Skip to main content
Glama

search_extensions

Search the Comfy Registry for node packs and see which are already installed before cloning, so you can plan installs without downloading repositories.

Instructions

Search the Comfy Registry for a node pack, and say which ones are already here.

The registry answers before anything is cloned, which is what makes this the first step rather than a convenience: each hit carries the pack's own dependencies, so plan_packages can be asked what installing it would move while the pack is still a row in somebody else's database. Cloning a repository to find out what it wants is the thing this ordering exists to avoid.

installed on a hit means an enabled copy of that same pack is already here, compared by registry id and git remote rather than by folder name. A disabled copy is reported separately, since it is not a conflict - it is a pack somebody switched off, and re-installing over it is rarely what they meant.

This reaches api.comfy.org, which is a third host: it can answer while PyPI is unreachable, and it can be down while ComfyUI is fine.

Args: query: what to search for - a name, part of one, or a subject like "video". limit: hits per page, at most 100. page: which page of the result, 1-based. total says how many there are.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pageNo
limitNo
queryYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.10

TDQS

A4.9/5.0
Behavior5/5

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

With no annotations, the description carries the full behavioral burden and does so well: it discloses that the tool reaches api.comfy.org as a third host, can answer while PyPI is unreachable, and can be down while ComfyUI is fine. It also explains the exact meaning of 'installed' compared by registry id and git remote and the distinction for disabled copies.

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 description is front-loaded with the core purpose and uses clear markdown structure, but the rationale paragraphs are longer than strictly necessary for a search tool. Most sentences add useful context, though the explanation of why ordering matters is somewhat discursive.

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?

Given the absence of annotations, the 0% schema description coverage, and the presence of an output schema, the description is complete enough for correct invocation. It covers purpose, usage context, parameter meanings, host behavior, and installed-state semantics without needing to explain return values.

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

Parameters5/5

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

Schema description coverage is 0%, so the description's Args section fully compensates. It explains query content, limit as hits per page with a maximum of 100, and page as a 1-based page selector while noting total indicates how many results exist.

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 first sentence gives a specific verb and resource: search the Comfy Registry for a node pack, and report which are already installed. It distinguishes itself from siblings such as install_extension and plan_packages by framing itself as the registry-first step before cloning.

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 explicitly states when to use it: as the first step before cloning, because the registry can answer while the pack is still a row in somebody else's database. It also names plan_packages as the follow-up and distinguishes enabled installed copies from disabled ones.

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