> ## Documentation Index
> Fetch the complete documentation index at: https://docs.getmcpulse.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Playbooks

> Prompts that work, and what the agent should be doing behind each.

Copy these, or use them as a shape. Each note says which tools a well-behaved agent will reach for.

## The weekly check

```
How is my orders server doing this week?
```

`get_insights` with `last_days: 7`, then `get_overview` for the headline figures.

Insights first is the right order: the panel is sorted worst-first, so the answer starts with what is wrong rather than with a wall of numbers.

## Find the tool worth fixing

```
Which tool on my orders server is costing me the most retries?
```

`list_tools` over 30 days, then `get_tool` on the worst offender.

The useful ranking is calls × failure rate, not failure rate alone — a tool at 20% over 30 calls matters less than one at 60% over 900.

## Diagnose one tool

```
Why is search_orders getting retried so much? Look at the outcome breakdown.
```

`get_tool`. The breakdown separates three different problems: high `bad_args` is a schema problem, high `empty` is a [silent-empties](/insights/silent-empties) problem, and mostly-`ok`-but-still-retried is a description problem.

## Price the server

```
What does my orders server cost someone per conversation, and which tool is
responsible for most of it?
```

`get_overview` with `metrics: ["cost", "sessions", "response_size"]`, then `metrics: ["tools"]` for the per-tool breakdown.

## Find dead weight

```
Which tools on my server has nobody called in the last 90 days, and what is
that costing in schema?
```

`get_insights` with `last_days: 90`. The dead-tool rule prices schema bytes against sessions in range.

Ninety days matters — a tool used monthly is dead in a 7-day window and alive in a 90-day one.

## Compare two periods

```
Compare first-call success on my orders server for the last 14 days against
the 14 before that.
```

`get_overview` with `metrics: ["first_call_success"]` and `last_days: 14`. The deltas are already computed against the preceding window of equal length — the agent should read them rather than making a second call and subtracting.

## Investigate one tool's behaviour in a session

```
What gets called immediately before and after get_customer?
```

`get_tool`, reading `follows`. Nightly, so it lags a day. See [Tool pairs](/metrics/tool-pairs).

## Audit everything

```
Go through every MCP on my account and tell me the single most valuable fix
for each, with the number that justifies it.
```

`list_mcps`, then `get_insights` per MCP.

## Setting a server up

```
Create an MCP called "Acme Orders" on MCPulse, then tell me how to install the SDK.
```

`create_mcp`, then the agent should send you to the dashboard for the key — there is no `create_key` tool, deliberately. See [Tools](/mcp/tools).

## Housekeeping

```
Rename "staging" to "Acme Staging", and revoke the key with prefix mp_live_a1b2.
```

`rename_mcp`, then `revoke_key`. A key is addressed by its **prefix**, which is what `list_keys` shows — an ambiguous prefix is refused rather than guessed, because revoking the wrong key is a silent outage.

```
Invite ada@example.com as an admin — her name is Ada Lovelace.
```

`invite_member`. Give the name: without it the team list shows an address where a person should be.

## Writes and confirmation

Three tools are marked destructive, and your client should confirm before calling them: `delete_mcp`, `revoke_key` and `remove_member`.

Two things worth knowing before you let an agent loose:

**Your role still applies.** A member's agent can read every number and change nothing, refused with the same sentence the dashboard would give. See [Roles and permissions](/team/roles).

**`update_notifications` replaces rather than merges.** Ask the agent to read the current settings first, or every event it leaves out silently falls back to its default:

```
Turn off email for the weekly summary but leave everything else as it is.
```

## Prompting notes

**Name the server.** The tools resolve an MCP by name, so "the orders server" saves a `list_mcps` round trip. Two MCPs with the same name are refused rather than guessed at.

**Say the window.** "This week", "the last 90 days", "March" all work. Without one you get the last 30 days.

**Ask for one metric when you want one metric.** `metrics: ["calls"]` is one small answer; the whole overview is many. A good agent narrows on its own, and saying so helps.

**Say what you want changed, not how.** The connector covers everything the dashboard does except ingest, minting a key and deleting the account. If an agent says it cannot do something, check your role before assuming the tool is missing.

**Expect a day's lag on three figures.** First-call success, retries and tool pairs come from the [nightly pass](/api/concepts/nightly-pass). An agent reading `nightly_as_of` will say so.

## Related

* [Tools](/mcp/tools)
* [Insights](/insights/overview)