Skip to main content
Glama
Cutover MCP

Cutover MCP

Official
by gocutover

Get Data Source Upload Url

get_data_source_upload_url

Generates a short-lived pre-signed URL for uploading a file that a Cutover data source reads, such as a CMDB export. Upload the raw file to the returned URL before it expires.

Instructions

Get a short-lived, pre-signed URL for uploading a file that a data source reads from, such as a CMDB export in JSON or CSV.

This server cannot read files on your machine, so upload the file yourself, straight away: send an HTTP PUT with the raw file as the body to the returned url before it expires (expires_in seconds). For example:

curl --fail -X PUT --upload-file ./cmdb.csv "<url>"

Keep the url in double quotes, because it contains & characters the shell would otherwise split on. Keep --fail, so a rejected upload exits with an error instead of looking like a success. If the upload fails or the url has expired, call this tool again for a new url rather than reusing the old one.

For a new data source, create it with datasource_endpoint_url as its url. The file is scanned for malware after upload, so test the data source can read it before importing.

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": {
      "file_name": "<file_name>"
    },
    "name": "get_data_source_upload_url"
  }
}

Input Schema

NameRequiredDescriptionDefault
file_nameYesName of the file to upload, e.g. "cmdb.csv". Used to build the storage key.
data_source_idNoOmit for the first upload, before the data source exists. To upload a new version of the file behind an existing data source, pass that data source's ID. The new file only replaces the old one if the returned datasource_endpoint_url is the data source's current url; if it differs, the data source will not read this upload until its url is changed to the returned one. After uploading, refresh and sync the data source to pick up the changes.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

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

With no annotations supplied, the description carries the full burden and does so well: it discloses the short-lived expiry, that the server cannot access local files, that malware scanning happens after upload, and that a rejected upload must surface as an error (--fail) rather than a false success. These are exactly the non-obvious traits an agent could otherwise get wrong.

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 and the time-critical instruction are front-loaded, and each later sentence adds operational value (curl invocation, shell quoting, --fail, retry). It is somewhat long and the shell-quoting aside is narrower than a general agent needs, keeping it just below a 5.

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

Completeness5/5

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

An output schema exists, so return values need not be enumerated, and the description still references the key returned fields (url, expires_in, datasource_endpoint_url). Combined with the upload workflow and post-upload verification note, nothing essential for correct invocation is missing.

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% and both parameters are already documented in detail, including the nuanced data_source_id semantics. The description adds only a light framing ('omit for the first upload' implicitly via its new-data-source guidance) and largely defers to the schema, so baseline 3 is correct.

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?

The opening sentence names a specific verb and resource ('Get a short-lived, pre-signed URL') and states exactly what the URL is for ('uploading a file that a data source reads from'), including the concrete example of a CMDB export in JSON or CSV. It is unmistakably distinct from the sibling read/list tools.

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?

The description tells the agent precisely how and when to act: upload the file yourself, immediately, via HTTP PUT before `expires_in` elapses. It also covers the failure branch ('If the upload fails or the url has expired, call this tool again for a new url rather than reusing the old one') and the ordering constraint for new data sources.

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