Skip to main content
Glama
Sign In
huly-mcp-selfhost

huly-mcp-selfhost

by JoKeks2023
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

search

Read-only

Find issues, docs, messages, cards, and files across a Huly workspace by full-text query; filter to issues only with status.

Instructions

Fulltext search across all content (issues, docs, messages, cards, files …); issues only, with status: search_issues

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": "search"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindsNoissue, document, message, card, file, person, organization, test-case, attachment or a class id
limitNo
queryYes
workspaceNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv3.5.1

TDQS

A3.9/5.0
Behavior3/5

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

The readOnlyHint annotation already establishes that the operation is non-mutating, and the description adds full-text, cross-content scope. It does not explain matching or ranking behavior, default workspace scope, pagination, or result contents, so its additional behavioral disclosure remains limited.

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?

The definition is compact, front-loaded, and free of filler, with the sibling routing rule placed immediately after the purpose. The shorthand “issues only, with status: search_issues” is slightly cryptic; a full clause would make that condition clearer without adding much length.

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

Completeness3/5

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

The description is sufficient to select the tool and make a basic query-based call, with read-only behavior supplied by annotations. For a four-parameter search tool with no output schema, however, the missing query semantics, workspace scoping, and result or pagination context leave clear invocation gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With only 25% schema description coverage, the description needs to compensate, but it mostly repeats resource examples already documented for kinds. “Fulltext” adds a little meaning for query, yet there is no guidance on query syntax, workspace values or default scope, or how limit relates to pagination.

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?

“Fulltext search across all content” states a specific operation and broad resource scope, while the parenthetical identifies representative content types. The final clause also distinguishes the tool from search_issues for status-oriented issue searches.

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?

It provides an explicit routing rule: use this tool for cross-content full-text search, but use search_issues when searching only issues with status. Although other selection boundaries are not covered, the named alternative addresses the most important sibling distinction.

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

Deploy Server

Other Tools