Skip to main content
Glama

Search Sirv Files

sirv_cdn_search_files
Read-onlyIdempotent

Search files in your connected Sirv account by name, folder, tag, or extension using Sirv search syntax. Returns matching file paths and details with paging and sorting options.

Instructions

Search the files in the Sirv account connected to the workspace, with Sirv search syntax in query, such as basename:boot or a folder or tag name.

Use it to find a Sirv file path. Do not use it for Studio library assets: use sirv_list_assets. To list one folder, use sirv_cdn_manage_folder.

Inputs: query is required. sort_field and sort_order work only together. Page with from (default 0) and size (default 100).

Read-only. Returns the matching files with their paths and details.

Credits: free.

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": {
      "query": "<query>"
    },
    "name": "sirv_cdn_search_files"
  }
}

Input Schema

NameRequiredDescriptionDefault
fromNoNumber of results to skip, for the next page, 0 to 1000. Default: 0
sizeNoResults per page, 1 to 100. Default: 100
orgIdNoWorkspace id from sirv_list_organizations. Default: the workspace you signed in to
queryYesSirv search query, such as a file name, a folder, a tag or an extension
sort_fieldNoField to sort by. Needs sort_order. Default: Sirv's relevance order
sort_orderNoSort direction. Needs sort_field

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changedv0.1.1
    • changedInput schema / properties / from / description
      Previous value: -"Pagination offset"New value: +"Number of results to skip, for the next page, 0 to 1000. Default: 0"
    • changedInput schema / properties / orgId / description
      Previous value: -"Organization ID (uses default org if omitted)"New value: +"Workspace id from sirv_list_organizations. Default: the workspace you signed in to"
    • addedInput schema / properties / orgId / pattern
      Added value: +"^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
    • changedInput schema / properties / query / description
      Previous value: -"Sirv search query, such as a filename, folder, tag, or extension query"New value: +"Sirv search query, such as a file name, a folder, a tag or an extension"
    • changedInput schema / properties / size / description
      Previous value: -"Number of results (default 100)"New value: +"Results per page, 1 to 100. Default: 100"
    • changedInput schema / properties / sort_field / description
      Previous value: -"Field to sort by; needs sort_order"New value: +"Field to sort by. Needs sort_order. Default: Sirv's relevance order"
    • changedInput schema / properties / sort_order / description
      Previous value: -"Sort direction; needs sort_field"New value: +"Sort direction. Needs sort_field"
  2. First observedv0.1.0

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so 'Read-only' largely restates structured data. It does add real context beyond that: the return shape ('matching files with their paths and details'), the sort_field/sort_order pairing constraint, and a 'Credits: free' cost signal.

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 purpose and routing, then a compact 'Inputs:' block covering defaults and the one constraint, then return/cost notes. Every line carries actionable information with no filler.

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?

For a six-parameter search tool with no output schema, the description covers purpose, routing, key parameter constraints, the return payload, and cost. Nothing an agent needs to invoke it correctly 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%, so every parameter is already documented, establishing a baseline of 3. The description only genuinely adds the coupling rule that sort_field and sort_order work only together, while the rest (query required, from default 0, size default 100) repeats schema descriptions.

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?

Names a specific verb and resource (search files in the connected Sirv account) and adds the query syntax hint ('basename:boot or a folder or tag name'). It explicitly distinguishes itself from two siblings by naming them and the condition that selects each, so an agent can route without opening a schema.

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 positive guidance (find a Sirv file path) plus two explicit exclusions with named alternatives: Studio library assets go to sirv_list_assets, single-folder listing goes to sirv_cdn_manage_folder. When/when-not/alternatives are all present.

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