Skip to main content
Glama
Sign In
Cat Burglar

Cat Burglar

by DrMkdaddy
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Site memory

memory

Store per-origin selector hints, notes, and reusable workflows; learn recent action sequences for replay and auto-inject top hints during navigation.

Instructions

Per-origin memory for selector hints, notes, and reusable workflows. Entries are agent-authored only (never page text). navigate injects the top hints automatically. Use learn after a successful run to save the recent action sequence as a workflow; verify selectors before replaying them.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "action": "<action>"
    },
    "name": "memory"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNoEntry id for get/remove.
kindNo
nameNoWorkflow or hint name.
textNoHint/note text (bounded, control chars stripped).
limitNo
stepsNoWorkflow steps. Omit on learn to use the recent action log.
actionYes
originNoCanonical origin, e.g. https://example.com. Defaults to the current page.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

With only readOnlyHint=false supplied, the description adds real behavioral context: entries are agent-authored and never scraped page text (a trust boundary), `learn` can synthesize steps from the recent action log when `steps` is omitted, and hints are auto-injected by a sibling tool. It omits destructiveness details (whether `clear` is origin-scoped or total, whether it is reversible) and any size/rate limits.

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?

Three tight sentences with no filler: identity and scope first, then the cross-tool injection fact, then the learn/verify guidance. Every sentence carries information an agent would otherwise have to guess.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Six distinct actions are packed into one tool with no output schema, yet the description never describes what `list`, `get`, or `learn` return or how results are shaped. The mutation side (remove/clear) and its consequences are also unexplained, so the definition is workable but leaves material gaps for a multi-action tool.

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?

Schema coverage is 63%, and the description compensates by mapping the `kind` enum to concrete meanings (selector hints, notes, reusable workflows) and by explaining the origin scoping and the omit-`steps`-on-learn behavior. It still leaves `id`, `name`, `limit`, and the args of `steps` to the schema.

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 names the resource precisely — a per-origin store of selector hints, notes, and reusable workflows — which is more than a restatement of the name 'memory'. It does not enumerate the six actions (list/get/put/remove/clear/learn) or state the verb for each, so the agent must open the schema to learn the operation set.

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?

It gives one concrete workflow rule ('Use `learn` after a successful run') and one lifecycle fact ('`navigate` injects the top hints automatically'), plus a caution to verify selectors before replaying. It never says when to prefer `put` over `learn` or `note`, when to `get` versus `list`, or when the store should not be used at all — usage is implied rather than routed.

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

Deploy Server

Other Tools