Skip to main content
Glama

Team temporary file transfer

kloudy_team_files
Destructive

Temporary owner-listed test route: use handle tensorverse/theo, tensorverse/xavier, tensorverse/grok or tensorverse/botbar only while the server enables that isolated test. The owner approves this roster, but these declared labels are not authenticated accounts or trusted-device identities; this test does not prove trusted-handle enforcement. Existing authenticated account connections remain separate. Send ZIPs or any original file to enrolled members of your own team. Any enrolled bot may initiate. prepare -> signed HTTP PUT (or upload_part per original part) using your own file/network tools -> complete -> recipient get/download/hash -> ack. All intended recipients acknowledging triggers temporary object deletion. MCP carries metadata only; never send model-written base64. S3 maximum 53687091200000 bytes; actual provider/tool limits still apply and have not been proven at that size. Multipart starts at 100 MiB, up to 10000 parts, each 5 MiB–5 GiB except last. Multipart S3 checksum is composite, not full-file SHA. Temporary URLs expire; get/prepare can renew within retention. Receipt does not prove content read. QVault vetting is separate.

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": {
      "operation": "<operation>"
    },
    "name": "kloudy_team_files"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNo
nameNo
handleNoOwner-listed temporary test handle, e.g. tensorverse/theo. Owner-approved roster with unverified transport identity, not account authentication. Use handle OR connection, not both.
sha256No
file_idNo
byte_sizeNo
mime_typeNo
operationYes
connectionNoExisting private owner-enrolled bot connection; omit when client supplies x-kloudy-team-connection. Never forward it to another bot. Use connection OR temporary test handle, not both.
part_bytesNo
part_numberNo
part_sha256No

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.8/5.0
Behavior5/5

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

Annotations already flag destructiveHint=true and openWorldHint=true, and the description goes well beyond them: ack by all recipients triggers temporary object deletion, temporary URLs expire and can be renewed within retention, MCP carries metadata only (never base64), and a receipt does not prove content was read. It also discloses concrete limits (S3 max 53687091200000 bytes, multipart from 100 MiB, up to 10000 parts of 5 MiB–5 GiB except the last) and the important caveat that multipart S3 checksum is composite rather than full-file SHA.

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

Conciseness3/5

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

Nearly every clause carries real information, so length is defensible for an eight-operation multipart workflow. But it is delivered as a semicolon-chained block with the least actionable content (test-route disclaimers about trusted-handle enforcement) front-loaded ahead of the actual purpose and the operation sequence.

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?

For a 12-parameter, eight-operation transfer tool with no output schema, the description covers the full round trip, deletion semantics, size/part constraints, and checksum caveats, which is close to what an agent needs to call it correctly. The remaining gap is per-operation behavior (what list returns, cancel vs cleanup), which is not addressed anywhere.

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 only 17% (just handle and connection), so the description must compensate. It partially does: byte_size max, part size/count bounds, and handle-vs-connection exclusivity are stated in prose. But half the parameters (to, name, sha256, file_id, mime_type, and most of the eight operation enum values such as list, cancel, cleanup) get no explanation in either the schema or the description.

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 eventually states a concrete verb and resource: 'Send ZIPs or any original file to enrolled members of your own team', with an explicit lifecycle (prepare -> PUT -> complete -> get -> ack). However, it opens with 'Temporary owner-listed test route', which is a caveat rather than the purpose, and it never distinguishes itself by name from kloudy_team, so the agent must read several sentences before learning what the tool actually does.

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 context is implied by 'Send ... to enrolled members of your own team' and 'Any enrolled bot may initiate', plus the handle-vs-connection exclusivity rule. But there is no explicit when-to-use/when-not guidance and no pointer to an alternative (e.g. kloudy_team) for non-file team operations, leaving routing to inference.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources