Skip to main content
Glama
tachyurgy
by tachyurgy

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MCP_HOSTNoHTTP transport bind host0.0.0.0
MCP_PORTNoHTTP transport bind port9000
APP_DB_PATHNoSQLite path for the app (`/data/...` to persist on a volume):memory:
APP_BASE_URLNoWhere the harness reaches the apphttp://localhost:8080
MCP_TRANSPORTNo`stdio` (embedded) or `http` (sandboxed port)stdio
HARNESS_FIXTURENoBaseline for `populate()`fixtures/seed_baseline.json
APP_HTTP_TIMEOUTNoClient timeout (short, so a wedged app fails fast)10

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
{
  "listChanged": true
}
logging
{}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
extensions
{
  "io.modelcontextprotocol/ui": {}
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
create_ticketB

Open a new support ticket. priority ∈ low|normal|high|urgent.

list_ticketsA

List tickets, optionally filtered by status (open|in_progress|closed).

get_ticketB

Fetch a single ticket by id.

assign_ticketC

Assign a ticket to someone; moves it to in_progress.

close_ticketD

Close a ticket.

populateC

Reset the app and load the deterministic baseline fixture.

snapshotB

Capture the full application state as a JSON document.

restoreC

Overwrite application state with a previously captured snapshot.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription
all_ticketsLive view of every ticket — handy as read-only context for an agent.
app_healthLiveness of the application under test.

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/tachyurgy/mcp-app-harness'

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