ArchiveBox API

Create crawl

archivebox_create_crawl

Queue a crawl over seed URLs with depth, tags, label, notes, and config overrides so the orchestrator snapshots linked pages.

Instructions

POST /api/v1/crawls/crawls

Create a crawl over seed URLs (queued; the orchestrator snapshots them).

Args: urls: Seed URLs. max_depth: Outlink depth to follow. tags: Tag names for the crawl's snapshots. tags_str: Comma-separated tag names (alternative to tags). label: Human label for the crawl. notes: Free-text notes (for example why it was captured). config: Per-crawl config overrides (for example plugin toggles).

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": {
      "urls": "<urls>"
    },
    "name": "archivebox_create_crawl"
  }
}

Input Schema

Name	Required	Description	Default
`tags`	No
`urls`	Yes
`label`	No
`notes`	No
`config`	No
`tags_str`	No
`max_depth`	No

Schema Changelog

Changes observed during successful MCP inspections.

Addedv2.6.0Nov 7, 2026

TDQS

A3.5/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=false and destructiveHint=false, so the mutation/network profile is covered by structured data. The description adds one genuinely useful behavioral fact - the crawl is queued and the orchestrator performs the snapshots - but says nothing about what is returned (presumably a crawl ID), whether re-posting the same URLs creates duplicates (non-idempotent per annotations), or what permissions/token are needed.

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?

Front-loaded with the operation, then a structured per-argument list that is easy to scan. The raw 'POST /api/v1/crawls/crawls' endpoint line adds little for an agent choosing a tool but is a single short line, so the waste is minor.

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 7-parameter mutation tool with no output schema and zero schema coverage, the description does the essential work of naming every parameter and disclosing the async queueing model. It falls short on the operational context an agent needs to call it safely: no return value, no auth requirement, no duplicate-handling guidance.

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 entire burden - and it does document all seven parameters with a short gloss each (urls, max_depth, tags, tags_str, label, notes, config). Gaps remain: max_depth's default of 0 is not explained (unlimited vs no outlink following), and no precedence rule is given for tags vs. tags_str, which overlap.

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?

States a specific verb and resource: 'Create a crawl over seed URLs'. The parenthetical '(queued; the orchestrator snapshots them)' clarifies what a crawl actually does, which is genuinely informative. It does not, however, explicitly distinguish itself from the sibling archivebox_create_snapshot, which is the closest alternative and the one most likely to be confused with it.

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

Usage Guidelines3/5

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

Usage is only implied: the queued/orchestrator note hints that this is an asynchronous kickoff rather than an immediate fetch, and the 'notes' example ('why it was captured') hints at archival intent. There is no statement of when to prefer this over archivebox_create_snapshot or archivebox_cli_add, and no prerequisites or auth requirements are named.

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

Deploy Server