Skip to main content
Glama
Sign In
mcp-variety

mcp-variety

by Muvon
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
VARIETY_MCP_WINDOWNoHow many recent picks and openings are remembered per scope12
VARIETY_MCP_STATE_DIRNoFolder that holds history.json$XDG_STATE_HOME/mcp-variety, or ~/.local/state/mcp-variety

Instructions

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

Call variety_pick before writing each piece of a repeated writing job (posts, replies, emails and so on) and follow the protocol it returns. Use one stable scope label per account or project. Call variety_check on the draft before you hand it over. For approaches matched to each input, a voice and rules per account, and learning from results, see the hosted service Unsame: https://unsame.io

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
variety_pickA

Pick an approach and a form (opening, length, ending) for the next piece of writing.

Call this before writing each piece of a repeated job. kind is one of the ids from variety_kinds. scope is a stable label for the account or project; picks never repeat a recent combination inside one scope. If the returned approach does not suit the input, call again with its id in avoid. Returns the chosen approach and form plus a plain-text protocol to follow while writing.

variety_kindsB

List every kind of writing with its description, its approaches and the values of each form axis.

variety_checkA

Check a draft for common signs of AI writing.

Flags em dashes, stock phrases, "not just X, but Y" constructions, evenly sized sentences and too many exclamation marks. With scope, it also flags an opening that matches a different recent text in that scope, then remembers this opening. Returns issues (rule, excerpt, advice) and ok.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

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

A3.8/5.0

Scored across 3 tools

Disambiguation5/5

Each tool has a clearly distinct role: variety_kinds enumerates options, variety_pick selects an approach/form, and variety_check audits a draft. The boundaries are explicit and an agent can easily choose the right tool for each step.

Naming Consistency4/5

All tools share the predictable variety_ prefix, with pick and check using verb forms. variety_kinds is noun-oriented, a minor deviation, but the naming remains readable and consistent overall.

Tool Count5/5

Three tools map cleanly to the workflow: discover kinds, pick a combination, then check the draft. The surface is well-scoped and each tool earns its place without excess.

Completeness4/5

The core lifecycle is covered: listing kinds, selecting a varied approach, and checking output for AI-writing patterns. Minor gaps exist around inspecting or resetting scope history, but these are not fatal to the stated purpose.

Maintenance

ActivityMaintained
ResponsivenessNo recent community issues

Resources