Skip to main content
Glama

seafile_search

Read-only

Search self-hosted Seafile libraries, file names and content, users, groups, and published repos via Seafile API endpoints.

Instructions

seafile_search covers the search toolset (6 route operations). Auth header Authorization Token. Self-hosted Seafile only. seafile.com hosts are refused. Actions: get_items_search: GET /api2/items-search/. GET /api2/items-search/ (ItemsSearch). Body and query are free-form. get_published_repo_search: GET /api/v2.1/published-repo-search/. GET /api/v2.1/published-repo-search/ (PublishedRepoSearchView). Body and query are free-form. get_search_group: GET /api/v2.1/search-group/. GET /api/v2.1/search-group/ (SearchGroup). Body and query are free-form. get_search_user: GET /api2/search-user/. GET /api2/search-user/ (SearchUser). Body and query are free-form. search: GET /api2/search/. Search libraries. Query q is the text. search_file: GET /api/v2.1/search-file/. Search file names and content. Query q is the text.

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": {
      "action": "<action>"
    },
    "name": "seafile_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyNoFree-form JSON or form body. /api2 routes are sent as form fields. /api/v2.1 routes are sent as JSON. Secrets are redacted in previews.
queryNoQuery parameters, such as p for a library path or q for search.
actionYesSeafile operation to call.
paramsNoPath parameters, such as repo_id or group_id.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

C2.8/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description adds genuinely non-obvious behavior: the Authorization Token header requirement, the self-hosted-only restriction, and the encoding split where /api2 routes take form fields while /api/v2.1 routes take JSON. It does not describe result shape or pagination, but the added context is substantive.

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

Conciseness2/5

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

The toolset summary and auth/host notes are correctly front-loaded, but each action entry repeats its endpoint twice ("GET /api2/items-search/. GET /api2/items-search/ (ItemsSearch).") and pads with the identical phrase "Body and query are free-form" six times. That is roughly half the text spent on duplication rather than information.

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

Completeness2/5

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

For a six-action multiplexed tool with no output schema, the description leaves four actions effectively undefined, so an agent cannot tell what get_search_group, get_search_user, get_items_search or get_published_repo_search return or which params they need. Auth, host restriction and body encoding are covered, but the per-action semantics that matter most for correct invocation are 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 description coverage is 100%, so the schema already documents body, query, action and params, making 3 the baseline. The description adds only that "Query q is the text" for two actions, which is a small increment over the schema's own "q for search" note.

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

Purpose3/5

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

The opening line establishes a clear verb+resource ("covers the search toolset") and two actions get real descriptions ("Search libraries", "Search file names and content"). But four of the six actions are only named by their route ("get_search_group: GET /api2/search-group/ (SearchGroup)"), which tells an agent nothing about what they do, and nothing distinguishes this from the seafile_libraries sibling.

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

Usage Guidelines2/5

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

The only guidance is a hosting constraint ("Self-hosted Seafile only. seafile.com hosts are refused"), which is a precondition rather than a when-to-use rule. There is no statement of when to pick search vs seafile_libraries or seafile_files_and_dirs, and no guidance on choosing among the six actions.

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