Skip to main content
Glama
yurii-mandzii

shadow-monitor-mcp

Get user actions

get_user_actions

Retrieve the time-ordered user action timeline from a captured bundle, with flexible filtering and source options.

Instructions

Return the full time-ordered user-action timeline (never just the last action — that lives on stateAtCapture.lastUserAction / bundle_overview). DEFAULT types are the story timeline: click, submit, navigate, toggle, select (plus dblclick/contextmenu/page_load) — NOT raw text inputs. Pass types:["input"] explicitly to see keystroke commits. source "auto" (default) uses semantics.userActions only when that list is genuinely populated (≥3 story actions, or the bundle has type:"action" events); otherwise reconstructs from rrweb so today's thin-semantics bundles still get the full ~20-row story. Explicit source "semantics" / "rrweb" force one path. Response includes actionsSource: "semantics" | "rrweb". Each action includes an rrweb window { fromTs, toTs, anchorId } for get_action_replay. Default limit 50.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoDefault 50.
typesNoFilter to these kinds. Default (story view): click, dblclick, contextmenu, submit, navigate, page_load, toggle, select. Text inputs are excluded unless you pass types:["input"]. Scroll / mousedown / focus need an explicit types request on the rrweb path.
offsetNoDefault 0.
sourceNoAction source: "auto" (default — rich semantics.userActions when available, else full rrweb timeline), "semantics" (force pre-computed list), or "rrweb" (force replay derivation). Never returns only lastUserAction.
bundleIdNoBundle handle from load_bundle. Optional when exactly one bundle is loaded.
Behavior5/5

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

Discloses key behaviors: never last action, default types, source auto logic with thresholds, explicit source options, response includes actionSource, and each action includes rrweb window. No annotations to contradict.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Description is information-dense but front-loaded with main purpose. Every sentence adds value, though slightly dense for quick scanning.

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

Completeness5/5

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

Comprehensive for a read tool: covers default behavior, all parameters, response structure, and integration with other tools (get_action_replay). No output schema needed as return values are described.

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 100%, so baseline 3. The description adds value by explaining default types, source auto decision logic, and clarifying that types exclude raw text inputs by default.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states it returns the full user-action timeline, distinguishes from sibling tools like bundle_overview which gives last action, and mentions get_action_replay for replay windows.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides guidance on when to use this tool (full timeline vs last action) and how to filter by types or source, but does not explicitly exclude other use cases or name alternative tools beyond last action reference.

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

Install Server

Other Tools

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/yurii-mandzii/shadow-monitor-mcp'

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