Skip to main content
Glama
Pandafile MCP Server

Pandafile MCP Server

Official
by pandafileco

Send files from URLs

send_from_urls

Create a Pandafile transfer from public HTTPS URLs without uploading files locally; it downloads them, returns a ready link, or provides an import ID to track large downloads.

Instructions

Create a Pandafile transfer from files at public https URLs: Pandafile downloads them itself (no local upload). Waits up to ~20 seconds. status "ready": the link works now. status "uploading": big files are still downloading – call get_import_status with the id until it is "ready" (or "failed"). Recipients are emailed when it is ready.

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": {
      "files": "<files>"
    },
    "name": "send_from_urls"
  }
}

Input Schema

NameRequiredDescriptionDefault
filesYes1–20 files.
titleNoTitle (up to 120 characters).
messageNoMessage to the recipients (up to 1000 characters).
passwordNoDownload password (8–200 characters). Recipients need it to download. Plus/Pro/Team only.
expires_atNoExact expiry as ISO 8601 (e.g. "2026-12-31T23:00:00Z"). Alternative to expires_in_days; same limits.
recipientsNoEmail addresses to send the link to once the transfer is ready.
expires_in_daysNoKeep the files this many days from now (1–90). Pro/Team only, at most 90 days after sending; not for test keys. Leave out for the plan default.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare the write, non-idempotent, open-world profile, so the description's job is context, and it delivers: server-side download, a ~20 second wait cap, the two possible statuses, the polling loop, and that recipients are emailed on readiness. It does not warn that repeated identical calls will create duplicate transfers (consistent with idempotentHint=false), which would be the last useful detail.

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

Conciseness5/5

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

Front-loaded with the core action and the key distinguishing constraint, then the status-handling flow. Every clause carries information — the wait cap, the status values, the polling instruction, and the email trigger — with no 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?

With no output schema, the description does the work of explaining the asynchronous status semantics and continuation path, which is the main risk for this tool. It leaves the shape of the creation response (id, link, status fields) implicit, though the get_import_status reference implies an id is returned.

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 description coverage is 100%, so the baseline is 3; every parameter including password tier restrictions and expiry alternatives is documented in the schema. The description adds no field-level meaning beyond clarifying that recipients get emailed once the transfer is ready, which is behavioral rather than parametric.

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 ("Create a Pandafile transfer from files at public https URLs") and immediately scopes it against the local-upload path ("Pandafile downloads them itself (no local upload)"), which is what separates it from send_files. An agent can choose between them without opening either schema.

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

Usage Guidelines4/5

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

Gives clear conditions for use — public https URLs, no local upload — and explicitly routes the agent to get_import_status with the id when status is "uploading". It does not explicitly name the sibling to use for local files, but the negative scoping ("no local upload") conveys the exclusion.

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