Skip to main content
ShoulderTap is configured by a single shouldertap.yaml file (generated by shtap init). Every command takes --config to point at a different path; it defaults to shouldertap.yaml in the current directory. Secrets are never stored in the config. Each *_env key names an environment variable that ShoulderTap resolves at runtime, loaded from a local .env file (gitignored) next to the config.

​
Example

shouldertap.yaml

​
Settings

​
org

​
string
required
Your organization’s display name. Used in expert-facing messages.
​
string
default:"UTC"
IANA timezone (for example America/Los_Angeles). Quiet hours are evaluated in this timezone.

​
llm

Optional. Without it, ShoulderTap runs without an LLM: it passes an expert’s reply through verbatim instead of drafting the outbound question or structuring the answer. The provider is resolved by litellm, so any supported model works.
​
string
The model id, for example claude-sonnet-4-6.
​
string
Name of the environment variable holding the provider API key (for example ANTHROPIC_API_KEY).

​
slack

Optional; required only for --transport slack. See Connect Slack.
​
string
Name of the environment variable holding the Slack bot token (for example SLACK_BOT_TOKEN).
​
string
Name of the environment variable holding the Slack signing secret (for example SLACK_SIGNING_SECRET).

​
server

​
integer
default:"8776"
Port the HTTP API and approval UI listen on.
​
string
default:"SHOULDERTAP_API_TOKEN"
Name of the environment variable holding the static bearer token that consumers, the CLI, and the MCP server use to authenticate. See Authentication.
If the variable named by server.api_token_env is unset, the API runs with authentication disabled — every request is accepted. ShoulderTap logs a warning on startup. Always set the token before exposing the server beyond localhost.

​
defaults

Fallback values the router applies to any request that doesn’t set them explicitly in its routing_policy.
​
duration
default:"2h"
How long to wait for a reply before re-asking the expert’s escalation_to. Shorthand like 2h in YAML; the wire protocol uses ISO-8601 (PT2H).
​
duration
default:"24h"
How long to wait across all asks before failing the request with reason timeout.
​
array
default:"null"
A [start, end] pair of local times, for example ["18:00", "09:00"]. No DMs are sent during quiet hours; asks are queued and sent when the window reopens. null disables quiet hours.
​
integer
default:"3"
Hard cap on how many unanswered asks an expert can have at once. Routing skips capped experts.
​
integer
default:"5"
Hard cap on asks sent to one expert in a single day. The daily count resets at the start of each day.

​
experts

The expert registry — an array of the humans ShoulderTap can ask. See Experts and routing for how matching works.
​
string
required
The expert’s Slack user ID (any string with the console transport).
​
string
required
Display name, used in outbound asks and in the answer’s provenance.
​
array
required
Topics this expert answers. Matched against a request’s normalized topic.
​
string
default:"null"
The id of another expert to re-ask if this one doesn’t reply within escalation_after.

​
topics

A map of topic name to per-topic settings.
​
string
default:"null"
The expert id to route to when no expert exactly or fuzzily matches this topic.

​
Secrets (.env)

Copy .env.example to .env and fill in the values. The variable names are referenced by the *_env keys above; the values live only in .env.
.env
PUT /experts rewrites the experts: section of shouldertap.yaml — the config file stays the source of truth for the registry. See the Experts endpoint.