Skip to main content
Glama
sixty-sh

@sixty-sh/mcp

Official
by sixty-sh

Install the sixty agent in this project

install_sixty

Fetch installation instructions for sixty matched to your project framework. Select your project kind to receive outcome-based steps that fit your codebase.

Instructions

Fetch the current install instructions from the collector, for the kind of project this is. Call with no kind to see the options. The instructions are written to be followed against a repository you can read: they name outcomes rather than file paths, because where the code goes depends on the framework and putting it in the wrong place fails silently.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
kindNoWhich tier this project is, which is what selects the package. node = a JavaScript or TypeScript server process you control. python = a Python server process: Django, Flask, FastAPI, any WSGI or ASGI app. go = a Go server process: any net/http server with a database/sql driver. ruby = a Ruby or Rails application, or any Rack app. php = a PHP application: Laravel, Symfony, or anything on PDO or MongoDB. browser = a frontend with a server of its own (Next, Remix, SvelteKit). lovable = a frontend with NO server of its own, whose backend is Supabase. A Lovable or Supabase project that has grown a server — an API route, an edge function, a backend added later — takes browser or node instead, which keep the key server-side and measure the server too. react-native = an iOS or Android app. Pick by what the repository actually is, not by what it talks to — the database does not change the answer. Omit to list them.
serviceNoWhat to call this service in sixty. Defaults to the project name.
Behavior3/5

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

With no annotations, the description carries full behavioral burden. It explains that the tool fetches instructions rather than performing an install, and it warns that 'putting it in the wrong place fails silently'. However, it does not explicitly state whether the operation is read-only, what the output format is, or any error conditions. The warning about silent failure adds useful context.

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

Conciseness5/5

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

The description is two sentences long and front-loads the primary action. The second sentence provides important context about how to use the fetched instructions, including a failure mode warning, without any filler. Every phrase earns its place.

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?

For a tool that fetches instructions, the description covers the key contextual nuances: the instructions are project-kind dependent, they should be followed against a readable repository, and they name outcomes rather than file paths. It does not describe the output format or handling of edge cases, but the tool's simplicity and lack of output schema make the description reasonably complete.

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

Parameters4/5

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

The input schema already provides extensive detail for both parameters (100% coverage), so the description does not repeat that. It adds value by advising to omit 'kind' to list options, which enhances parameter usability. It does not add anything for 'service', but the schema already covers that.

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?

The description clearly states the tool fetches install instructions from the collector for the project kind, which distinguishes it from the sibling tools that manage findings and services. The verb is specific ('Fetch') and the resource is 'install instructions', though the title 'Install the sixty agent' suggests a more direct action than fetching instructions, slightly muddying the purpose.

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 description provides a practical usage hint ('Call with no kind to see the options') and explains how the instructions are meant to be followed, but it does not explicitly state when to use this tool versus alternatives or when not to use it. Sibling tools are clearly about findings, so the differentiation is implicit rather than explicit.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/sixty-sh/sixty-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server