameters:

- `footprint_id` (integer, required)

### `add_footprint` (~166 tokens)

Add a new bookmark. Use when the user says "save/bookmark/collect this link".

Call list_categories() and list_tags() FIRST to discover existing categories
and tags — avoid creating duplicates. If title is empty, it will be auto-extracted.

Args:
    url: Web page URL (required)
    title: Custom title (leave empty for auto-extraction)
    description: Summary/notes
    category_ids: Comma-separated category IDs, e.g. "1,3"
    tag_names: Comma-separated tag names, e.g. "AI,tutorial"

Input parameters:

- `category_ids` (string)
- `description` (string)
- `tag_names` (string)
- `title` (string)
- `url` (string, required)

### `update_footprint` (~168 tokens)

Update a bookmark. Use when the user says "change the title",
"move to another category", or "add a description".

⚠️ category_ids REPLACES the entire category list — NOT append!
Correct approach: get_footprint(id) → see current categories → merge in new IDs.
Example: existing [3,5], want to add 7 → category_ids="3,5,7" (NOT just "7")

Args:
    footprint_id: Bookmark ID (from search or list results)
    title/description/category_ids/tag_names: Leave empty to keep unchanged

Input parameters:

- `category_ids` (string)
- `description` (string)
- `footprint_id` (integer, required)
- `tag_names` (string)
- `title` (string)

### `list_categories` (~84 tokens)

List all categories (personal + shared). Use at the start of any bookmark
operation to discover available categories and their IDs.

Returns each category with id, name, and mode fields.
mode=null → personal category. mode="cocreate"/"subscribe" → shared category.
Use the 'id' field in add_footprint / update_footprint category_ids parameter.

### `create_category` (~80 tokens)

Create a new category. Use when the user says "create a new category called..."
or when organizing bookmarks into a new group.

Call list_categories() first to avoid duplicates.

Args:
    name: Category name
    category_set_id: Parent category set (0=default)

Input parameters:

- `category_set_id` (integer)
- `name` (string, required)

### `list_tags` (~24 tokens)

List all tags. Use before tagging bookmarks to see existing tags and avoid duplicates.

### `list_content_types` (~67 tokens)

List all content types the user has used. Use before adding bookmarks
to pick a content_type consistent with the user's existing library.

Returns each type with a usage count, ordered most-used first.
Common values: article, video, image, audio, page — but any string is valid.

### `list_category_sets` (~35 tokens)

List all category sets. Use when the user asks about their organizational
structure or needs to create a category in a specific set.

### `create_category_set` (~52 tokens)

Create a new category set (a container of categories). Use when the user
says "create a new workspace/set for...".

Args:
    name: Category set name

Input parameters:

- `name` (string, required)

### `create_shared_category` (~145 tokens)

Create a shared category for team collaboration. Use when the user says
"create a shared collection" or "let's share a folder with my team".

⚠️ In subscribe mode, only the owner can add bookmarks — members get 403 from
add_to_shared_category. Use mode="cocreate" for full team editing.

Args:
    name: Category name (required)
    mode: "cocreate" (multiple editors) or "subscribe" (read-only). Default: "cocreate"
    description: Optional description for the shared category

Input parameters:

- `description` (string)
- `mode` (string)
- `name` (string, required)

### `join_shared_category` (~56 tokens)

Join a shared category by invite code. Use when the user says
"I have an invite code" or "join this shared collection".

Args:
    invite_code: 8-character invite code

Input parameters:

- `invite_code` (string, required)

### `create_invite_link` (~97 tokens)

Generate an invite link for others to join. Use when the user says
"send the invite link to my team" or "invite someone to this shared category".

Args:
    shared_category_id: Shared category ID (from list_categories — pick ones where mode is not null)
    duration_hours: Link validity in hours (default: 24)

Input parameters:

- `duration_hours` (integer)
- `shared_category_id` (integer, required)

### `add_to_shared_category` (~114 tokens)

Add one of your existing bookmarks to a shared category. Use when the user
says "add this to the team collection" or wants to contribute to a shared folder.

The bookmark must belong to you. In subscribe mode, only the owner can add;
members get 403. In cocreate mode, all members can add.

Args:
    shared_category_id: Shared category ID
    footprint_id: Bookmark ID to add

Input parameters:

- `footprint_id` (integer, required)
- `shared_category_id` (integer, required)

### `remove_from_shared_category` (~77 tokens)

Remove a bookmark from a shared category. Use when the user says
"take this out of the shared collection". Does not delete the bookmark itself.

Args:
    shared_category_id: Shared category ID
    footprint_id: Bookmark ID to remove

Input parameters:

- `footprint_id` (integer, required)
- `shared_category_id` (integer, required)

### `copy_footprint` (~93 tokens)

Copy a bookmark from a shared category into your personal collection.
Use when the user says "save this shared bookmark to my own collection"
or "add that to my personal list".

Args:
    footprint_id: Bookmark ID to copy
    category_ids: Target personal category IDs, comma-separated, e.g. "1,3"

Input parameters:

- `category_ids` (string, required)
- `footprint_id` (integer, required)

### `batch_update_footprints` (~145 tokens)

Batch update up to 50 bookmarks at once. Use when the user says
"reorganize all my bookmarks" or for bulk categorization / renaming.

⚠️ updates must be a valid JSON array. Malformed JSON or > 50 items returns an error.
category_ids still REPLACES (not appends) — verify existing categories with get_footprint() first.

Args:
    updates: JSON string, format '[{"id":"uuid","title":"New Title","category_ids":"1,3"}, ...]'
             Each object requires "id". Optional: title, description, category_ids, tag_names

Input parameters:

- `updates` (string, required)

### `agent_magic_link` (~79 tokens)

Generate a delivery link to the user. Use after organizing bookmarks —
this is the Agent-first delivery loop core.

Call this as the final step, then send the link to the user:
"Done organizing — view here → [link]"
User opens it to see a card-based interface with all organized bookmarks.
Link valid for 30 days, reusable.

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/piccolo123-url-manager-mcp/url-manager-mcp#diagnostics

## Score history

- 2026-08-20: 64
- 2026-08-19: 64
- 2026-08-18: 64
- 2026-08-17: 64
- 2026-08-16: 64
- 2026-08-15: 64
- 2026-08-14: 49

## Links

- PyPI project: https://pypi.org/project/url-manager-mcp/
- Socket report: https://socket.dev/pypi/package/url-manager-mcp
- Repository: https://github.com/Piccolo123/url-manager-mcp
- Changelog RSS feed: https://verifymcp.io/servers/piccolo123-url-manager-mcp/url-manager-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/piccolo123-url-manager-mcp/url-manager-mcp.json
- HTML version of this page: https://verifymcp.io/servers/piccolo123-url-manager-mcp/url-manager-mcp