Skip to main content
Glama
KuudoAI

amazon-agent-atlas-mcp

by KuudoAI
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
URLYesThe URL of your Kuudo deployment, e.g., https://<your-host>/mcp. Replace <your-host> with the hostname of your deployment.
KUUDO_API_KEYYesYour Kuudo API key, used as a Bearer token in the Authorization header.

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{}
prompts
{}
resources
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
tagsA

Catalog entry. Runs in your Kuudo deployment, not here. List available tool tags. Use to browse available tools by tag before searching.

searchA

Catalog entry. Runs in your Kuudo deployment, not here. Search for available tools by query. Returns matching tools ranked by relevance.

get_schemaA

Catalog entry. Runs in your Kuudo deployment, not here. Get parameter schemas for specific tools. Use after searching to get the detail needed to call a tool.

executeA

Catalog entry. Runs in your Kuudo deployment, not here. Chain await call_tool(...) calls in one Python block and return the final value. Only call_tool(tool_name: str, params: dict) -> Any is available as an external function. Supported imports: asyncio, datetime, json, math, os, pathlib, re, sys, typing. Other standard-library and third-party imports, including collections, are unavailable in the sandbox. Use f-strings because str.format is unavailable. Limits: 10 seconds, 50,000,000 bytes of memory, and recursion depth 100.

Prompts

Interactive templates invoked by user choice

NameDescription
connectHow to connect a client to your Kuudo deployment of this server.

Resources

Contextual data attached and managed by the client

NameDescription
Tool catalogThe 4-tool catalog this stub serves, as JSON.
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.9/5.0

Scored across 4 tools

Disambiguation4/5

The tools are mostly distinct: tags and search both help discover tools, but by different routes (tag browsing vs. query search). get_schema and execute are clearly separate for detail retrieval and execution. Minor overlap exists between tags and search, but descriptions sufficiently clarify the difference.

Naming Consistency3/5

Names are simple and lowercase, but not fully consistent: 'tags' is a noun while 'search', 'get_schema', and 'execute' are verbs (or verb_noun in the case of get_schema). There is no chaotic mixing of conventions, but the pattern is not uniform.

Tool Count5/5

With 4 tools, the set is well-scoped for its purpose: discover by tag, search, get schema, and execute. Every tool serves a distinct role in the workflow and none is superfluous.

Completeness4/5

The set covers the core lifecycle of browsing, searching, schematizing, and executing remote tools. A minor gap is the lack of a direct 'list all tools' operation; discovery relies on tags or search, but the workflow is otherwise complete.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources