Playbook

Upload from URL

upload_from_url

Upload a single asset to a Playbook board by giving Playbook a public URL to fetch. Returns immediately with a skeleton asset; the byte fetch runs asynchronously in the background. Requires a token with the write scope. Playbook fetches the URL itself, anonymously — a link behind a login or a signed URL that has expired will not work here, and neither will a file that exists only on someone's machine. For those, use share_board with enable_uploads. It returns a link a person can drop files on without signing in, and whatever they add lands on that board for you to collect with list_assets. It needs a live human and it shows the board's existing contents to anyone holding the link, so reach for it only once no fetchable URL is available. The fetch runs to a time budget (five minutes of streaming), so a source that is very large or very slow fails with "Source URL too large to fetch; upload manually" — when that happens, send the bytes yourself with create_upload_url rather than retrying. Tip: validate collection_token with get_board first — an unknown token silently falls back to an anonymous default board.

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": {
      "uri": "<uri>"
    },
    "name": "upload_from_url"
  }
}

Input Schema

Name	Required	Description
`uri`	Yes	Public URL of the file to ingest
`tags`	No	Manual tags to apply
`title`	No	Override the title. Defaults to the filename in the URL. Not derived when as_link is true — Playbook titles those from the linked page's own metadata.
`status`	No	Status label to set
`as_link`	No	If true, store as a bare link instead of fetching bytes (default false)
`description`	No	Optional description
`ai_generated`	No	Mark the asset as produced by an AI tool. Set it at creation rather than by a later update. Through these tools it is a marker and nothing else; on Playbook's REST presigned-upload endpoints the same flag additionally suppresses automatic duplicate merging and grouping.
`organization`	No	Workspace slug, as returned by list_organizations. Omit it when the account has a single workspace — it is then resolved from your token. Pass it only when the account has several, or when you mean a workspace other than the obvious one.
`ai_agent_payload`	No	Free-form JSON metadata stored with the asset — for example generation settings such as model and seed, or a source job id. Playbook never interprets it. Max 4096 BYTES of serialised JSON; anything larger is REJECTED, never truncated. A write REPLACES the whole object. Readable per asset (get_asset, or list/search with get_ai_payload=true) but NOT searchable or filterable.
`collection_token`	No	Destination board token. If omitted or unknown, Playbook silently routes to a default anonymous board — call get_board first to validate.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 3, 2026
- removedInput schema / additionalProperties
```
Removed value: -false
```
- addedInput schema / properties / ai_agent_payload / propertyNames
```
Added value: +{
+  "type": "string"
+}
```

Changed4 schema fields changedOct 5, 2026

addedInput schema / additionalProperties
```
Added value: +false
```

changedInput schema / properties / ai_agent_payload / description

Previous value: -"Your own scratch space on this asset — prompt, model, seed, source job id, anything you need to recognise it in a later session. Playbook never interprets it. Max 4096 BYTES of serialised JSON; anything larger is REJECTED, never truncated. A write REPLACES the whole object. Readable per asset (get_asset, or list/search with get_ai_payload=true) but NOT searchable or filterable."New value: +"Free-form JSON metadata stored with the asset — for example generation settings such as model and seed, or a source job id. Playbook never interprets it. Max 4096 BYTES of serialised JSON; anything larger is REJECTED, never truncated. A write REPLACES the whole object. Readable per asset (get_asset, or list/search with get_ai_payload=true) but NOT searchable or filterable."

removedInput schema / properties / context

Removed value: -{
-  "description": "Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): \"Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization.\"",
-  "type": "string"
-}

changedInput schema / required

Previous value: -[
-  "uri",
-  "context"
-]New value: +[
+  "uri"
+]

First observedOct 2, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Annotations already mark this as a non-read-only, open-world, non-idempotent call, but the description adds far more: it returns immediately with a skeleton asset while the byte fetch runs asynchronously, requires a token with `write` scope, fetches anonymously, and enforces a five-minute streaming budget with the exact error string returned. It also warns that an unknown `collection_token` silently falls back to an anonymous board — a failure mode no annotation could convey.

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 core action, async behavior, and auth, then alternatives, then failure handling, then a tip — a sensible priority order. The `share_board` digression runs several sentences and could be tightened, but every part is actionable rather than filler.

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

Completeness4/5

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

Covers the hard parts an agent needs for a 10-parameter, no-output-schema mutation: async return shape, auth scope, fetch constraints, timeout error, and correct fallbacks. The one real gap is how to confirm the background fetch actually succeeded (poll `get_asset`? watch for a status?), which the description never says.

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

Parameters3/5

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

Schema coverage is 100%, including the `collection_token` silent-fallback note and the `as_link`/`title` interaction, so the description's 'validate collection_token with get_board first' tip largely restates the schema. It adds emphasis and a cross-tool step but no genuinely new parameter semantics, so the baseline of 3 applies.

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

Purpose5/5

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

States a specific verb and resource ('Upload a single asset to a Playbook board by giving Playbook a public URL to fetch') and immediately distinguishes itself from the plural `upload_from_urls`, from `create_upload_url` (manual bytes), and from `share_board` (human-mediated uploads). The word 'single' and 'Playbook fetches the URL itself' make the boundary unmistakable.

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

Usage Guidelines5/5

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

Gives explicit when-to-use and when-not-to-use conditions: not for login-gated links, expired signed URLs, or local files; for those, `share_board` with `enable_uploads`, and even that is framed as a last resort because it needs a live human and exposes board contents. On timeout it names the correct fallback (`create_upload_url`) and explicitly says not to retry.

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

All Playbook tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?