Skip to main content
Glama
Sign In

Kloudy

by ai.kloudy
OverviewDiscussionsAdmin

Find MCP tools

find_mcp_tools
Read-onlyIdempotent

Find public MCP servers, tools and SDKs using a few task keywords. Returns a page of up to twenty relevant discovery candidates with their name, source, link, capability tags and a heuristic metadata score. Read-only: does not install, connect, call or run tools. Use ask for a short Kloudy setup request, or introduce for a short description.

Input Schema

NameRequiredDescriptionDefault
goalNoA few task keywords such as postgres, or a short setup request such as install npx kloudy. Exclude personal information and conversation history.
limitNoPage size, default 8. Results are never padded.
offsetNoNext offset returned for this exact goal.
operationNoquery searches candidates; ask returns Kloudy setup links; introduce describes discovery.query

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / limit / description
      Previous value: -"Maximum discovery candidates to return."New value: +"Page size, default 8. Results are never padded."
    • changedInput schema / properties / limit / maximum
      Previous value: -5New value: +20
    • addedInput schema / properties / offset
      Added value: +{
+  "description": "Next offset returned for this exact goal.",
+  "maximum": 999999,
+  "minimum": 0,
+  "type": "integer"
+}
  2. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the bar is lower; the description still reinforces this and adds real substance by describing the return shape (up to twenty candidates with name, source, link, capability tags and a heuristic score). It does not describe rate limits, error behavior, or what happens when a page is empty.

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?

Front-loaded with purpose and scope in the first sentence, then returns, then the read-only guarantee. Every sentence is short and earns its place, though the closing ask/introduce sentence duplicates the operation enum description already present in the schema.

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

Completeness4/5

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

There is no output schema, so the description correctly carries the return-content description, and the safety profile is well covered by annotations plus the explicit read-only sentence. Gaps are minor: no mention of empty-result handling, result ranking meaning, or how deeply offset pagination should be driven.

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 carries goal, limit, offset and the operation enum. The description echoes 'a few task keywords' and the twenty-result page cap but contributes no formatting, syntax or edge-case detail beyond the schema, which is the baseline 3 case.

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

Purpose4/5

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

States a specific verb and resource ('Find public MCP servers, tools and SDKs') plus the input modality ('a few task keywords') and the return payload. It only implicitly separates itself from siblings, via 'does not install, connect, call or run tools', without naming kloudy_connect_card or the kloudy_build_* tools as the place to go for those actions.

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

Usage Guidelines3/5

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

The read-only disclaimer implies 'use something else to install or connect', but no sibling is named and no when-not-to-use rule is given. The 'Use ask ... or introduce ...' sentence is really guidance for the operation enum, which the schema already documents at 100% coverage, so it adds little routing value.

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

All Kloudy toolsInspect
Try in Browser
Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources