ArchiveBox API

Create snapshot

archivebox_create_snapshot

Queue a URL for archiving by creating a snapshot, with optional crawl attachment, depth, title, tags, and initial status.

Instructions

POST /api/v1/core/snapshots

Create one snapshot for a URL (queued for archiving).

Args: url: The URL to snapshot. crawl_id: Attach the snapshot to an existing crawl. depth: Crawl depth of this snapshot. title: Initial title. tags: Tag names to apply. status: Initial status (default queued).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "url": "<url>"
    },
    "name": "archivebox_create_snapshot"
  }
}

Input Schema

Name	Required	Description	Default
`url`	Yes
`tags`	No
`depth`	No
`title`	No
`status`	No
`crawl_id`	No

Schema Changelog

Changes observed during successful MCP inspections.

Addedv2.6.0Nov 7, 2026

TDQS

B3.3/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=false, idempotentHint=false, openWorldHint=true and destructiveHint=false, so the write/non-destructive/non-idempotent profile is covered. The description adds genuine value with 'queued for archiving' and the default status 'queued', telling the agent the call returns before archiving completes. It says nothing about auth requirements, rate limits, or what happens on duplicate URL submission, which matters for a non-idempotent create.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose is front-loaded in the first sentence and the parameter list is compact with no filler. The leading 'POST /api/v1/core/snapshots' line and the 'Args:' boilerplate are HTTP-handler artifacts that add little for an agent, but they are brief.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a non-idempotent creation endpoint with six parameters and no output schema, the definition should say what comes back (presumably a snapshot identifier the agent needs for follow-up calls like archivebox_get_snapshot) and whether the URL is validated. The parameter list and 'queued' hint cover the essentials but leave the post-call workflow to guesswork.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the full burden, and it does list all six parameters with short semantics — notably 'crawl_id: Attach the snapshot to an existing crawl' and 'depth: Crawl depth', which add meaning beyond bare types. It is terse (e.g., no valid values for 'status', no explanation of how depth interacts with crawl_id), so it compensates but not completely.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a concrete verb and resource ('Create one snapshot for a URL') and adds the important qualifier that it is 'queued for archiving', which tells the agent this is an enqueue rather than a synchronous fetch. It does not differentiate from close siblings such as archivebox_cli_add or archivebox_ingest_snapshots, which likely also accept a URL, so the agent cannot disambiguate on purpose alone.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance, no conditions that select this over archivebox_cli_add or web_extract, and no prerequisites mentioned (the sibling set includes archivebox_check_api_token, implying auth matters). The only usage signal is implicit in the word 'queued'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server